A ROS-based Simulator for Testing the Enhanced Autonomous Navigation of the Mars 2020 Rover

Toupet, Olivier; Sesto, Tyler Del; Ono, Masahiro; Myint, Steven; Hook, Joshua Vander; McHenry, Michael

doi:10.1109/aero47225.2020.9172345

Cited by 18 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Described at length in [8], a Monte Carlo simulation environment was built for testing ENav and Mars 2020 navigation (Figure 4). The Robotics Operating System (ROS) [14] was used for inter-process communication.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Based Path Planning for Improved Rover Navigation

Abcouwer

Daftry

Sesto

et al. 2021

2021 IEEE Aerospace Conference (50100)

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The Mars 2020 mission [7] and its Perseverance Rover will use the Enhanced Navigation (ENav) library [8] to plan paths on the Martian surface. ENav takes as input stereo imagery, maintains a 2.5D heightmap describing the terrain, and chooses the best maneuver to safely move the rover toward the global goal.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Path Planning for Improved Rover Navigation

Abcouwer

Daftry

Sesto

et al. 2021

2021 IEEE Aerospace Conference (50100)

Self Cite

View full text Add to dashboard Cite

show abstract

“…For all our experiments presented in this section, we used a ROS-based, high-fidelity simulation environment called ENav Sim [34] that was originally developed for prototyping and testing of Perseverance's ENav algorithm. ENav Sim is capable of generating a rich set of varied 2.5D terrains representative of the candidate Mars landing sites, producing synthetic stereo images for simulating onboard hightmap generation, and simulating the rover's motion.…”

Section: A Experimental Setupmentioning

confidence: 99%

MLNav: Learning to Safely Navigate on Martian Terrains

Daftry

Abcouwer

Sesto

et al. 2022

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

We present MLNav, a learning-enhanced path planning framework for safety-critical and resource-limited systems operating in complex environments, such as rovers navigating on Mars. MLNav makes judicious use of machine learning to enhance the efficiency of path planning while fully respecting safety constraints. In particular, the dominant computational cost in such safety-critical settings is running a model-based safety checker on the proposed paths. Our learned search heuristic can simultaneously predict the feasibility for all path options in a single run, and the model-based safety checker is only invoked on the top-scoring paths. We validate in high-fidelity simulations using both real Martian terrain data collected by the Perseverance rover, as well as a suite of challenging synthetic terrains. Our experiments show that: (i) compared to the baseline ENav path planner on board the Perserverance rover, MLNav can provide a significant improvement in multiple key metrics, such as a 10x reduction in collision checks when navigating real Martian terrains, despite being trained with synthetic terrains; and (ii) MLNav can successfully navigate highly challenging terrains where the baseline ENav fails to find a feasible path before timing out.

show abstract

“…Existing methods to address the uncertainty propagation problem of autonomous and robotic systems are all approximate and mainly address Gaussian uncertainties. For example, [33] uses linearized models and Gaussian uncertainties to address uncertainty propagation in motion planning of robotic systems under uncertainty, [34] uses Monte Carlo based uncertainty propagation for motion planning of NASA's Mars rovers, [35] uses unscented transformation based uncertainty propagation for simultaneous localization and mapping of vehicles, [36] uses a sample based approach for uncertainty propagation in planetary entry vehicles, [37] uses polynomial chaos and Gaussian uncertainties for uncertainty propagation in chance constrained motion planning, [32] uses moment closure based uncertainty propagation for polynomial and trigonometric stochastic systems in the presence of Gaussian processes, [38] uses linearized models to propagate and represent uncertainties in the form of probabilistic flow tubes, and [39] uses deep learning for uncertainty propagation through nonlinear systems.…”

Section: Introductionmentioning

confidence: 99%

Moment-Based Exact Uncertainty Propagation Through Nonlinear Stochastic Autonomous Systems

Jasour¹,

Wang²,

Williams³

2021

Preprint

View full text Add to dashboard Cite

In this paper, we address the problem of uncertainty propagation through nonlinear stochastic dynamical systems. More precisely, given a discrete-time continuous-state probabilistic nonlinear dynamical system, we aim at finding the sequence of the moments of the probability distributions of the system states up to any desired order over the given planning horizon. Moments of uncertain states can be used in estimation, planning, control, and safety analysis of stochastic dynamical systems. Existing approaches to address moment propagation problems provide approximate descriptions of the moments and are mainly limited to particular set of uncertainties, e.g., Gaussian disturbances. In this paper, to describe the moments of uncertain states, we introduce trigonometric and also mixed-trigonometric-polynomial moments. Such moments allow us to obtain closed deterministic dynamical systems that describe the exact time evolution of the moments of uncertain states of an important class of autonomous and robotic systems including underwater, ground, and aerial vehicles, robotic arms and walking robots. Such obtained deterministic dynamical systems can be used, in a receding horizon fashion, to propagate the uncertainties over the planning horizon in real-time.To illustrate the performance of the proposed method, we benchmark our method against existing approaches including linear, unscented transformation, and sampling based uncertainty propagation methods that are widely used in estimation, prediction, planning, and control problems.

show abstract

A ROS-based Simulator for Testing the Enhanced Autonomous Navigation of the Mars 2020 Rover

Cited by 18 publications

References 6 publications

Machine Learning Based Path Planning for Improved Rover Navigation

Machine Learning Based Path Planning for Improved Rover Navigation

MLNav: Learning to Safely Navigate on Martian Terrains

Moment-Based Exact Uncertainty Propagation Through Nonlinear Stochastic Autonomous Systems

Contact Info

Product

Resources

About