Distributionally Safe Path Planning: Wasserstein Safe RRT
- Univ. of California, San Diego, CA (United States); Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
- Univ. of California, San Diego, CA (United States)
In this paper, we propose a Wasserstein metric-based random path planning algorithm. Wasserstein Safe RRT (W-Safe RRT) provides finite-sample probabilistic guarantees on the safety of a returned path in an uncertain obstacle environment. Vehicle and obstacle states are modeled as distributions based upon state and model observations. Additionally, we define limits on distributional sampling error so the Wasserstein distance between a vehicle state distribution and obstacle distributions can be bounded. This enables the algorithm to return safe paths with a confidence bound through combining finite sampling error bounds with calculations of the Wasserstein distance between discrete distributions. W-Safe RRT is compared against a baseline minimum encompassing ball algorithm, which ensures balls that minimally encompass discrete state and obstacle distributions do not overlap. The improved performance is verified in a 3D environment using single, multi, and rotating non-convex obstacle cases, with and without forced obstacle error in adversarial directions, showing that W-Safe RRT can handle poorly modeled complex environments.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE; US Office of Naval Research (ONR)
- Grant/Contract Number:
- 89233218CNA000001; N00014-19-1-2471
- OSTI ID:
- 1878051
- Report Number(s):
- LA-UR-21-25559; 2377-3766
- Journal Information:
- IEEE Robotics and Automation Letters, Vol. 7, Issue 1; ISSN 2377-3766
- Publisher:
- IEEECopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Adversarial Sampling-Based Motion Planning
Improved Performance of Asymptotically Optimal Rapidly Exploring Random Trees