Human‐like motion planning for autonomous parking based on revised bidirectional rapidly‐exploring random tree* with Reeds‐Shepp curve

Abstract

Autonomous parking is one significant autonomous application and will be implemented in daily life in the near future. Due to encountered narrow environments, the issues related to autonomous parking, such as path quality requirements, strict collision avoidance, and motion direction changes, must be overcome properly. Moreover, to be applied in daily driving activities, real‐time planning and human preference should be fulfilled by the designed motion planners. Therefore, an efficient and human‐like motion planning method based on the revised Bidirectional Rapidly‐Exploring Random Tree* (Bi‐RRT*) with Reeds‐Shepp curve is presented. The proposed method results in human‐like paths which have high trajectory quality and consistency for parking scenarios due to the revised Bi‐RRT* framework. Strict collision checking model guarantees the resulting paths to be collision‐free and even leaves safe distance from obstacles and uncertainties. State space adjustment makes the path optimization more efficient and effective. On the other hand, the cost function revision makes the resulting paths meet human driving behavior, such as less backward driving and motion direction changes. In addition, rigorous simulations and analysis demonstrate the effectiveness of the cost function revision and the state space adjustment and illustrate good performance of the proposed approach in common and even complex parking scenarios.

An Autonomous Parking System of Optimally Integrating Bidirectional Rapidly-Exploring Random Trees and Parking-Oriented Model Predictive Control

“…By considering the above-mentioned limitations and problems, the smooth-feedback Bi-RRT* is proposed to generate feasible and human-like parking paths with high quality and consistency efficiently [10]. Nevertheless, the optimization and exploring efficiency in narrow spaces are not good enough.…”

“…In this paper, the proposed motion planner aims to improve the inefficient exploration in narrow spaces in [10]. Also, parking-oriented MPC is proposed to track the resulting parking path accurately and smoothly for real-time requirements.…”

“…A motion planner using smooth-feedback Bi-RRT* is utilized to plan parking paths in high path quality and consistency for various parking scenarios [10]. Moreover, the proposed motion planner revises the original framework to improve exploration and optimization.…”

“…The proposed process aims to improve the optimization and exploring efficiency in [10]. As shown in Figure 4, The former two steps are to optimize the connected solutions, interpolated by the Reeds-Shepp curve, with RRT* as the original version.…”

“…As shown in Figure 4, The former two steps are to optimize the connected solutions, interpolated by the Reeds-Shepp curve, with RRT* as the original version. The original process in [10] feeds the smooth process results back to RRT* trees for each found solution. However, it may result in heavy load for the following computation and fall into a local minimum easily.…”