Knowledge-Biased Sampling-Based Path Planning for Automated Vehicles Parking

Abstract

We consider automated vehicles operation in constrained environments, i.e. the automated parking (AP). The core of AP is formulated as a path planning problem, and Rapidly-exploring Randomized Tree (RRT) algorithm is adopted. To improve the baseline RRT, we propose several algorithmic tweaks, i.e. reversed RRT tree growth, direct tree branch connection using Reeds-Shepp curves, and RRT seeds biasing via regulated parking space/vehicle knowledge. We prove that under these tweaks the algorithm is complete and feasible. We then examine its performance (time, success rate, convergence to the optimal path) and scalability (to different parking spaces/vehicles) via batched simulations. We also test it using a real vehicle in a realistic parking environment. The proposed solution presents itself more applicable when compared with other baseline algorithms. INDEX TERMSAutomated vehicles; Automated parking; Sampling-based path planning; Knowledgebased biasing.

Research on parallel parking path planning based on the G-PSOA

“…Automatic parking PP algorithms mainly include Genetic Algorithm(GA) [2], Ant Colony Optimization(ACO) [3], Rapidly-exploring Random Tree(RRT) [4], and others. In [5], it used RRT for parking PP however, the convergence speed using this algorithm was slow, and the planned path was poorly smoothed. In [6], it used the grid method ACO to find the optimal path.…”

Fast Planning and Tracking of Complex Autonomous Parking Maneuvers With Optimal Control and Pseudo-Neural Networks

“…In the field of path and trajectory planning for automated parking, the main techniques that emerge in the literature [2] are search-based, sampling-based, and optimal control-based. The search methods, like the many variants of A* and Hybrid A* [3], [4], and the sampling RRT*-like techniques [5], [6] tend to suffer from curse of dimensionality issues, when the parking spaces are narrow and a fine map resolution is required [2], [7]. Moreover, the search A*-like methods are generally used for path planning, and the computed path may be far from the global optimum.…”

Online Trajectory Replanning for Sudden Environmental Changes During Automated Parking: A Parallel Stitching Method

“…UTOMATED parking refers to driving an autonomous vehicle from an initial pose to a desired goal pose in a parking lot, during which the vehicle should avoid collisions with the surrounding obstacles [1][2][3][4]. As a critical module in an automated parking system, trajectory planning is responsible for finding a kinematically feasible and collision-free curve with the traverse time and energy minimized [5][6][7][8][9][10][11][12]. In contrast Bai Li, Zhuyan Yin, Yakun Ouyang, Xiang Zhong, and Shiqi Tang are with the College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China (e-mails: libai@zju.edu.cn, 1026078242@qq.com, yakun@hnu.edu.cn, zx5587@126.com, tangshiqi@hnu.edu.cn).…”