西安工程大学学报2025，Vol.39Issue(2)：65-74,10.DOI:10.13338/j.issn.1674-649x.2025.02.008
深度强化学习下的管道气动软体机器人控制
Pipe pneumatic soft robot control based on deep reinforcement learning
摘要
Abstract
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 de-formation 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 con-trol,enabling the design of an autonomous motion controller for dynamic bending.The experi-mental results demonstrate that the PR-DDPG algorithm effectively controls the autonomous con-tinuous 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.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Key words
pipeline soft robot/motion control/deep reinforcement learning/depth deterministic policy gradient algorithm分类
机械工程引用本文复制引用
江雨霏,朱其新..深度强化学习下的管道气动软体机器人控制[J].西安工程大学学报,2025,39(2):65-74,10.基金项目
国家自然科学基金项目(51875380,62063010,51375323) （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) （关键核心技术"揭榜挂帅"）
苏州市科技计划(基础研究)项目(SJC2023002) （基础研究）
