Continuous Control of a Soft Continuum Arm using Deep Reinforcement Learning
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 497-503
Abstract
Soft Continuum Arms (SCAs) are challenging to control due to their highly nonlinear characteristics and sensitivity to external loading. Recent efforts to address the control problem using machine learning techniques are limited to simple SCA architectures. In this paper, we train a model-free reinforcement learning control policy based on Deep Deterministic Policy Gradient (DDPG) for end effector path tracking on a BR 2 SCA. Unlike simple SCA architectures, the BR 2 SCA has the functionality to bend and rotate spatially thus leading to enhanced workspace and ability to perform complex tasks. The control policy is first validated in simulations and then implemented on a prototype BR 2 with state feedback. An average tracking error less than 3 cm (<; diameter of the SCA) is reported using the proposed control policy. The efficacy of the control policy is validated for different loading conditions both in simulations and on the SCA prototype.Keywords
This publication has 17 references indexed in Scilit:
- Learning dynamic models for open loop predictive control of soft robotic manipulatorsBioinspiration & Biomimetics, 2017
- Model-free control for soft manipulators based on reinforcement learning2017
- Toward Effective Soft Robot Control via Reinforcement Learning2017
- Multiobjective Optimization for Stiffness and Position Control in a Soft Robot Arm ModuleIEEE Robotics and Automation Letters, 2017
- Exploiting Morphology of a Soft Manipulator for Assistive Tasks2017
- A Bioinspired Soft Robotic Gripper for Adaptable and Effective GraspingSoft Robotics, 2015
- Model-Less Feedback Control of Continuum Manipulators in Constrained EnvironmentsIEEE Transactions on Robotics, 2014
- Predicting initialization effectiveness for trajectory optimization2014
- OctArm - A soft robotic manipulator2007
- Learning inverse kinematics2002