PATH PLANNING COLLISION AVOIDANCE USING REINFORCEMENT LEARNING
Abstract
Industrial robots have grown over the years making production systems more and more efficient, requiring the need for efficient trajectory generation algorithms that optimize and, if possible, generate collision-free trajectories without interrupting the production process. In this work is presented the use of Reinforcement \nLearning (RL), based on the Q-Learning algorithm, in the trajectory generation of a robotic manipulator and also a comparison of its use with and without constraints of the manipulator kinematics, in order to generate collision free trajectories. The results of the simulations are presented with respect to the efficiency of the \nalgorithm and its use in trajectory generation, a comparison of the computational cost for the use \nof constraints is also presented.
Metrics
Topics
Related Documents
Path Planning Collision Avoidance using Reinforcement Learning
Josias G. BatistaFelipe J. S. VasconcelosKaio Martins RamosDarielson A. SouzaJosé L. N. Silva
UAV Path Planning Employing MPC-Reinforcement Learning Method Considering Collision Avoidance
Mahya RamezaniHamed HabibiJosé Luis Sánchez-LópezHolger Voos
Collision Avoidance System Using Reinforcement Learning
Aravindhan ThaninayagamS. V. Raswanth PrasathRupesh RoshanDarshana Othayoth
A COLREGs-based path-planning method for collision avoidance considering path cost through reinforcement learning
Wanping SongZengqiang ChenMingwei SunYongshuai WangQinglin Sun
Path planning and dynamic collision avoidance algorithm under COLREGs via deep reinforcement learning
Xinli XuPeng CaiZahoor AhmedVidya Sagar YellapuWeidong Zhang