摘要
在复杂的管道环境中,与刚性机器人相比,软体机器人更适合执行操作任务。然而,由于具有无限自由度和非线性变形的特点,软体机器人的控制是一个较大的挑战。根据管道气动软体机器人变形方式进行动力学建模,提出一种结合预测奖励技术的深度确定性策略梯度(predictive reward-deep deterministic policy gradient,PR-DDPG)算法,将其应用于管道气动软体机器人的连续运动控制,为其动态的弯曲运动控制问题设计自主运动控制器。实验结果表明:PR-DDPG算法能够有效控制管道气动软体机器人在三维空间中进行自主连续运动,且可控制其前端到达目标点与目标方向。与深度确定性策略梯度(deep deterministic policy gradient,DDPG)算法相比,PR-DDPG算法的收敛时间减少了约17%,奖励值提高了约20%,提高了管道气动软体机器人的连续运动控制性能。
In complex pipeline environments,soft robots are more suitable for operational tasks compared to rigid robots.However,due to their infinite degrees of freedom and nonlinear deformation characteristics,the control of soft robots posed a significant challenge.To address the dynamic bending motion control of pipe pneumatic soft,a dynamic model was developed based on their deformation characteristics,and a predictive reward-deep deterministic policy gradient(PR-DDPG)algorithm was proposed.This algorithm was applied to achieve continuous motion control,enabling the design of an autonomous motion controller for dynamic bending.The experimental results demonstrate that the PR-DDPG algorithm effectively controls the autonomous continuous motion of pipe pneumatic soft in three-dimensional space,allowing their front ends to reach target positions and orientations.Compared with the deep deterministic policy gradient(DDPG)algorithm,the convergence time of PR-DDPG is reduced by approximately 17%,and the reward value is improved by about 20%.The PR-DDPG algorithm improves the continuous motion control capabilities of pipe pneumatic soft.
作者
江雨霏
朱其新
JIANG Yufei;ZHU Qixin(School of Electronic and Information Engineering,Suzhou University of Science and Technology,Suzhou 215009,Jiangsu,China;School of Mechanical Engineering,Suzhou University of Science and Technology,Suzhou 215009,Jiangsu,China;Jiangsu Province Intelligent Coexisting-Cooperative-Cognitive Robot Engineering Research Center,Suzhou 215009,Jiangsu,China;Suzhou Key Laboratory of Coexisting-Cooperative-Cognitive Robot Technology,Suzhou 215009,Jiangsu,China)
出处
《西安工程大学学报》
2025年第2期65-74,共10页
Journal of Xi’an Polytechnic University
基金
国家自然科学基金项目(51875380,62063010,51375323)
苏州市科技发展计划(关键核心技术“揭榜挂帅”)项目(SYG2024148)
苏州市科技计划(基础研究)项目(SJC2023002)。
关键词
管道软体机器人
运动控制
深度强化学习
深度确定性策略梯度算法
pipeline soft robot
motion control
deep reinforcement learning
depth deterministic policy gradient algorithm
作者简介
第一作者:江雨霏(1998-),女,硕士研究生;通信作者:朱其新(1971-),男,教授,研究方向为伺服控制、机器人、控制理论及应用。E-mail:bob21cn@163.com。
