Autonomous Off-Road Navigation over Extreme Terrains with Perceptually-Challenging Conditions

Thakker, Rohan; Alatur, Nikhilesh; Fan, David D.; Tordesillas, Jesus; Paton, Michael; Otsu, Kyohei; Toupet, Olivier; Agha–mohammadi, Ali–akbar

doi:10.1007/978-3-030-71151-1_15

Cited by 27 publications

(25 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This results in more efficient and safer planning when compared to deterministic methods. For example, in our prior work [38], the deterministic approach led to frequent oscillations in planning as obstacles appeared and disappeared with sensor and localization noise.…”

Section: B Hardware Resultsmentioning

confidence: 97%

“…Furthermore, a method for incorporating sensor and state uncertainty to obtain a probabilistic terrain estimate in the form of a grid-based elevation map was considered in [15]. Our work builds upon these ideas by performing traversability analyses using classical geometric methods, while incorporating the uncertainty of these methods for risk-aware planning [2,38].…”

Section: Related Workmentioning

confidence: 99%

“…a region of the environment in which the robot will suffer or become damaged has a high traversability cost. Building upon our previous work on traversability in extreme terrains [38], we formulate the problem as a risk-aware, online nonlinear Model Predictive Control (MPC) problem, in which the uncertainty of traversability is taken into account when planning a trajectory. Our goal is to minimize the traversability cost, but directly minimizing the mean cost leads to an unfavorable result because tail events with low probability of occurrence (but high consequence) are ignored (Figure 2).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation

Fan¹,

Otsu²,

Kubo

et al. 2021

Robotics: Science and Systems XVII

Self Cite

View full text Add to dashboard Cite

Although ground robotic autonomy has gained widespread usage in structured and controlled environments, autonomy in unknown and off-road terrain remains a difficult problem. Extreme, off-road, and unstructured environments such as undeveloped wilderness, caves, and rubble pose unique and challenging problems for autonomous navigation. To tackle these problems we propose an approach for assessing traversability and planning a safe, feasible, and fast trajectory in real-time. Our approach, which we name STEP (Stochastic Traversability Evaluation and Planning), relies on: 1) rapid uncertaintyaware mapping and traversability evaluation, 2) tail risk assessment using the Conditional Value-at-Risk (CVaR), and 3) efficient risk and constraint-aware kinodynamic motion planning using sequential quadratic programming-based (SQP) model predictive control (MPC). We analyze our method in simulation and validate its efficacy on wheeled and legged robotic platforms exploring extreme terrains including an abandoned subway and an underground lava tube.

show abstract

Section: B Hardware Resultsmentioning

confidence: 97%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation

Fan¹,

Otsu²,

Kubo

et al. 2021

Robotics: Science and Systems XVII

Self Cite

View full text Add to dashboard Cite

show abstract

“…Geometry-based methods build a 2.5D or 3D terrain map that is used to extract features, such as the maximum, minimum, and variance of the height and slope of the terrain [10,11]. Planning algorithms for such methods can take into account the stability of the robot on the terrain [2,12]. Since sensor and localization uncertainty can play a large role in the construction of environment maps, various methods exist for estimating the probability distributions of states based on the kinematic model of the vehicle and the terrain height uncertainty [3,13].…”

Section: Instantiating the Systemmentioning

confidence: 99%

“…One classic approach is to perform online geometric mapping and traversability estimation and then use these estimates, along with a hand-tuned cost function, for planning feasible paths [1][2][3][4]. With careful design and incorporation of prior knowledge into the decision-making pipeline, these approaches, which we term "geometry-based" and "geometric costmap"-based, are a standard and performant approach.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments

Dashora,

Shin,

Shah

et al. 2021

Preprint

View full text Add to dashboard Cite

Fig. 1: Our approach combines a learning-based method and a geometry-based planner to plan obstacle-free trajectories for a Husky robot in a deployment area with obstacles (trees, grass, bushes) as seen in (a). An example navigation task is shown in (b), where the robot (marked in red) must navigate to the goal (marked in green) while avoiding obstacles on its path. On its path to the goal, the robot often encounters a scenes like (c) where there are non-traversable elements like shrubs (highlighted in cyan) and novel obstacles like a wall. Learning-based methods successfully avoid previously seen obstacles but can struggle with novel obstacles, leading to a collision with the wall (d). While a geometric approach can avoid this by predicting the collision, it is unable to reason about the traversability of large shrubs that are hard to identify (e). Note that the cyan markers are shown for illustration only and are not available to the robot. Our approach, HIP, combines attributes from both these methods and successfully plans a collision-free trajectory (f). Videos of our results are hosted at sites.google.com/view/hybrid-imitative-planning/.

show abstract

How Challenging is a Challenge? CEMS: a Challenge Evaluation Module for SLAM Visual Perception

Zhao,

Gao,

et al. 2024

J Intell Robot Syst

View full text Add to dashboard Cite

Despite promising SLAM research in both vision and robotics communities, which fundamentally sustains the autonomy of intelligent unmanned systems, visual challenges still threaten its robust operation severely. Existing SLAM methods usually focus on specific challenges and solve the problem with sophisticated enhancement or multi-modal fusion. However, they are basically limited to particular scenes with a non-quantitative understanding and awareness of challenges, resulting in a significant performance decline with poor generalization and(or) redundant computation with inflexible mechanisms. To push the frontier of visual SLAM, we propose a fully computational reliable evaluation module called CEMS (Challenge Evaluation Module for SLAM) for general visual perception based on a clear definition and systematic analysis. It decomposes various challenges into several common aspects and evaluates degradation with corresponding indicators. Extensive experiments demonstrate our feasibility and outperformance. The proposed module has a high consistency of 88.298% compared with annotation ground truth, and a strong correlation of 0.879 compared with SLAM tracking performance. Moreover, we show the prototype SLAM based on CEMS with better performance and the first comprehensive CET (Challenge Evaluation Table) for common SLAM datasets (EuRoC, KITTI, etc.) with objective and fair evaluations of various challenges. We make it available online to benefit the community on our website.

show abstract

Autonomous Off-Road Navigation over Extreme Terrains with Perceptually-Challenging Conditions

Cited by 27 publications

References 18 publications

STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation

STEP: Stochastic Traversability Evaluation and Planning for Risk-Aware Off-road Navigation

Hybrid Imitative Planning with Geometric and Predictive Costs in Off-road Environments

How Challenging is a Challenge? CEMS: a Challenge Evaluation Module for SLAM Visual Perception

Contact Info

Product

Resources

About