Skip to content
Space Robotics

Autonomous Navigation

Autonomous navigation is the onboard selection of the next drive step from stereo range data, without a human having seen the terrain. It exists because a rover commanded once per sol can only be driven blind as far as the previous sol’s imagery resolves the ground, and because the round trip light time forbids a human in the control loop [1]. The environment makes it hard in three ways: the processors are radiation-hardened parts a generation or more behind terrestrial hardware, the power budget does not allow sensors and CPU to run continuously [7], and the cost of a wrong decision is a vehicle that cannot be recovered.

Design space and where flight converged

Section titled “Design space and where flight converged”

Four families of approach appear in the corpus. They differ in what they compute from the sensor data and in how far each has progressed.

Geometric hazard maps with local arc scoring. Stereo or laser range is turned into a grid of step, tilt and roughness hazards, and candidate arcs are scored against it. The lineage runs from the Stanford Cart, which built a sparse three-dimensional model of its obstacles from camera slides and drove around them [11], through Sojourner, which stopped every 7 cm of traverse to difference laser-stripe images and detect hazards [15], to GESTALT on MER and MSL [1][2]. Pre-launch evaluation of the Pathfinder system separated goal designation, localization, hazard detection and path selection and measured each [14]. This family has flown on every Mars rover.

Global graph search over a cost map. Local scoring fails when a dead end is larger than the sensor range. A FIDO test campaign showed local avoidance detecting every rock in a semicircle and still failing to reach a goal behind it [36]. Field D*, built on the D* incremental replanner [10], was added to the MER flight software in 2006 to remove that failure mode, at about 3 percent extra time per drive step in ground testing [26], and became part of Curiosity AutoNav [2]. State-lattice planners reached 10 Hz replanning on a FIDO prototype [7]. Sampling planners such as the rapidly-exploring random tree [13] and potential-field methods [12] come from outside planetary robotics. Potential fields carry the local-minimum failure their author states [12]. The corpus holds no flight use of either.

Terrain-adaptive and learned traversability. Geometry does not say whether sand will hold a wheel. Proposals include fuzzy traversability indices built from slope and rock concentration [18], applied to stereo imagery in a rover demonstration [17]; vibration classifiers on wheel-terrain contact [27][37]; learned slip prediction integrated with D* planning and slip-compensated path following in a design that was never run as a whole system [25]; a computational slip model for MER planning [24]; a random-forest classifier of wheel-relevant terrain classes for Curiosity imagery motivated by wheel damage [29]; and the AI4Mars dataset of about 326,000 crowdsourced labels over 35,000 Curiosity, Opportunity and Spirit images [30]. Terrain-aware traverse planning for a Mars Sample Return rover has been evaluated only in simulation [32]. A confidence-aware exploration planner for lunar terrain has been run only in simulated arenas [38]. What has flown is narrower: a wheel speed controller hot-patched onto Curiosity in 2017 to reduce wheel forces, with 3.6 km of in-flight telemetry comparison [31]. The learned ENav heuristic discussed below is likewise simulation only [4]. A vision-language model that classifies terrain complexity from camera images and switches between three navigation modes was evaluated only in Gazebo simulation, with a 79.5 percent efficiency gain over a conservative-only baseline on one mixed-terrain traverse and no onboard compute reported [43]. A neural radiance field trained on drone imagery as an onboard global map, with stereo-derived local costs interpolated over it, was tested only in simulated Moon and Mars scenes, with three runs per arm [42].

Extreme-terrain and non-wheeled platforms. Planners for a tethered rappelling rover run in simulation over states that carry the anchor history, and the field version omitted the tether constraint [34]. A wheel-on-limb rover ran LiDAR SLAM and ABIT* planning on salt terrain in Death Valley as a Europa analogue [35]. Neither has a flight counterpart.

Supporting this are localization and perception. Visual odometry on the MER Navcam pairs converged 97 percent of the time on Spirit (590 of 609 attempts) and 95 percent on Opportunity (828 of 875), correcting slips as large as 125 percent on a 25 degree slope [22]. Earlier work on slip-compensating path following fused visual odometry, IMU and vehicle kinematics on a rocker-bogie test rover, off flight hardware [23]. Global localization against orbital maps by matching a CNN-segmented skyline to one rendered from a HiRISE elevation model was demonstrated on Perseverance imagery and reported in image-space error rather than meters [33]. Field datasets for benchmarking such methods include a 10 km Devon Island traverse with differential GPS truth [39] and Moroccan Mars-analog trajectories [40].

What converged in flight is the first two families, and the reason is cost. Every flown rover has paid for stereo and map building on a slow processor, and the designs that flew were the ones whose cost could be bounded and tested on the ground. Learned methods add a model footprint and inference cost on flight processors that none of the corpus works gives.

What it computes

Section titled “What it computes”

Input is one or more stereo pairs, the current pose estimate, a goal waypoint and a set of human-specified keep-in and keep-out zones. Output is a single arc or turn-in-place command and an updated traversability map. The Mars rovers have used two generations of the same decomposition: build a geometric hazard map from stereo range, score a set of candidate motions against it, execute one, repeat [1][2][4].

GESTALT, MER and MSL

Section titled “GESTALT, MER and MSL”

GESTALT (Grid-based Estimation of Surface Traversability Applied to Local Terrain) fits rover-sized patches of the stereo point cloud to a plane and evaluates three hazard classes against it: step obstacles, taken as large elevation deltas from the best fit plane; tilt hazards, taken as a large angle between the surface normal and the up vector; and roughness, taken as the residual of the planar fit [1]. The result is a rover-centred traversability grid, 10 x 10 m on Spirit and 12 x 12 m on Opportunity, both at 0.2 m cells, and as many as ten separate point clouds could be accumulated before an assessment was run.

Stereo feeds it. MER used a windowed 1D search along epipolar lines with a sum of absolute differences metric on images captured binned at 1024x256 and downsampled and rectified to 256x256 [1]. Spirit typically used the 125 degree field of view front and rear HazCams for about 15,000 3D points per pair, Opportunity the 45 degree NavCams for about 48,000.

Curiosity kept GESTALT with a coarser grid, a World Map at 40 x 40 cm cells over 10 x 10 m, updated at the end of each drive step from one HazCam pair and several NavCam pairs [2]. Forward mapping takes three NavCam pairs at -54, -14 and +26 degrees azimuth covering 2.5 to 10 m, plus a front HazCam pair covering 0.3 to 3 m, all captured at 256x1024 and processed at 256x256 [2]. Backward mapping is more expensive because the rear HazCams must be supplemented by two 30 degree turns in place, each producing a near pair at 256x256 and a horizon pair processed at 192x1024.

Curiosity added a global planner. After each drive step the World Map is merged into a Global Map at the same resolution over a default 50 x 50 m, and a version of Field D* selects a globally optimal path across it [2]. Planning is done in the 2.5D world model with no prediction of future slip. Four path selection strategies are available: Directed, which ignores the map; Guarded, which drives at the goal but halts before entering a hazard or keep-out cell; AvoidKOZ, which avoids only human-specified keep-out zones; and AutoNav, which avoids both. Waypoint-style driving was used in 33.2 percent of the first seven years of attempted drives [2].

The optimality that D* guarantees is optimality at every state of the traverse with respect to all information known at that step, conditional on the arc cost corrections received from the sensor being correct and on the robot’s state in the graph being known exactly [10]. Neither condition is met on a rover: the map is built from stereo range with a noise floor that grows with distance and an occluded footprint, and the pose feeding it carries the slip and localization error that visual odometry exists to bound. The speedup that made incremental replanning affordable, close to 300 times faster than brute-force replanning with A* on a 1,000,000-state grid, was measured in simulation on randomly generated grids with an idealized omnidirectional sensor of 10 states radius and perfect detection inside it, timed on a 1994 workstation, and the author states it depends strongly on obstacle density and on the ratio of known to unknown obstacles [10].

ENav and Approximate Clearance Evaluation, Mars 2020

Section titled “ENav and Approximate Clearance Evaluation, Mars 2020”

ENav replaces the goodness-grid-plus-arc-vote scheme with an explicit search over a tree of candidate paths and a separate safety oracle [4]. The planning cycle is: process disparity into a 2.5D heightmap centred on the rover; assign each cell a traversal cost, infinite inside a keep-out zone and finite but elevated for unimaged terrain; rank the candidate path tree by a cost that combines maneuver time, sampled terrain cost and a Dijkstra estimate of cost to go from the path end to the global goal; run Approximate Clearance Evaluation on paths in ascending cost order; actuate the first maneuver of the cheapest ACE-validated path.

The default tree is 14 candidate turns in place including the null turn, followed by two levels of 11 3 m arcs of varying curvature, 1694 paths in total, planning about 6 m ahead [4]. ACE takes the rover pose and the heightmap, finds the minimum and maximum terrain height inside the potential footprint of each wheel, and returns infinite cost if the resulting attitude and clearance bounds violate parameterized limits.

The ENav algorithm is documented in full in a journal account covering flight results through sol 1312 (28 October 2024): average driving speed rose from Curiosity’s 17.3 m/h to about 92 m/h, and AutoNav drove over 90 percent of 32.1 km [41]. It also describes two-stage path selection, wheel bounding-box expansion for robustness against slip, and Monte Carlo and Mars Yard verification [41].

