Embodied Self-Supervised Learning (EMSSL) with Sampling and Training Coordination for Robot Arm Inverse Kinematics Model Learning

TL;DR

This paper introduces an embodied self-supervised learning framework for robot arm inverse kinematics, utilizing sampling and training coordination to improve learning efficiency and adaptability in complex, redundant systems.

Contribution

It presents a novel EMSSL framework with sampling and training coordination, enhancing autonomous inverse model learning for robot arms with redundant degrees of freedom.

Findings

Accelerated model learning through batch inference and parallel computation.

Effective fast adaptation strategies for robot arm inverse models.

Experimental validation demonstrating improved learning efficiency.

Abstract

Forward and inverse kinematics models are fundamental to robot arms, serving as the basis for the robot arm's operational tasks. However, in model learning of robot arms, especially in the presence of redundant degrees of freedom, inverse model learning is more challenging than forward model learning due to the non-convex problem caused by multiple solutions. In this paper, we propose a framework for autonomous learning of the robot arm inverse model based on embodied self-supervised learning (EMSSL) with sampling and training coordination. We investigate batch inference and parallel computation strategies for data sampling in order to accelerate model learning and propose two approaches for fast adaptation of the robot arm model. A series of experiments demonstrate the effectiveness of the method we proposed. The related code will be available soon.