NR-RRT: Neural Risk-Aware Near-Optimal Path Planning in Uncertain Nonconvex Environments

Balancing the trade-off between safety and efficiency is of significant importance for path planning under uncertainty. Many developed risk-aware path planners explicitly limit the probability of collision to an acceptable bound in uncertain environments. However, convex obstacles or Gaussian uncertainties are usually assumed to make the problem tractable in the existing method. These assumptions limit the generalization and application of path planners in real-world implementations. In this article, we propose to apply deep learning methods to the sampling-based planner, developing a novel risk bounded near-optimal path planning algorithm named neural risk-aware RRT (NR-RRT). Specifically, a deterministic risk contours map is maintained by perceiving the probabilistic nonconvex obstacles, and a neural network sampler is proposed to predict the next most-promising safe state. Furthermore, the recursive divide-and-conquer planning and bidirectional search strategies are used to accelerate the convergence to a near-optimal solution with guaranteed bounded risk. Worst-case theoretical guarantees can also be proven owing to a standby safety guaranteed planner utilizing a uniform sampling distribution. Simulation experiments demonstrate that the proposed algorithm outperforms the state-of-the-art for finding risk bounded low-cost paths in uncertain nonconvex environments with seen and unseen scene layouts. Note to Practitioners—This article is motivated by developing an efficient risk-aware path planner that can quickly find risk bounded solutions in uncertain nonconvex environments for practical applications, such as autonomous vehicles and search-and-rescue robots. Sampling-based planning approaches such as rapidly-exploring random tree (RRT) and its variants are popular for their good performance in exploring the state space. However, it is quite time-consuming to look for risk bounded paths in uncertain environments, especially under nonconvex and non-Gaussian constraints. The initial paths are often of poor quality. Therefore, we propose the NR-RRT algorithm to rapidly find near-optimal solutions with guaranteed bounded risk. It utilizes an informed bidirectional search strategy after having past experiences in the challenging environments. It can be applied in not only seen uncertain scenarios but also those have unseen scene layouts different from the training scenarios. However, the algorithm cannot handle the problem in environments that contain entirely unseen obstacles. In future research, we will address the problem of planning under robot model uncertainty.