Proactive Action Visual Residual Reinforcement Learning for Contact-Rich Tasks Using a Torque-Controlled Robot

10/25/2020
by   Yunlei Shi, et al.
0

Contact-rich manipulation tasks are commonly found in modern manufacturing settings. However, manually designing a robot controller is considered hard for traditional control methods as the controller requires an effective combination of modalities and vastly different characteristics. In this paper, we firstly consider incorporating operational space visual and haptic information into reinforcement learning(RL) methods to solve the target uncertainty problem in unstructured environments. Moreover, we propose a novel idea of introducing a proactive action to solve the partially observable Markov decision process problem. Together with these two ideas, our method can either adapt to reasonable variations in unstructured environments and improve the sample efficiency of policy learning. We evaluated our method on a task that involved inserting a random-access memory using a torque-controlled robot, and we tested the success rates of the different baselines used in the traditional methods. We proved that our method is robust and can tolerate environmental variations very well.

READ FULL TEXT

page 1

page 2

page 3

10/24/2018

Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks

Contact-rich manipulation tasks in unstructured environments often requi...
07/28/2019

Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks

Contact-rich manipulation tasks in unstructured environments often requi...
03/04/2019

Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly

Precise robotic manipulation skills are desirable in many industrial set...
06/13/2019

Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards

Connector insertion and many other tasks commonly found in modern manufa...
06/08/2021

Residual Feedback Learning for Contact-Rich Manipulation Tasks with Uncertainty

While classic control theory offers state of the art solutions in many p...
08/18/2020

ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation

Many Reinforcement Learning (RL) approaches use joint control signals (p...
03/31/2021

Simultaneous Navigation and Construction Benchmarking Environments

We need intelligent robots for mobile construction, the process of navig...