Cost on flight hardware

Section titled “Cost on flight hardware”
Spirit and OpportunityCuriosityPerseverance
Autonomy processor20 MHz RAD6000133 MHz RAD750133 MHz RAD750 plus Virtex-5QV on a second RAD750 board
RAM128 MB128 + 512 MB128 MB x2 plus 512 MB x2
Stereo pixels per step10,000 to 50,00040,000 to 200,000240,000 to 1,200,000 on the FPGA
Autonomous navigation pause per stepabout 120 sabout 120 stypically 0 if not steering
Speed penalty against directed driving4 to 10 times slower4 to 10 times slowernone reported

Sources: [5] Table 1 for the hardware and pause columns, [3] for the speed penalty on MER and MSL, [6] for the Mars 2020 entry.

At most 75 percent of the MER RAD6000 was available to autonomy software, and dynamic allocation was discouraged, leaving fixed pools of 4 MB, 9 MB and up to ten further 2 MB blocks whose use cut into the memory available for image processing [1]. The same processor ran more than 90 concurrent VxWorks tasks, and instrument interfaces were not optimized for speed: acquiring one image and storing it in RAM took a minimum of 5 s [7]. MSL was expected to generate about 100 W on average, which does not permit keeping every sensor powered and the CPU highly utilized for long.

ENav’s cost is dominated by ACE. Each evaluation takes an estimated 10 to 20 ms on the Perseverance RAD750 [4]. The baseline configuration averaged 275 evaluations per planning cycle in benign terrain and 377 in complex terrain, about 4.5 s of ACE per cycle [4]. ENav is defined to be overthinking when a cycle exceeds 275 evaluations, roughly 3 to 4 s of computation, which forces the rover to stop until a path is found; Monte Carlo simulation predicted a 20.0 percent overthink rate in complex terrain and rare exceedance in benign terrain. Evaluating the entire 1694 path tree at 25 cm intervals would call ACE more than 22,000 times and take over 3 minutes [4].

Two heuristics were tested against that budget over 780 Monte Carlo trials per terrain class [4]. A gradient convolution heuristic using Sobel operators cut complex-terrain path inefficiency from 25.4 to 19.9 percent and the overthink rate from 20.0 to 14.2 percent, at a success rate of 67.1 against a 69.9 percent baseline. A learned ACE-probability heuristic reached 72.5 percent success, 20.4 percent inefficiency and a 7.1 percent overthink rate [4]. With no minimum evaluation count, the learned heuristic cut complex-terrain ACE evaluations from 377 to 90, about 1.1 s rather than 4.5 s per cycle. No trial in any experiment failed through a violated safety constraint; all failures were timeouts or no-path outcomes.

Measured performance

Section titled “Measured performance”

Early flight timings set the scale. On the 20 MHz RAD6000, one autonomous decision to perceive, detect hazards, choose a direction and execute a 35 cm step took 97 s on Spirit [21]. Stereo matching at 256x256 took 24 to 30 s per pair, a full GESTALT cycle about 70 s, and visual odometry about 160 s per step [20]. Pre-launch software timing measured speed and not detection accuracy [19]. FPGA stereo and visual odometry co-processors were later tested on a prototype rover to remove that pause. The MSL-equivalent speeds quoted for them are scaled from RAD6000 timings, not measured on a RAD750 [28].

MER used onboard terrain assessment for 1354 of Spirit’s 4798 m and 1379 of Opportunity’s 5947 m as of 15 August 2005, about 25 percent of distance for both [1]. Spirit’s longest commanded drive was 124 m on sol 125, 62 m directed followed by 62 m under Terrain Assessment and Local Path Selection [1]. Nearly a third of Spirit’s traverse to the Columbia Hills was driven under Terrain Assessment, and it reached the hills about 50 percent sooner than directed driving alone would have allowed. Opportunity’s longest planned drive covered 390 m over sols 383 to 385, of which 284 m was autonomous in 70, 104 and 110 m increments with no commands sent after the first sol [1].

Curiosity accumulated 1116.7 m of AutoNav odometry in total by 14 April 2022, limited by wheel damage and by sampling priorities rather than by the algorithm [5]. Perseverance drove 4802 m of AutoNav odometry during the 31 sol Rapid Traverse Campaign alone, 94.8 percent of the campaign’s 5063.4 m, at an average 79.7 m/h over a modeled 2.98 h of driving per sol [5]. Strategic planning for that campaign assumed peak AutoNav rates of 200 to 250 m/sol, and chose a 4.8 km route over a 2.4 km one on that basis, because the shorter route crossed the Seitah ripple field where AutoNav was expected to yield under 50 m on many sols. Mid-drive waypoints were set about every 120 m [5].

Perseverance drive modeDistance to sol 1710DurationEffective rateShare of odometryLongest sol
AVOID_ALL31,857.00 m343.76 h92.67 m/h75.28 percent403.00 m, sol 1540
GUARDED257.05 m2.81 h91.32 m/h0.61 percent39.00 m, sol 1292
UNGUARDED9910.53 m120.20 h82.45 m/h23.42 percent93.32 m, sol 1288
AVOID_KOZ0.00 m0.00 hnot used0.0 percentnone

Source: [6], Table 1. AVOID_ALL avoids both stereo-detected geometric hazards and human-specified keep-out zones; GUARDED runs the same onboard terrain assessment and visual odometry but stops rather than steering around an obstacle; UNGUARDED follows the uplinked path and ignores whatever image processing is enabled.

The 9.6 m/h gap between AVOID_ALL and UNGUARDED is the entire remaining cost of onboard hazard avoidance on Perseverance, against the 4 to 10 times penalty carried by MER and Curiosity [3][6]. Records set under autonomy include 319.786 m on sol 351, 520.499 m in a single plan on sol 399, 528.7 m over sols 404 to 405, 699.9 m over sols 407 to 409 with no human path input across three sols of driving, and 411.7 m on sol 1540 of which 403 m was autonomous [5][6].

Failure modes

Section titled “Failure modes”

Conservatism against unknown terrain is the dominant one. M2020 AutoNav depends on mast-mounted NavCam stereo, and sand features produce gaps in the onboard stereo results; in complex terrain with dense rocks, frequent outcrops or coverage gaps, the conservative hazard assessment reduces path efficiency and can stop progress entirely [5]. The sol 385 drive terminated on a no-path fault after AutoNav determined there was no route to the goal [5][8].

Position uncertainty propagates into the map. Perseverance grows every human-specified keep-out zone by the accumulated position uncertainty, which is assumed at 5 percent of distance driven when visual odometry converges and 50 percent when it does not, so a run of convergence failures inflates the keep-out geometry until the planner can no longer find a corridor [8][9]. Onboard global localization against orbital maps exists to reset that term [8].

The planner has no slip model. Curiosity’s global path planning runs in the 2.5D world model without predicting future slip [2], and the ENav work attributes the path inefficiency of the baseline to ACE finding narrow safe paths that disappear once slip occurs, forcing backtracking or tight turns [4].

Mapping cost shapes the drive pattern rather than the map. Curiosity’s autonomous imaging capabilities can be used together but in practice are used independently, because combining them costs seconds of extra image processing plus mast repointing that can only happen while the vehicle is stopped [2]. Backward AutoNav is the extreme case, requiring two 30 degree turns in place per mapping cycle.

What is not established

Section titled “What is not established”

The corpus holds no measured obstacle detection or false alarm rate for the MER stereo hazard detector [19][20]. The learned ENav heuristic has been run only in a ROS simulation; its RAD750 timings are arithmetic conversions from evaluation counts, and the model’s memory and inference cost on the flight processor are not given [4]. Terrain classification methods for slip and wheel damage [25][29][32] have no flight record as navigation inputs, and the classifier evidence cited here reports no accuracy for the Curiosity case [29]. The vibration classifiers were tested at walking pace on Earth, in air, on non-regolith surfaces [27][37]. Tethered and wheel-on-limb planners were validated in simulation or Earth analogue geometry only [34][35]. The MER-era slip model [24] and the rover localization and odometry results of the Mars Sample Return era [16] report their results qualitatively or from single runs. The optimality guarantee of D* is conditional on exact state knowledge, which a rover does not have [10].

