Learning Inverse Statics Models Efficiently

TL;DR

This paper introduces an enhanced online learning method for inverse statics models that leverages symmetries to significantly reduce sample complexity, demonstrated on various robotic arms.

Contribution

It extends Online Goal Babbling and Direction Sampling to efficiently learn inverse statics mappings by exploiting symmetries, reducing sample requirements.

Findings

Successful learning of inverse statics for 2R, 3R, and 4R robotic arms.

Sample reduction factors of at least 8 and 16 for 2R and 3R arms, respectively.

Demonstrates the effectiveness of symmetry exploitation in robotic inverse statics learning.

Abstract

Online Goal Babbling and Direction Sampling are recently proposed methods for direct learning of inverse kinematics mappings from scratch even in high-dimensional sensorimotor spaces following the paradigm of "learning while behaving". To learn inverse statics mappings - primarily for gravity compensation - from scratch and without using any closed-loop controller, we modify and enhance the Online Goal Babbling and Direction Sampling schemes. Moreover, we exploit symmetries in the inverse statics mappings to drastically reduce the number of samples required for learning inverse statics models. Results for a 2R planar robot, a 3R simplified human arm, and a 4R humanoid robot arm clearly demonstrate that their inverse statics mappings can be learned successfully with our modified online Goal Babbling scheme. Furthermore, we show that the number of samples required for the 2R and 3R arms can be reduced by a factor of at least 8 and 16 resp. -depending on the number of discovered symmetries.