Path Planning for Autonomous Vehicles in Unknown Semi-structured Environments

TLDR

The study builds on the 2007 DARPA Urban Challenge, where autonomous vehicles navigated parking lots. The authors present a practical path‑planning algorithm for autonomous vehicles in unknown semi‑structured environments with online obstacle detection. The algorithm first applies a variant of A* search in the vehicle’s 3‑D kinematic state space to generate a kinematically feasible trajectory, then refines it with nonlinear optimization to achieve a local or global optimum, and further incorporates prior topological knowledge to accelerate search and produce trajectories better suited to environmental structure. In DARPA Urban Challenge trials the planner achieved near‑flawless performance on tasks such as parking‑lot navigation and U‑turns on blocked roads, and in real parking‑lot experiments it replanned within 50–300 ms per cycle.

Abstract

We describe a practical path-planning algorithm for an autonomous vehicle operating in an unknown semi-structured (or unstructured) environment, where obstacles are detected online by the robot’s sensors. This work was motivated by and experimentally validated in the 2007 DARPA Urban Challenge, where robotic vehicles had to autonomously navigate parking lots. The core of our approach to path planning consists of two phases. The first phase uses a variant of A* search (applied to the 3D kinematic state space of the vehicle) to obtain a kinematically feasible trajectory. The second phase then improves the quality of the solution via numeric non-linear optimization, leading to a local (and frequently global) optimum. Further, we extend our algorithm to use prior topological knowledge of the environment to guide path planning, leading to faster search and final trajectories better suited to the structure of the environment. We present experimental results from the DARPA Urban Challenge, where our robot demonstrated near-flawless performance in complex general path-planning tasks such as navigating parking lots and executing U-turns on blocked roads. We also present results on autonomous navigation of real parking lots. In those latter tasks, which are significantly more complex than the ones in the DARPA Urban Challenge, the time of a full replanning cycle of our planner is in the range of 50—300 ms.