References

  1. Maimone, M. W., Leger, P. C. and Biesiadecki, J. J. (2007). Overview of the Mars Exploration Rovers' Autonomous Mobility and Vision Capabilities . IEEE International Conference on Robotics and Automation, Space Robotics Workshop. Source
    BibTeX
    @inproceedings{maimone2007overview,
  title = {Overview of the Mars Exploration Rovers' Autonomous Mobility and Vision Capabilities},
  author = {Maimone, Mark W. and Leger, P. Chris and Biesiadecki, Jeffrey J.},
  booktitle = {IEEE International Conference on Robotics and Automation, Space Robotics Workshop},
  address = {Rome, Italy},
  year = {2007},
  url = {https://www-robotics.jpl.nasa.gov/media/documents/mer_autonomy_icra_2007.pdf}
}
  2. Rankin, A., Maimone, M., Biesiadecki, J., Patel, N., Levine, D. and Toupet, O. (2021). Mars Curiosity Rover Mobility Trends During the First Seven Years . Journal of Field Robotics, 5. Source
    BibTeX
    @article{rankin2021mars,
  title = {Mars Curiosity Rover Mobility Trends During the First Seven Years},
  author = {Rankin, Arturo and Maimone, Mark and Biesiadecki, Jeffrey and Patel, Nikunj and Levine, Dan and Toupet, Olivier},
  journal = {Journal of Field Robotics},
  volume = {38},
  number = {5},
  pages = {759--800},
  year = {2021},
  doi = {10.1002/rob.22011},
  abstract = {Abstract NASA's Mars Science Laboratory (MSL) Curiosity rover landed on Mars on August 6, 2012. In the 7 years between landing and August 6, 2019 (sol 2488), Curiosity has driven 21,318.5 m over a variety of terrain types and slopes, employing multiple drive modes with varying amounts of onboard autonomy. Curiosity's drive distances each sol have ranged from its shortest drive of 2.6 cm to its longest drive of 142.5 m, with an average drive distance of 28.9 m. Real‐time human intervention is not possible during Curiosity's drives due to the latency in uplinking commands and downlinking telemetry. Instead, the operations team relies on Curiosity's fault protection, autonomous navigation, and visual odometry software to keep the rover safe during drives. During its first 7 years on Mars, Curiosity has attempted 738 drives. While 622 drives ran to completion, 116 drives were prevented or stopped early by Curiosity's fault protection software. The primary risks to mobility success have been wheel damage, wheel entrapment, progressive wheel sinkage, and the potential for hardware or cable failures that result in an inability to command one or more steer or drive actuators. In this paper, we describe Curiosity's mobility subsystem, mobility trends over the first 21.3 km of the mission, operational aspects of mobility fault protection, risks to continued mobility success, and risk mitigation strategies.}
}
  3. Rankin, A., Holloway, A., Sabel, A., Patel, N. and Maimone, M. W. (2022). Visual Odometry Thinking While Driving for the Curiosity Mars Rover's Three-Year Test Campaign: Impact of Evolving Constraints on Verification and Validation . IEEE Aerospace Conference, 20230005759. Source
    BibTeX
    @inproceedings{rankin2022visual,
  title = {Visual Odometry Thinking While Driving for the Curiosity Mars Rover's Three-Year Test Campaign: Impact of Evolving Constraints on Verification and Validation},
  author = {Rankin, Arturo and Holloway, Alexandra and Sabel, Anna and Patel, Nikunj and Maimone, Mark W.},
  booktitle = {IEEE Aerospace Conference},
  number = {20230005759},
  pages = {1-10},
  institution = {NASA},
  year = {2022},
  doi = {10.1109/aero53065.2022.9843487},
  abstract = {Over the first 9 years of the Mars Science Laboratory (MSL) Curiosity rover's surface mission, more than 87% of its driving was performed using Visual Odometry (VO). The benefits of using VO during driving are that it minimizes rover position uncertainty and can be used to monitor wheel slip, halting a drive if excessive wheel slip is occurring. The VO implementation onboard Curiosity acquires and processes VO images in between drive steps while the rover is stationary. A VO Thinking While Driving (VTWD) flight software capability has been developed to enable the processing of VO images during rover driving, increasing the distance Curiosity can drive using VO during a given time period up to as much as 1.75x total distance. Verification and Validation (V&V) of this capability has been challenging due to impacts from the COVID-19 pandemic and unavailability of the JPL Mars Yard outdoor test site. The VTWD V&Vtest procedures were modified to use a small indoor space with Mars-like terrain. This paper describes the 3 year V&V effort under challenging conditions to approve the VTWD capability for use on the Curiosity rover.}
}
  4. Abcouwer, N., Daftry, S., Del Sesto, T., Toupet, O., Ono, M., Venkatraman, S., Lanka, R., Song, J. and Yue, Y. (2021). Machine Learning Based Path Planning for Improved Rover Navigation . IEEE Aerospace Conference. Source
    BibTeX
    @inproceedings{abcouwer2021machine,
  title = {Machine Learning Based Path Planning for Improved Rover Navigation},
  author = {Abcouwer, Neil and Daftry, Shreyansh and Del Sesto, Tyler and Toupet, Olivier and Ono, Masahiro and Venkatraman, Siddarth and Lanka, Ravi and Song, Jialin and Yue, Yisong},
  booktitle = {IEEE Aerospace Conference},
  pages = {1-9},
  address = {Big Sky, Montana},
  year = {2021},
  doi = {10.1109/aero50100.2021.9438337},
  abstract = {Enhanced AutoNav (ENav), the baseline surface navigation software for NASA's Perseverance rover, sorts a list of candidate paths for the rover to traverse, then uses the Approximate Clearance Evaluation (ACE) algorithm to evaluate whether the most highly ranked paths are safe. ACE is crucial for maintaining the safety of the rover, but is computationally expensive. If the most promising candidates in the list of paths are all found to be infeasible, ENav must continue to search the list and run time-consuming ACE evaluations until a feasible path is found. In this paper, we present two heuristics that, given a terrain heightmap around the rover, produce cost estimates that more effectively rank the candidate paths before ACE evaluation. The first heuristic uses Sobel operators and convolution to incorporate the cost of traversing high-gradient terrain. The second heuristic uses a machine learning (ML) model to predict areas that will be deemed untraversable by ACE. We used physics simulations to collect training data for the ML model and to run Monte Carlo trials to quantify navigation performance across a variety of terrains with various slopes and rock distributions. Compared to ENav's baseline performance, integrating the heuristics can lead to a significant reduction in ACE evaluations and average computation time per planning cycle, increase path efficiency, and maintain or improve the rate of successful traverses. This strategy of targeting specific bottlenecks with ML while maintaining the original ACE safety checks provides an example of how ML can be infused into planetary science missions and other safety-critical software.}
}
  5. Rankin, A., Del Sesto, T., Hwang, P., Justice, H., Maimone, M., Verma, V. and Graser, E. (2023). Perseverance Rapid Traverse Campaign . IEEE Aerospace Conference. Source
    BibTeX
    @inproceedings{rankin2023perseverance,
  title = {Perseverance Rapid Traverse Campaign},
  author = {Rankin, Arturo and Del Sesto, Tyler and Hwang, Pauline and Justice, Heather and Maimone, Mark and Verma, Vandi and Graser, Evan},
  booktitle = {IEEE Aerospace Conference},
  pages = {1-16},
  address = {Big Sky, Montana},
  year = {2023},
  doi = {10.1109/aero55745.2023.10115835},
  abstract = {Over the first 13 months of the Mars 2020 mission, the Perseverance rover traversed nearly 5 km along the Jezero Crater floor. Near the end of that period, the Science team was anxious to relocate to the ancient Delta region near the crater rim, over 5 km away. A Rapid Traverse Campaign was planned that would prioritize use of Perseverance's autonomous navigation software to drive at an unprecedented high pace and minimize science activities. The Rapid Traverse Campaign started in March 2022 and lasted 31 Martian days. During the campaign, Perseverance drove over 5 km in 24 drives, during which its autonomy software planned 94.8% of its overall driving, enabling it to set several new planetary rover driving records. Perseverance exceeded the longest daily drive distance record achieved by a previous planetary rover (219 meters) 11 times and set new records for the longest multi-sol drive distance in a single plan (528.7 meters) and the longest continuation drive (699.9 meters) by operating without human drive path input during 3 sols of driving. This paper details the planning and execution of the Rapid Traverse Campaign.}
}
  6. Maimone, M., Verma, V., Rankin, A., Kaplan, K., Carsten, J., Schaler, E., Boroson, E., Graser, E., Srinivasan, T., Nash, J. and Chiu, D. (2026). Roving on the Edge: Robotic Operations Power Perseverance's Ascent of Jezero Crater Rim . Annual AAS Guidance, Navigation and Control Conference. Source
    BibTeX
    @inproceedings{maimone2026roving,
  title = {Roving on the Edge: Robotic Operations Power Perseverance's Ascent of Jezero Crater Rim},
  author = {Maimone, Mark and Verma, Vandi and Rankin, Arturo and Kaplan, Kyle and Carsten, Joseph and Schaler, Ethan and Boroson, Elizabeth and Graser, Evan and Srinivasan, Thirupathi and Nash, Jeremy and Chiu, Darwin},
  booktitle = {Annual AAS Guidance, Navigation and Control Conference},
  year = {2026},
  url = {https://www-robotics.jpl.nasa.gov/media/documents/2026_RO_AAS_final.pdf}
}
  7. Kuwata, Y., Elfes, A., Maimone, M., Howard, A., Pivtoraiko, M., Howard, T. M. and Stoica, A. (2008). Path Planning Challenges for Planetary Robots . IEEE/RSJ International Conference on Intelligent Robots and Systems, Workshop on Planning, Perception and Navigation for Intelligent Vehicles. Source
    BibTeX
    @inproceedings{kuwata2008path,
  title = {Path Planning Challenges for Planetary Robots},
