A New Data Source for Inverse Dynamics Learning

TL;DR

This paper introduces a novel data source derived from feedback control signals to improve inverse dynamics learning in robots, enhancing model accuracy and convergence speed in both simulation and real-world applications.

Contribution

It proposes a new training signal from desired accelerations, enabling better inverse dynamics models by combining traditional and feedback-based data sources.

Findings

Combined data sources lead to faster convergence.

The approach improves model accuracy in real-world tests.

Incremental learning enhances inverse dynamics models.

Abstract

Modern robotics is gravitating toward increasingly collaborative human robot interaction. Tools such as acceleration policies can naturally support the realization of reactive, adaptive, and compliant robots. These tools require us to model the system dynamics accurately -- a difficult task. The fundamental problem remains that simulation and reality diverge--we do not know how to accurately change a robot's state. Thus, recent research on improving inverse dynamics models has been focused on making use of machine learning techniques. Traditional learning techniques train on the actual realized accelerations, instead of the policy's desired accelerations, which is an indirect data source. Here we show how an additional training signal -- measured at the desired accelerations -- can be derived from a feedback control signal. This effectively creates a second data source for learning inverse dynamics models. Furthermore, we show how both the traditional and this new data source, can be used to train task-specific models of the inverse dynamics, when used independently or combined. We analyze the use of both data sources in simulation and demonstrate its effectiveness on a real-world robotic platform. We show that our system incrementally improves the learned inverse dynamics model, and when using both data sources combined converges more consistently and faster.