Learning-Based Risk-Bounded Path Planning Under Environmental Uncertainty

Building a general and efficient path planning framework in uncertain nonconvex environments is challenging due to the safety constraints and complex configuration. Tradi- tional avenues usually involve convexifying obstacles and presume Gaussian distribution, which are not universal. Meanwhile, the fast convergence of high-quality solutions is not guaranteed. Therefore, we develop a novel neural risk-bounded path planner to quickly find near-optimal solutions that have an acceptable collision probability in the complex environments. Firstly, we retrieve the nonconvex obstacles with arbitrary probabilistic uncertainties in the form of a deterministic point cloud map. A neural network sampler encodes it into a latent embedding and is trained with sufficient expert demonstrations, predicting states in the potential subspace. We construct a neural cost estimator to select the best informed state from those samples. Then, we recursively use the simple yet effective neural networks to march toward the start and goal bidirectionally. The collision risk of the intermediate connections is verified based on sum-of- squares optimization. Simulation results show that our approach significantly saves time and resources in finding comparable solutions over the state-of-the-art methods in the seen and unseen challenging environments. Note to Practitioners—More and more robots are deployed in unstructured environments, such as forests and subterranean caves. However, uncertainty in the environment situational aware- ness usually causes accidents. To quickly generate safe paths without over-conservation in uncertain complex environments, we propose a neural risk-bounded sampling-based path planner. Conventional methods consume lots of computation time and resources to generate satisfactory results. Our learning-based risk-bounded path planning framework can efficiently find paths with a guaranteed risk tolerance avoiding uncertain nonconvex static obstacles. It imitates the expert to generate informed states in a subspace that potentially contains the optimal solution. In This work was supported in part by Hong Kong RGC CRF grant C4063- 18G, Shenzhen Outstanding Scientific and Technological Innovation Talents Training Project under Grant RCBS20221008093305007, and National Natu- ral Science Foundation of China grant #62103181. (Corresponding authors: Jiankun Wang and Max Q.-H. Meng.) F. Meng and H. Ma are with the Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong (e-mail: {feimeng, hanma}@link.cuhk.edu.hk). L. Chen is with the School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA 30332 USA (e-mail: lian- gliang.chen@gatech.edu). J. Wang is with Shenzhen Key Laboratory of Robotics Perception and Intel- ligence and the Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China, and also with Jiaxing Research Institute, Southern University of Science and Technology, Jiaxing, China (e-mail: wangjk@sustech.edu.cn). Max Q.-H. Meng is with Shenzhen Key Laboratory of Robotics Perception and Intelligence and the Department of Electronic and Electrical Engineering at Southern University of Science and Technology in Shenzhen, China. He is a Professor Emeritus in the Department of Electronic Engineering at The Chinese University of Hong Kong in Hong Kong and was a Professor in the Department of Electrical and Computer Engineering at the University of Alberta in Canada (e-mail: max.meng@ieee.org). practice, we need to formulate the observed uncertain obstacle at a grid map into the polynomial containing random variables and determine their probability distributions.