  author = {Kuwata, Yoshiaki and Elfes, Alberto and Maimone, Mark and Howard, Andrew and Pivtoraiko, Mihail and Howard, Thomas M. and Stoica, Adrian},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems, Workshop on Planning, Perception and Navigation for Intelligent Vehicles},
  address = {Nice, France},
  year = {2008},
  url = {https://www-robotics.jpl.nasa.gov/media/documents/Path_Planning_Challenges_for_Planetary_Robots.pdf}
}
  8. Verma, V., Nash, J., Saldyt, L., Dwight, Q., Wang, H., Myint, S., Biesiadecki, J., Maimone, M., Tumbar, A., Ansar, A., Kubiak, G. and Hogg, R. (2024). Enabling Long and Precise Drives for the Perseverance Mars Rover via Onboard Global Localization . IEEE Aerospace Conference. Source
    BibTeX
    @inproceedings{verma2024enabling,
  title = {Enabling Long and Precise Drives for the Perseverance Mars Rover via Onboard Global Localization},
  author = {Verma, Vandi and Nash, Jeremy and Saldyt, Lucas and Dwight, Quintin and Wang, Haoda and Myint, Steven and Biesiadecki, Jeffrey and Maimone, Mark and Tumbar, Andrei and Ansar, Adnan and Kubiak, Gerik and Hogg, Robert},
  booktitle = {IEEE Aerospace Conference},
  address = {Big Sky, Montana},
  year = {2024},
  url = {https://www-robotics.jpl.nasa.gov/media/documents/2024_Global_Localization_IEEE_Aero.pdf}
}
  9. Maimone, M., Cheng, Y. and Matthies, L. (2007). Two Years of Visual Odometry on the Mars Exploration Rovers . Journal of Field Robotics, 3. Source
    BibTeX
    @article{maimone2007two,
  title = {Two Years of Visual Odometry on the Mars Exploration Rovers},
  author = {Maimone, Mark and Cheng, Yang and Matthies, Larry},
  journal = {Journal of Field Robotics},
  volume = {24},
  number = {3},
  pages = {169--186},
  institution = {NASA Jet Propulsion Laboratory},
  year = {2007},
  doi = {10.1002/rob.20184},
  abstract = {Abstract NASA's two Mars Exploration Rovers (MER) have successfully demonstrated a robotic Visual Odometry capability on another world for the first time. This provides each rover with accurate knowledge of its position, allowing it to autonomously detect and compensate for any unforeseen slip encountered during a drive. It has enabled the rovers to drive safely and more effectively in highly sloped and sandy terrains and has resulted in increased mission science return by reducing the number of days required to drive into interesting areas. The MER Visual Odometry system comprises onboard software for comparing stereo pairs taken by the pointable mast‐mounted 45 deg FOV Navigation cameras (NAVCAMs). The system computes an update to the 6 degree of freedom rover pose ( x , y , z , roll, pitch, yaw) by tracking the motion of autonomously selected terrain features between two pairs of 256×256 stereo images. It has demonstrated good performance with high rates of successful convergence (97% on Spirit, 95% on Opportunity), successfully detected slip ratios as high as 125%, and measured changes as small as 2 mm, even while driving on slopes as high as 31 deg. Visual Odometry was used over 14% of the first 10.7 km driven by both rovers. During the first 2 years of operations, Visual Odometry evolved from an “extra credit” capability into a critical vehicle safety system. In this paper we describe our Visual Odometry algorithm, discuss several driving strategies that rely on it (including Slip Checks, Keep‐out Zones, and Wheel Dragging), and summarize its results from the first 2 years of operations on Mars. © 2006 Wiley Periodicals, Inc.}
}
  10. Stentz, A. (1994). The D* Algorithm for Real-Time Planning of Optimal Traverses . Robotics Institute, Carnegie Mellon University, CMU-RI-TR-94-37. Source
    BibTeX
    @techreport{stentz1994algorithm,
  title = {The D* Algorithm for Real-Time Planning of Optimal Traverses},
  author = {Stentz, Anthony},
  number = {CMU-RI-TR-94-37},
  institution = {Robotics Institute, Carnegie Mellon University},
  year = {1994},
  url = {https://www.ri.cmu.edu/pub_files/pub3/stentz_anthony__tony__1994_2/stentz_anthony__tony__1994_2.pdf}
}
  11. Moravec, H. P. (1980). Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover . Carnegie Mellon University, CMU-RI-TR-3 / STAN-CS-80-813 / AIM-340. Source
    BibTeX
    @phdthesis{moravec1980obstacle,
  title = {Obstacle Avoidance and Navigation in the Real World by a Seeing Robot Rover},
  author = {Moravec, Hans P.},
  journal = {Carnegie Mellon University},
  number = {CMU-RI-TR-3 / STAN-CS-80-813 / AIM-340},
  school = {Stanford University},
  type = {Ph.D. dissertation},
  year = {1980},
  doi = {10.1184/r1/6557033.v1}
}
  12. Khatib, O. (1986). Real-Time Obstacle Avoidance for Manipulators and Mobile Robots . Earth and Space Science, 1. Source
    BibTeX
    @article{khatib1986real,
  title = {Real-Time Obstacle Avoidance for Manipulators and Mobile Robots},
  author = {Khatib, Oussama},
  journal = {Earth and Space Science},
  volume = {5},
  number = {1},
  pages = {90-98},
  publisher = {SAGE Publications},
  year = {1986},
  doi = {10.1177/027836498600500106},
  abstract = {This paper presents a unique real-time obstacle avoidance approach for manipulators and mobile robots based on the artificial potential field concept. Collision avoidance, tradi tionally considered a high level planning problem, can be effectively distributed between different levels of control, al lowing real-time robot operations in a complex environment. This method has been extended to moving obstacles by using a time-varying artificial patential field. We have applied this obstacle avoidance scheme to robot arm mechanisms and have used a new approach to the general problem of real-time manipulator control. We reformulated the manipulator con trol problem as direct control of manipulator motion in oper ational space—the space in which the task is originally described—rather than as control of the task's corresponding joint space motion obtained only after geometric and kine matic transformation. Outside the obstacles' regions of influ ence, we caused the end effector to move in a straight line with an upper speed limit. The artificial potential field ap proach has been extended to collision avoidance for all ma nipulator links. In addition, a joint space artificial potential field is used to satisfy the manipulator internal joint con straints. This method has been implemented in the COSMOS system for a PUMA 560 robot. Real-time collision avoidance demonstrations on moving obstacles have been performed by using visual sensing.}
}
  13. LaValle, S. M. (1998). Rapidly-Exploring Random Trees: A New Tool for Path Planning . Department of Computer Science, Iowa State University, TR 98-11. Source
    BibTeX
    @techreport{lavalle1998rapidly,
  title = {Rapidly-Exploring Random Trees: A New Tool for Path Planning},
  author = {LaValle, Steven M.},
  number = {TR 98-11},
  institution = {Department of Computer Science, Iowa State University},
  year = {1998},
  url = {https://msl.cs.illinois.edu/~lavalle/papers/Lav98c.pdf}
}
  14. Matthies, L., Gat, E., Harrison, R., Wilcox, B., Volpe, R. and Litwin, T. (1995). Mars Microrover Navigation: Performance Evaluation and Enhancement . Autonomous Robots, 4. Source
    BibTeX
    @article{matthies1995mars,
  title = {Mars Microrover Navigation: Performance Evaluation and Enhancement},
  author = {Matthies, Larry and Gat, Erann and Harrison, Reid and Wilcox, Brian and Volpe, Richard and Litwin, Todd},
  journal = {Autonomous Robots},
  volume = {2},
  number = {4},
  pages = {291--311},
  year = {1995},
  doi = {10.1007/bf00710796}
}
  15. Matijevic, J. (1998). Autonomous Navigation and the Sojourner Microrover . AIAA ASCEND. Source
    BibTeX
    @inproceedings{matijevic1998autonomous,
  title = {Autonomous Navigation and the Sojourner Microrover},
  author = {Matijevic, J.},
  booktitle = {AIAA ASCEND},
  publisher = {JPL Open Repository},
  year = {1998},
  url = {https://dataverse.jpl.nasa.gov/dataset.xhtml?persistentId=hdl:2014/19052}
}
  16. Volpe, R., Estlin, T., Laubach, S., Olson, C. and Balaram, J. (1999). Enhanced Mars Rover Navigation Techniques . IEEE International Conference on Robotics and Automation. Source
    BibTeX
    @inproceedings{volpe1999enhanced,
  title = {Enhanced Mars Rover Navigation Techniques},
  author = {Volpe, R. and Estlin, T. and Laubach, Sharon and Olson, C. and Balaram, J.},
  booktitle = {IEEE International Conference on Robotics and Automation},
  volume = {1},
  pages = {926-931},
  publisher = {IEEE},
  year = {1999},
  doi = {10.1109/robot.2000.844167},
  abstract = {Robust navigation through rocky terrain by small mobile robots is important for maximizing science return from missions to Mars. We are addressing this problem at multiple levels through the development of intelligent sequencing, sensor constrained path planning, natural terrain visual localization, and real-time state estimation. Each of these techniques is described and their complementary aspects discussed. Experimental results are provided from implementation on our Mars rover prototype operating in realistic scenarios.}
}
  17. Howard, A. and Seraji, H. (2000). Real-Time Assessment of Terrain Traversability for Autonomous Rover Navigation . IEEE/RSJ International Conference on Intelligent Robots and Systems. Source
    BibTeX
    @inproceedings{howard2000real,
  title = {Real-Time Assessment of Terrain Traversability for Autonomous Rover Navigation},
  author = {Howard, A. and Seraji, Homayoun},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  volume = {1},
  pages = {58-63},
  publisher = {IEEE},
  year = {2000},
  doi = {10.1109/iros.2000.894582},
