ADD-RRV for motion planning in complex environments

Abstract

In this paper, we present a novel sampling-based motion planning method in various complex environments, especially with narrow passages. We use online the results of the planner in the ADD-RRT framework to identify the types of the local configuration space based on the principal component analysis (PCA). The identification result is then used to accelerate the expansion similar to RRV around obstacles and through narrow passages. We also propose a modified bridge test to identify the entrance of a narrow passage and boost samples inside it. We have compared our method with known motion planners in several scenarios through simulations. Our method shows the best performance across all the tested planners in the tested scenarios.

CERRT: A Mobile Robot Path Planning Algorithm Based on RRT in Complex Environments

“…Wu et al proposed the Fast-RRT [7] algorithm, which detects narrow passages by re-randomizing the expansion direction at collision points, but the algorithm's stability is poor. Cai et al combined RRV with bridge testing [8], enabling efficient identification and expansion in complex environments without the need for additional collision detection, greatly reducing computational intensity, but the algorithm can generate a large number of useless vertices in open areas. Building upon RRV and RRT-Connect, Li et al proposed an adaptive random tree algorithm called ARRT-Connect [9], which effectively improves the algorithm's performance, but the algorithm may fall into concave traps.…”

An Effective Obstacle Avoidance and Motion Planning Design for Underwater Telescopic Arm Robots Based on a Tent Chaotic Dung Beetle Algorithm

“…Aiming at the impact of algorithmic motion obstacle avoidance [18][19][20][21] performance on trajectory planning [22][23][24], many people have combined their own research to propose corresponding improvement measures. For example, Jing Xia [25] proposed a seven-degree-of-freedom robotic arm anthropomorphic motion planning method under task constraints, which uses collision-free paths combined with robotic arm anthropomorphic motion planning to shorten the motion path by half, while Peng Cai [26] and others proposed a hybrid sampling algorithm based on RRV to recognize local complex regions, which effectively improves the operational efficiency and planning success rate. In this paper, to address the drawbacks of the algorithm, we propose the use of chaotic mapping to increase the number of iteration layers of the population number and to select the iterative optimizer.…”