基于DPPO的移动采摘机器人避障路径规划及仿真

Obstacle Avoidance Path Planning and Simulation of Mobile Picking Robot Based on DPPO

针对移动采摘机器人在野外作业过程中面临随机多变的复杂路径环境难以自主决策的难题,提出一种基于深度强化学习的自主避障路径规划方法。设定状态空间和动作空间,借助人工势场法设计奖励函数的思想,提出了一种基于碰撞锥避碰检测的障碍物惩罚系数设定方法,提高自主避碰能力。构建了虚拟仿真系统,使用分布式近端策略优化算法(distributed proximal policy optimization,DPPO)完成了移动采摘机器人的学习训练并进行实验验证。仿真结果表明:本系统能够快速、稳定的控制虚拟移动采摘机器人自主避障,获得更优的作业路径,为采摘机器人自主导航提供理论与技术支撑。

Aiming at the autonomous decision-making difficulty of mobile picking robots in random and changeable complicated path environment during field operations,an autonomous obstacle avoidance path planning method based on deep reinforcement learning is propose.By setting the state space and action space and using the artificial potential field method to design the reward function,an obstacle penalty coefficient setting method based on collision cone collision avoidance detection is proposed to improve the autonomous collision avoidance ability.A virtual simulation system is constructed,in which the learning and training of the mobile picking robot is carried out and verified by experiments through the distributed proximal policy optimization(DPPO).Simulation results show that the system can quickly and stably control the virtual mobile picking robot to autonomously avoid obstacles and obtain a better operating path,which can provide theoretical and technical support for the autonomous navigation of picking robot.