  abstract = {This paper presents a novel technique for real-time measurement of terrain characteristics and incorporation of this information into the navigation strategy of an autonomous mobile robot. The proposed methodology utilizes a fuzzy logic framework for on-board analysis of terrain traversability, and develops a set of fuzzy navigation rules that guide the rover toward the safest and the most traversable terrain. In addition, a simple goal-seeking behavior is used to drive the rover from its initial position to a user-specified goal position. The overall navigation strategy, consisting of terrain-traverse and goal-seeking behaviors, requires no a priori information about the environment, and uses the on-board traversability analysis to enable the rover to select easy-to-traverse paths to the goal autonomously. The terrain traversability navigation rules are tested and validated with a set of physical rover experiments. These experiments demonstrate the real-time capability of the terrain assessment and fuzzy navigation algorithms.}
}
  18. Seraji, H. (1999). Traversability Index: A New Concept for Planetary Rovers . IEEE International Conference on Robotics and Automation. Source
    BibTeX
    @inproceedings{seraji1999traversability,
  title = {Traversability Index: A New Concept for Planetary Rovers},
  author = {Seraji, H.},
  booktitle = {IEEE International Conference on Robotics and Automation},
  volume = {3},
  pages = {2006-2013},
  year = {1999},
  doi = {10.1109/robot.1999.770402},
  abstract = {A traversability index is introduced as a new and simple measure for traversability of planetary surfaces by mobile robots. This index is developed using the framework of fuzzy logic, and is expressed by linguistic fuzzy sets that quantify the suitability of the terrain for traversal based on its physical properties, such as slope and roughness. The traversability index is used for classifying planetary surfaces, and provides a simple means for incorporating the terrain quality data (out to about 10 metres) into the rover navigation strategy. A set of fuzzy navigation rules is developed using the traversability index to guide the rover toward the safest and the most traversable terrain. In addition, another set of fuzzy rules is developed to drive the rover from its initial position to a user-specified goal position. These two rule sets are integrated in a two-stage procedure for autonomous rover navigation without a priori knowledge about the environment. A computer simulation study is presented to demonstrate the capability of the rover to reach the goal safely while avoiding impassable terrains.}
}
  19. Goldberg, S. B., Maimone, M. W. and Matthies, L. (2002). Stereo Vision and Rover Navigation Software for Planetary Exploration . IEEE Aerospace Conference. Source
    BibTeX
    @inproceedings{goldberg2002stereo,
  title = {Stereo Vision and Rover Navigation Software for Planetary Exploration},
  author = {Goldberg, Steven B. and Maimone, Mark W. and Matthies, Larry},
  booktitle = {IEEE Aerospace Conference},
  volume = {5},
  pages = {2025--2036},
  address = {Big Sky, Montana},
  year = {2002},
  doi = {10.1109/aero.2002.1035370},
  abstract = {NASA's Mars Exploration Rover (MER) missions will land twin rovers on the surface of Mars in 2004. These rovers will have the ability to navigate safely through unknown and potentially hazardous terrain, using autonomous passive stereo vision to detect potential terrain hazards before driving into them. Unfortunately, the computational power of currently available radiation hardened processors limits the amount of distance (and therefore science) that can be safely achieved by any rover in a given time frame. We present overviews of our current rover vision and navigation systems, to provide context for the types of computation that are required to navigate safely. We also present baseline timing results that represent a lower bound in achievable performance (useful for systems engineering studies of future missions), and describe ways to improve that performance using commercial grade (as opposed to radiation hardened) processors. In particular, we document speedups to our stereo vision system that were achieved using the vectorized operations provided by Pentium MMX technology. Timing data were derived from implementations on several platforms: a prototype Mars rover with flight-like electronics (the Athena Software Development Model (SDM) rover), a RAD6000 computing platform (as will be used in the 2003 MER missions), and research platforms with commercial Pentium III and Sparc processors. Finally, we summarize the radiation effects analysis that suggests that commercial grade processors are likely to be adequate for Mars surface missions, and discuss the level of speedup that may accrue from using these instead of radiation hardened parts.}
}
  20. Maimone, M., Johnson, A., Cheng, Y., Willson, R. and Matthies, L. (2004). Autonomous Navigation Results from the Mars Exploration Rover (MER) Mission . International Symposium on Experimental Robotics. Source
    BibTeX
    @inproceedings{maimone2004autonomous,
  title = {Autonomous Navigation Results from the Mars Exploration Rover (MER) Mission},
  author = {Maimone, Mark and Johnson, Andrew and Cheng, Yang and Willson, Reg and Matthies, Larry},
  booktitle = {International Symposium on Experimental Robotics},
  address = {Singapore},
  year = {2004},
  url = {https://dataverse.jpl.nasa.gov/dataset.xhtml?persistentId=hdl:2014/41077}
}
  21. Tunstel, E. W., Howard, A., Maimone, M. and Trebi-Ollennu, A. (2005). Mars exploration rover performance as a baseline for flight rover autonomy technology assessment . MTG: IEEE International Conference on Robotics and Automation. Source
    BibTeX
    @inproceedings{tunstel2005marsa,
  title = {Mars exploration rover performance as a baseline for flight rover autonomy technology assessment},
  author = {Tunstel, Edward W. and Howard, Ayanna and Maimone, Mark and Trebi-Ollennu, Ashitey},
  booktitle = {MTG: IEEE International Conference on Robotics and Automation},
  publisher = {JPL Open Repository},
  year = {2005},
  url = {https://dataverse.jpl.nasa.gov/dataset.xhtml?persistentId=hdl:2014/37587}
}
  22. Cheng, Y. and Maimone, M. (2005). Visual odometry on the Mars Exploration Rovers . IEEE International Conference on Systems, Man and Cybernetics. Source
    BibTeX
    @inproceedings{cheng2005visual,
  title = {Visual odometry on the Mars Exploration Rovers},
  author = {Cheng, Yang and Maimone, Mark},
  booktitle = {IEEE International Conference on Systems, Man and Cybernetics},
  volume = {1},
  pages = {903-910},
  publisher = {IEEE},
  year = {2005},
  doi = {10.1109/icsmc.2005.1571261},
  abstract = {NASA's Mars Exploration Rovers (MER) was designed to traverse in Viking Lander-I style terrains: mostly flat, with many small non-obstacle rocks and occasional obstacles. During actual operations in such terrains, onboard position estimates derived solely from the onboard inertial measurement unit and wheel encoder-based odometry achieved well within the design goal of at most 10% error. However, MER vehicles were also driven along slippery slopes tilted as high as 31 degrees. In such conditions an additional capability was employed to maintain a sufficiently accurate onboard position estimate: visual odometry. The MER visual odometry system comprises onboard software for comparing stereo pairs taken by the pointable mast-mounted 45 degree FOV navigation cameras (NAV-CAMs). The system computes an update to the 6-DOF rover pose (x, y, z, roll, pitch, yaw) by tracking the motion of autonomously-selected "interesting" terrain features between two pairs of stereo images, in both 2D pixel and 3D world coordinates. A maximum likelihood estimator is applied to the computed 3D offsets to produce a final, corrected estimate of vehicle motion between the two pairs. In this paper we describe the visual odometry algorithm used on the Mars Exploration Rovers, and summarize its results from the first year of operations on Mars.}
}
  23. Helmick, D. M., Cheng, Y., Clouse, D. S., Matthies, L. H. and Roumeliotis, S. I. (2004). Path following using visual odometry for Mars Rover in high-slip environments . JPL Open Repository. Source
    BibTeX
    @inproceedings{helmick2004path,
  title = {Path following using visual odometry for Mars Rover in high-slip environments},
  author = {Helmick, Daniel M. and Cheng, Yang and Clouse, Daniel S. and Matthies, Larry H. and Roumeliotis, Stergios I.},
  publisher = {JPL Open Repository},
  year = {2004},
  url = {https://dataverse.jpl.nasa.gov/dataset.xhtml?persistentId=hdl:2014/38778}
}
  24. Yen, J. (2007). Slip validation and prediction for Mars Exploration Rovers . JPL Open Repository. Source
    BibTeX
    @inproceedings{yen2007slip,
  title = {Slip validation and prediction for Mars Exploration Rovers},
  author = {Yen, Jeng},
  publisher = {JPL Open Repository},
  year = {2007},
  url = {https://dataverse.jpl.nasa.gov/dataset.xhtml?persistentId=hdl:2014/41348}
}
  25. Helmick, D. M., Angelova, A., Livianu, M. and Matthies, L. H. (2007). Terrain Adaptive Navigation for Mars Rovers . IEEE Aerospace Conference. Source
    BibTeX
    @inproceedings{helmick2007terrain,
  title = {Terrain Adaptive Navigation for Mars Rovers},
  author = {Helmick, Daniel M. and Angelova, Anelia and Livianu, Matthew and Matthies, Larry H.},
  booktitle = {IEEE Aerospace Conference},
  pages = {1-11},
  address = {Big Sky, Montana},
  year = {2007},
  doi = {10.1109/aero.2007.352684},
  abstract = {A navigation system for Mars rovers in very rough terrain has been designed, implemented, and tested on a research rover in Mars analog terrain. This navigation system consists of several technologies that are integrated to increase the capabilities compared to current rover navigation algorithms. These technologies include: goodness maps and terrain triage, terrain classification, remote slip prediction, path planning, high-fidelity traversability analysis (HFTA), and slip-compensated path following. The focus of this paper is not on the component technologies, but rather on the integration of these components. Results from the onboard integration of several of the key technologies described here are shown. Additionally, the results from independent demonstrations of several of these technologies are shown. Future work will include the demonstration of the entire integrated system.}
