A Path Planning Method with a Bidirectional Potential Field Probabilistic Step Size RRT for a Dual Manipulator

Abstract

The search efficiency of a rapidly exploring random tree (RRT) can be improved by introducing a high-probability goal bias strategy. In the case of multiple complex obstacles, the high-probability goal bias strategy with a fixed step size will fall into a local optimum, which reduces search efficiency. Herein, a bidirectional potential field probabilistic step size rapidly exploring random tree (BPFPS-RRT) was proposed for the path planning of a dual manipulator by introducing a search strategy of a step size with a target angle and random value. The artificial potential field method was introduced, combining the search features with the bidirectional goal bias and the concept of greedy path optimization. According to simulations, taking the main manipulator as an example, compared with goal bias RRT, variable step size RRT, and goal bias bidirectional RRT, the proposed algorithm reduces the search time by 23.53%, 15.45%, and 43.78% and decreases the path length by 19.35%, 18.83%, and 21.38%, respectively. Moreover, taking the slave manipulator as another example, the proposed algorithm reduces the search time by 6.71%, 1.49%, and 46.88% and decreases the path length by 19.88%, 19.39%, and 20.83%, respectively. The proposed algorithm can be adopted to effectively achieve path planning for the dual manipulator.

Enhancing Mobile Robot Navigation: Optimization of Trajectories through Machine Learning Techniques for Improved Path Planning Efficiency

“…Motion capture technology finds applications in various robotics domains, providing valuable insights into robot movements and interactions with the environment [39]. In mobile robotics, motion capture data are instrumental in creating realistic simulations for training and testing path planning algorithms, offering insights into robot kinematics and dynamics for the development of accurate motion models and controllers [40].…”

Recent advances in Rapidly-exploring random tree: A review

“…The Rapidly-exploring Random Tree (RRT) algorithm commonly referred to in the field is actually heuristically biasing RRT (HBRRT) [ 3 ], target-biased RRT (TBRRT) [ [4] , [5] , [6] , [7] ], goal-biased RRT (GBRRT) [ [8] , [9] , [10] , [11] ], goal-oriented RRT (GORRT) [ [12] , [13] , [14] ] or goal-directed RRT algorithm (GDRRT) [ [15] , [16] , [17] , [18] ], the idea of this algorithm is to take the initial position as the root node and then add leaf nodes by random sampling. When the leaf nodes of the random tree arrive at the target position, the path from the initial position to the goal position is planned.…”

“…In terms of branch step size improvement, some researchers determine the optimal branch size through extensive experiments in a given scenario [ 64 , 65 ], and others give specific strategies, for example, In Ref. [ 6 ], a step growth rate is introduced into the expression of angle selection [ 66 ]. introduces the "step-size dichotomy" to solve the problem of excessively long step size in the APF algorithm due to the large range of obstacle rejection, and applies it to the motion planning of the citrus picking manipulator.…”