}
  26. Carsten, J., Rankin, A., Ferguson, D. and Stentz, A. (2007). Global Path Planning on Board the Mars Exploration Rovers . IEEE Aerospace Conference. Source
    BibTeX
    @inproceedings{carsten2007global,
  title = {Global Path Planning on Board the Mars Exploration Rovers},
  author = {Carsten, Joseph and Rankin, Arturo and Ferguson, Dave and Stentz, Anthony},
  booktitle = {IEEE Aerospace Conference},
  pages = {1-11},
  publisher = {IEEE},
  year = {2007},
  doi = {10.1109/aero.2007.352683},
  abstract = {In January 2004, NASA's twin Mars exploration rovers (MERs), spirit and opportunity, began searching the surface of Mars for evidence of past water activity. In order to localize and approach scientifically interesting targets, the rovers employ an on-board navigation system. Given the latency in sending commands from Earth to the Martian rovers (and in receiving return data), a high level of navigational autonomy is desirable. Autonomous navigation with hazard avoidance (AutoNav) is currently performed using a local path planner called GESTALT (grid-based estimation of surface traversability applied to local terrain). GESTALT uses stereo cameras to evaluate terrain safety and avoid obstacles. GESTALT works well to guide the rovers around narrow and isolated hazards, however, it is susceptible to failure when clusters of closely spaced, non-traversable rocks form extended obstacles. In May 2005, a new technology task was initiated at the Jet Propulsion Laboratory to address this limitation. A version of the Carnegie Mellon University Field D* global path planner has been integrated into MER flight software, enabling simultaneous local and global planning during AutoNav. A revised version of AutoNav was uploaded to the rovers during the summer of 2006. This paper describes how global planning was integrated into the MER flight software, and presents results of testing the improved AutoNav system using the MER Surface System TestBed rover.}
}
  27. Brooks, C. A. and Iagnemma, K. (2005). Vibration-Based Terrain Classification for Planetary Exploration Rovers . IEEE Transactions on Robotics, 6. Source
    BibTeX
    @article{brooks2005vibration,
  title = {Vibration-Based Terrain Classification for Planetary Exploration Rovers},
  author = {Brooks, Christopher A. and Iagnemma, Karl},
  journal = {IEEE Transactions on Robotics},
  volume = {21},
  number = {6},
  pages = {1185--1191},
  year = {2005},
  doi = {10.1109/tro.2005.855994},
  abstract = {Safe, autonomous mobility in rough terrain is an important requirement for planetary exploration rovers. Knowledge of local terrain properties is critical to ensure a rover's safety on slopes and uneven surfaces. Visual features are often used to classify terrain; however, vision can be sensitive to lighting variations and other effects. This paper presents a method to classify terrain based on vibrations induced in the rover structure by wheel-terrain interaction during driving. This sensing mode is robust to lighting variations. Vibrations are measured using an accelerometer mounted on the rover structure. The classifier is trained using labeled vibration data during an offline learning phase. Linear discriminant analysis is used for online identification of terrain classes, such as sand, gravel, or clay. This approach has been experimentally validated on a laboratory testbed and on a four-wheeled rover in outdoor conditions.}
}
  28. Howard, T. M., Morfopoulos, A., Morrison, J., Kuwata, Y., Villalpando, C., Matthies, L. and McHenry, M. (2012). Enabling continuous planetary rover navigation through FPGA stereo and visual odometry . AIAA SPACE and Astronautics Forum. Source
    BibTeX
    @inproceedings{howard2012enabling,
  title = {Enabling continuous planetary rover navigation through FPGA stereo and visual odometry},
  author = {Howard, Thomas M. and Morfopoulos, A. and Morrison, Jack and Kuwata, Yoshiaki and Villalpando, C. and Matthies, L. and McHenry, M.},
  booktitle = {AIAA SPACE and Astronautics Forum},
  pages = {1-9},
  publisher = {IEEE},
  year = {2012},
  doi = {10.1109/aero.2012.6187041},
  abstract = {Safe navigation under resource constraints is a key concern for autonomous planetary rovers operating on extraterrestrial bodies. Computational power in such applications is typically constrained by the radiation hardness and energy consumption requirements. For example, even though the microprocessors used for the Mars Science Laboratory (MSL) mission rover are an order of magnitude more powerful than those used for the rovers on the Mars Exploration Rovers (MER) mission, the computational power is still significantly less than that of contemporary desktop microprocessors. It is therefore important to move safely and efficiently through the environment while consuming a minimum amount of computational resources, energy and time. Perception, pose estimation, and motion planning are generally three of the most computationally expensive processes in modern autonomy navigation architectures. An example of this is on the MER where each rover must stop, acquire and process imagery to evaluate its surroundings, estimate the relative change in pose, and generate the next mobility system maneuver [1]. This paper describes improvements in the energy efficiency and speed of planetary rover autonomous traverse accomplished by converting processes typically performed by the CPU onto a Field Programmable Gate Arrays (FPGA) coprocessor. Perception algorithms in general are well suited to FPGA implementations because much of processing is naturally parallelizable. In this paper we present novel implementations of stereo and visual odometry algorithms on a FPGA. The FPGA stereo implementation is an extension of [2] that uses "random in linear out" rectification and a higher-performance interface between the rectification, filter, and disparity stages of the stereo pipeline. The improved visual odometry component utilizes a FPGA implementation of a Harris feature detector and sum of absolute differences (SAD) operator. The FPGA implementation of the stereo and visual odometry functionality have demonstrated a performance improvement of approximately three orders of magnitude compared to the MER-class avionics. These more efficient perception and pose estimation modules have been merged with motion planning techniques that allow for continuous steering and driving to navigate cluttered obstacle fields without stopping to perceive. The resulting faster visual odometry rates also allow for wheel slip to be detected earlier and more reliably. Predictions of resulting improvements in planetary rover energy efficiency and average traverse speeds are reported. In addition, field results are presented that compare the performance of autonomous navigation on the Athena planetary rover prototype using continuous steering or driving and continuous steering and driving with GESTALT traversability analysis using the FPGA perception and pose estimation improvements.}
}
  29. Ono, M., Fuchs, T. J., Steffy, A., Maimone, M. and Yen, J. (2015). Risk-aware planetary rover operation: autonomous terrain classification and path planning . IEEE Aerospace Conference. Source
    BibTeX
    @inproceedings{ono2015risk,
  title = {Risk-aware planetary rover operation: autonomous terrain classification and path planning},
  author = {Ono, Masahiro and Fuchs, Thoams J. and Steffy, Amanda and Maimone, Mark and Yen, Jeng},
  booktitle = {IEEE Aerospace Conference},
  pages = {1-10},
  publisher = {IEEE},
  year = {2015},
  doi = {10.1109/aero.2015.7119022},
  abstract = {Identifying and avoiding terrain hazards (e.g., soft soil and pointy embedded rocks) are crucial for the safety of planetary rovers. This paper presents a newly developed ground-based Mars rover operation tool that mitigates risks from terrain by automatically identifying hazards on the terrain, evaluating their risks, and suggesting operators safe paths options that avoids potential risks while achieving specified goals. The tool will bring benefits to rover operations by reducing operation cost, by reducing cognitive load of rover operators, by preventing human errors, and most importantly, by significantly reducing the risk of the loss of rovers. The risk-aware rover operation tool is built upon two technologies. The first technology is a machine learning-based terrain classification that is capable of identifying potential hazards, such as pointy rocks and soft terrains, from images. The second technology is a risk-aware path planner based on rapidly-exploring random graph (RRG) and the A* search algorithms, which is capable of avoiding hazards identified by the terrain classifier with explicitly considering wheel placement. We demonstrate the integrated capability of the proposed risk-aware rover operation tool by using the images taken by the Curiosity rover.}
}
  30. Swan, R. M., Atha, D., Leopold, H. A., Gildner, M., Oij, S., Chiu, C., Hong, X. and Ono, H. (2021). AI4MARS: A Dataset for Terrain-Aware Autonomy on Mars . JPL Open Repository. Source
    BibTeX
    @inproceedings{swan2021ai4mars,
  title = {AI4MARS: A Dataset for Terrain-Aware Autonomy on Mars},
  author = {Swan, R. Michael and Atha, Deegan and Leopold, Henry A. and Gildner, Matthew and Oij, Stephanie and Chiu, Cindy and Hong, Xiangyu and Ono, Hiro},
  publisher = {JPL Open Repository},
  year = {2021},
  url = {https://dataverse.jpl.nasa.gov/dataset.xhtml?persistentId=hdl:2014/54773}
}
  31. Toupet, O., Biesiadecki, J., Rankin, A., Steffy, A., Meirion-Griffith, G., Levine, D., Schadegg, M. and Maimone, M. (2019). Terrain-adaptive wheel speed control on the Curiosity Mars rover: Algorithm and flight results . Journal of Field Robotics, 5. Source
    BibTeX
    @article{toupet2019terrain,
  title = {Terrain-adaptive wheel speed control on the Curiosity Mars rover: Algorithm and flight results},
  author = {Toupet, Olivier and Biesiadecki, Jeffrey and Rankin, Arturo and Steffy, Amanda and Meirion-Griffith, Gareth and Levine, Dan and Schadegg, Maximilian and Maimone, Mark},
  journal = {Journal of Field Robotics},
  volume = {37},
  number = {5},
  pages = {699-728},
  publisher = {Wiley},
  year = {2019},
  doi = {10.1002/rob.21903},
  abstract = {Abstract NASA's Mars Science Laboratory Curiosity rover landed in August 2012 and began experiencing higher rates of wheel damage beginning in October 2013. While the wheels were designed to accumulate considerable damage, the unexpected damage rate raised concerns regarding wheel lifetime. In response, the Jet Propulsion Laboratory developed and deployed mobility flight software on Curiosity that reduces the forces on the wheels. The new algorithm adapts each wheel's speed to fit the terrain topography in real time, by leveraging the rover's measured attitude rates and rocker/bogie suspension angles and rates. Together with a rigid‐body kinematics model, it estimates the real‐time wheel‐terrain contact angles and commands idealized, no‐slip wheel angular rates. In addition, free‐floating “wheelies” are detected and autonomously corrected. Ground test data indicate that the forces on the wheels are reduced by 19% for leading wheels and 11% for middle leading wheels. On the ground, the required data volume increased by up to 129%, and drive duration increased by up to 25%. In flight, data collected over 3.6 km and 149 drives confirmed a reduction in wheel current, correlated with wheel torque, of 18.7%. The new algorithm proved to use fewer resources in flight than ground estimates suggested, as only a 10% increase in drive duration and double the drive data volume were experienced. These data indicate the promise of the new algorithm to extend the life of the wheels for the Curiosity rover. This paper describes the algorithm, its ground testing campaign and associated challenges, and its validation, implementation, and performance in flight.}
}
  32. Hedrick, G. and Gu, Y. (2021). Terrain-aware traverse planning for a Mars sample return rover . Advanced Robotics, 21-22. Source
    BibTeX
    @article{hedrick2021terrain,
  title = {Terrain-aware traverse planning for a Mars sample return rover},
  author = {Hedrick, G. and Gu, Y.},
  journal = {Advanced Robotics},
  volume = {35},
  number = {21-22},
  pages = {1286-1301},
  publisher = {Informa UK Limited},
  year = {2021},
  doi = {10.1080/01691864.2021.1955000}
}
  33. Ebadi, K., Coble, K., Kogan, D., Atha, D., Schwartz, R., Padgett, C. and Vander Hook, J. (2021). Semantic Mapping in Unstructured Environments: Toward Autonomous Localization of Planetary Robotic Explorers . IEEE Aerospace Conference. Source
    BibTeX
    @inproceedings{ebadi2021semantic,
  title = {Semantic Mapping in Unstructured Environments: Toward Autonomous Localization of Planetary Robotic Explorers},
  author = {Ebadi, Kamak and Coble, Kyle and Kogan, Dima and Atha, Deegan and Schwartz, Russell and Padgett, Curtis and Vander Hook, Joshua},
  booktitle = {IEEE Aerospace Conference},
  publisher = {JPL Open Repository},
  year = {2021},
  doi = {10.48577/jpl.p2p07m}
}
  34. Paton, M., Strub, M. P., Brown, T., Greene, R. J., Lizewski, J., Patel, V., Gammell, J. D. and Nesnas, I. (2020). Navigation on the Line: Traversability Analysis and Path Planning for Extreme-Terrain Rappelling Rovers . IEEE/RSJ International Conference on Intelligent Robots and Systems. Source
    BibTeX
    @inproceedings{paton2020navigation,
  title = {Navigation on the Line: Traversability Analysis and Path Planning for Extreme-Terrain Rappelling Rovers},
  author = {Paton, Michael and Strub, Marlin P and Brown, Travis and Greene, Rebecca J and Lizewski, Jacob and Patel, Vandan and Gammell, Jonathan D and Nesnas, Issa},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  pages = {7034-7041},
  publisher = {IEEE},
  year = {2020},
  doi = {10.1109/iros45743.2020.9341409},
  abstract = {Many areas of scientific interest in planetary exploration, such as lunar pits, icy-moon crevasses, and Martian craters, are inaccessible to current wheeled rovers. Rappelling rovers can safely traverse these steep surfaces, but require techniques to navigate their complex terrain. This dynamic navigation is inherently time-critical and communication constraints (e.g. delays and small communication windows) will require planetary systems to have some autonomy.Autonomous navigation for Martian rovers is well studied on moderately sloped and locally planar surfaces, but these methods do not readily transfer to tethered systems in non-planar 3D environments. Rappelling rovers in these situations have additional challenges, including terrain-tether interaction and its effects on rover stability, path planning and control.This paper presents novel traversability analysis and path planning algorithms for rappelling rovers operating on steep terrains that account for terrain-tether interaction and the unique stability and reachability constraints of a rapelling system. The system is evaluated with a series of simulations and an analogue mission. In simulation, the planner was shown to reliably find safe paths down a 55 degree slope when a stable tether-terrain configuration exists and never recommended an unsafe path when one did not. In a planetary analogue mission, elements of the system were used to autonomously navigate Axel, a JPL rappelling rover, down a 30 degree slope with 95% autonomy by distance travelled over 46 meters.}
}
  35. Reid, W., Paton, M., Emanuel, B., Chamberlain-Simon, B. and Meirion-Griffith, G. (2020). Autonomous Navigation over Europa Analogue Terrain for an Actively Articulated Wheel-on-Limb Rover . IEEE/RSJ International Conference on Intelligent Robots and Systems. Source
    BibTeX
    @inproceedings{reid2020autonomous,
  title = {Autonomous Navigation over Europa Analogue Terrain for an Actively Articulated Wheel-on-Limb Rover},
  author = {Reid, William and Paton, Michael and Emanuel, Blair and Chamberlain-Simon, Brendan and Meirion-Griffith, Gareth},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  pages = {1939-1946},
  publisher = {IEEE},
  year = {2020},
  doi = {10.1109/iros45743.2020.9341234},
  abstract = {The ocean world Europa is a prime target for exploration given its potential habitability [1]. We propose a mobile robotic system that is capable of autonomously traversing tens of meters to visit multiple sites of interest on a Europan analogue surface. Due to the topology of Europan terrain being largely unknown, it is desired that this mobility system traverse a large variety of terrain types. The mobility system should also be capable of crossing unstructured terrain in an autonomous manner given the communications limitations between Earth and Europa.A wheel-on-limb robotic rover is presented that may actively conform to terrain features up to 1.5 wheel diameters tall while driving. The robot uses a sampling-based motion planner to generate paths that leverage its unique locomotive capabilities. The planner assesses terrain hazards and wheel workspace limits as obstacles. It may also select a mobility mode based on predicted energy usage and the need for limb articulation on the terrain being traversed. This autonomous mobility was evaluated on chaotic salt-evaporite terrain found in Death Valley, CA, an analogue to the Europan surface. Over the course of 38 trials, the rover autonomously traversed 435m of extreme terrain while maintaining a rate of 0.64 traverse ending failures for every 10m driven.}
}
  36. Baumgartner, E. and Maurette, M. (2000). Autonomous navigation ability: FIDO test results . ESA Workshop on Advanced Space Technologies for Robotics and Automation. Source
    BibTeX
    @inproceedings{baumgartner2000autonomous,
  title = {Autonomous navigation ability: FIDO test results},
  author = {Baumgartner, E. and Maurette, M.},
  booktitle = {ESA Workshop on Advanced Space Technologies for Robotics and Automation},
  publisher = {JPL Open Repository},
  year = {2000},
  url = {https://dataverse.jpl.nasa.gov/dataset.xhtml?persistentId=hdl:2014/16356}
}
  37. Bai, C., Guo, J., Guo, L. and Song, J. (2019). Deep Multi-Layer Perception Based Terrain Classification for Planetary Exploration Rovers . Sensors, 14. Source
    BibTeX
    @article{bai2019deep,
  title = {Deep Multi-Layer Perception Based Terrain Classification for Planetary Exploration Rovers},
  author = {Bai, Chengchao and Guo, Jifeng and Guo, Linli and Song, Junlin},
  journal = {Sensors},
  volume = {19},
  number = {14},
  pages = {3102},
  publisher = {MDPI AG},
  year = {2019},
  doi = {10.3390/s19143102},
  abstract = {Accurate classification and identification of the detected terrain is the basis for the long-distance patrol mission of the planetary rover. But terrain measurement based on vision and radar is subject to conditions such as light changes and dust storms. In this paper, under the premise of not increasing the sensor load of the existing rover, a terrain classification and recognition method based on vibration is proposed. Firstly, the time-frequency domain transformation of vibration information is realized by fast Fourier transform (FFT), and the characteristic representation of vibration information is given. Secondly, a deep neural network based on multi-layer perception is designed to realize classification of different terrains. Finally, combined with the Jackal unmanned vehicle platform, the XQ unmanned vehicle platform, and the vibration sensor, the terrain classification comparison test based on five different terrains was completed. The results show that the proposed algorithm has higher classification accuracy, and different platforms and running speeds have certain influence on the terrain classification at the same time, which provides support for subsequent practical applications.}
}
  38. Park, M., Cho, D., Kim, S. and Cho, Y. (2025). CUTE-Planner: Confidence-aware Uneven Terrain Exploration Planner . International Conference on Space Robotics. Source
    BibTeX
    @inproceedings{park2025cute,
  title = {CUTE-Planner: Confidence-aware Uneven Terrain Exploration Planner},
  author = {Park, Miryeong and Cho, Dongjin and Kim, Sanghyun and Cho, Younggun},
  booktitle = {International Conference on Space Robotics},
  pages = {72-78},
  year = {2025},
  doi = {10.1109/isparo66239.2025.11436759},
  abstract = {Planetary exploration robots must navigate uneven terrain while building reliable maps for space missions. However, most existing methods incorporate traversability constraints but may not handle high uncertainty in elevation estimates near complex features like craters, do not consider exploration strategies for uncertainty reduction, and typically fail to address how elevation uncertainty affects navigation safety and map quality. To address the problems, we propose a framework integrating safe path generation, adaptive confidence updates, and confidence-aware exploration strategies. Using Kalman-based elevation estimation, our approach generates terrain traversability and confidence scores, then incorporates them into Graph-Based exploration Planner (GBP) to prioritize exploration of traversable low-confidence regions. We evaluate our framework through simulated lunar experiments using a novel low-confidence region ratio metric, achieving 69% uncertainty reduction compared to baseline GBP. In terms of mission success rate, our method achieves 100% while baseline GBP achieves 0%, demonstrating improvements in exploration safety and map reliability.}
}
  39. Furgale, P., Carle, P., Enright, J. and Barfoot, T. D. (2012). The Devon Island rover navigation dataset . The International Journal of Robotics Research, 6. Source
    BibTeX
    @article{furgale2012devon,
  title = {The Devon Island rover navigation dataset},
  author = {Furgale, Paul and Carle, Pat and Enright, John and Barfoot, Timothy D.},
  journal = {The International Journal of Robotics Research},
  volume = {31},
  number = {6},
  pages = {707-713},
  publisher = {SAGE Publications},
  year = {2012},
  doi = {10.1177/0278364911433135},
  abstract = {In this paper we present a rover navigation dataset collected at a Mars/Moon analogue site on Devon Island, in the Canadian High Arctic. The dataset is split into two parts. The first part contains rover traverse data: stereo imagery, Sun vectors, inclinometer data, and ground-truth position information from a differential global positioning system (DGPS) collected over a 10-km traverse. The second part contains long-range localization data: 3D laser range scans, image panoramas, digital elevation models, and GPS data useful for global position estimation. All images are available in common formats and other data is presented in human-readable text files. To facilitate use of the data, Matlab parsing scripts are included.}
}
  40. Meyer, L., Smíšek, M., Fontan Villacampa, A., Oliva Maza, L., Medina, D., Schuster, M. J., Steidle, F., Vayugundla, M., Müller, M. G., Rebele, B., Wedler, A. and Triebel, R. (2021). The MADMAX data set for visual-inertial rover navigation on Mars . Journal of Field Robotics, 6. Source
    BibTeX
    @article{meyer2021madmax,
  title = {The MADMAX data set for visual-inertial rover navigation on Mars},
  author = {Meyer, Lukas and Smíšek, Michal and Fontan Villacampa, Alejandro and Oliva Maza, Laura and Medina, Daniel and Schuster, Martin J. and Steidle, Florian and Vayugundla, Mallikarjuna and Müller, Marcus G. and Rebele, Bernhard and Wedler, Armin and Triebel, Rudolph},
  journal = {Journal of Field Robotics},
  volume = {38},
  number = {6},
  pages = {833-853},
  publisher = {Wiley},
  year = {2021},
  doi = {10.1002/rob.22016},
  abstract = {Abstract Planetary rovers increasingly rely on vision‐based components for autonomous navigation and mapping. Developing and testing these components requires representative optical conditions, which can be achieved by either field testing at planetary analog sites on Earth or using prerecorded data sets from such locations. However, the availability of representative data is scarce and field testing in planetary analog sites requires a substantial financial investment and logistical overhead, and it entails the risk of damaging complex robotic systems. To address these issues, we use our compact human‐portable DLR Sensor Unit for Planetary Exploration Rovers (SUPER) in the Moroccan desert to show resource‐efficient field testing and make the resulting Morocco‐Acquired data set of Mars‐Analog eXploration (MADMAX) publicly accessible. The data set consists of 36 different navigation experiments, captured at eight Mars analog sites of widely varying environmental conditions. Its longest trajectory covers 1.5 km and the combined trajectory length is 9.2 km. The data set contains time‐stamped recordings from monochrome stereo cameras, a color camera, omnidirectional cameras in stereo configuration, and from an inertial measurement unit. Additionally, we provide the ground truth in position and orientation together with the associated uncertainties, obtained by a real‐time kinematic‐based algorithm that fuses the global navigation satellite system data of two body antennas. Finally, we run two state‐of‐the‐art navigation algorithms, ORB‐SLAM2 and VINS‐mono, on our data to evaluate their accuracy and to provide a baseline, which can be used as a performance reference of accuracy and robustness for other navigation algorithms. The data set can be accessed at https://rmc.dlr.de/morocco2018 .}
}
  41. Toupet, O., Ono, M., del Sesto, T., Maimone, M. and McHenry, M. (2026). Enhanced Autonomous Navigation on the Perseverance Mars Rover . IEEE Transactions on Field Robotics. Source
    BibTeX
    @article{toupet2026enhanced,
  title = {Enhanced Autonomous Navigation on the Perseverance Mars Rover},
  author = {Toupet, Olivier and Ono, Masahiro and del Sesto, Tyler and Maimone, Mark and McHenry, Michael},
  journal = {IEEE Transactions on Field Robotics},
  volume = {3},
  pages = {83--124},
  year = {2026},
  doi = {10.1109/tfr.2025.3636366},
  abstract = {This paper presentsEnhanced Autonomous Navigation, orENav, the autonomous driving algorithm of NASA’s Mars roverPerseverance. A unique challenge for the autonomous driving ofPerseveranceis to meet strict safety and performance requirements in a highly uncertain environment with only a single-core CPU with extremely limited computing resources. ENav overcame this challenge with a novel two-stage path selection approach that balances the path optimality and computational efficiency, combined with a unique collision checking algorithm that conservatively approximates computationally expensive kinematic settling (Otsu et al., 2020). In addition, ENav provides robustness against slip by expanding the bounding boxes for wheels used by the collision check. These new features, together with FPGA-accelerated vision processing, enabledPerseveranceto autonomously drive on substantially more rock-dense terrains and increased the average daily driving distance by an order of magnitude compared to its predecessors, theCuriosity, Spirit, andOpportunityrovers. Perseverance has set several new records for autonomous driving on Mars, breaking those previously held by the Opportunity rover. As of the 1312th Martian day since landing, or 28 October 2024 on the Earth calendar, ∼90% of the 32.1 km of driving has used ENav to evaluate the terrain. This paper provides detailed documentation of the ENav algorithm, as well as its implementation, testing, deployment, and driving results on Mars.}
}
  42. Dai, A., Gupta, S. and Gao, G. (2026). Neural Radiance Maps for Extraterrestrial Navigation and Path Planning. arxiv.org/abs/2603.17236v1
    BibTeX
    @misc{dai2026neural,
  title = {Neural Radiance Maps for Extraterrestrial Navigation and Path Planning},
  author = {Dai, Adam and Gupta, Shubh and Gao, Grace},
  year = {2026},
  url = {https://arxiv.org/abs/2603.17236v1}
}
  43. Cheng, S., Zhou, R., Feng, W., Yang, H., Gao, H., Deng, Z. and Ding, L. (2025). VLM-Empowered Multi-Mode System for Efficient and Safe Planetary Navigation . IEEE/RSJ International Conference on Intelligent Robots and Systems. Source
    BibTeX
    @inproceedings{cheng2025vlm,
  title = {VLM-Empowered Multi-Mode System for Efficient and Safe Planetary Navigation},
  author = {Cheng, Sinuo and Zhou, Ruyi and Feng, Wenhao and Yang, Huaiguang and Gao, Haibo and Deng, Zongquan and Ding, Liang},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  pages = {1487-1494},
  year = {2025},
  doi = {10.1109/iros60139.2025.11247594},
  abstract = {The increasingly complex and diverse planetary exploration environment requires more adaptable and flexible rover navigation strategy. In this study, we propose a VLM-empowered multi-mode system to achieve efficient while safe autonomous navigation for planetary rovers. Vision-Language Model (VLM) is used to parse scene information by image inputs to achieve a human-level understanding of terrain complexity. Based on the complexity classification, the system switches to the most suitable navigation mode, composing of perception, mapping and planning modules designed for different terrain types, to traverse the terrain ahead before reaching the next waypoint. By integrating the local navigation system with a map server and a global waypoint generation module, the rover is equipped to handle long-distance navigation tasks in complex scenarios. The navigation system is evaluated in various simulation environments. Compared to the single-mode conservative navigation method, our multi-mode system is able to bootstrap the time and energy efficiency in a long-distance traversal with varied type of obstacles, enhancing efficiency by 79.5%, while maintaining its avoidance capabilities against terrain hazards to guarantee rover safety. More system information is shown at https://chengsn1234.github.io/multi-mode-planetary-navigation/.}
}