Exploiting Ergonomic Priors in Human-to-Robot Task Transfer

TL;DR

This paper presents a novel method for human-to-robot task transfer using null space policies learned from demonstration, enabling accurate task reproduction, generalization across different robot configurations, and obstacle avoidance.

Contribution

It introduces a programming by demonstration approach that learns null space policies for task transfer, outperforming existing methods and enabling system retargeting and obstacle avoidance.

Findings

Accurately reproduces tasks with minimal data points (<10^-14 error)

Outperforms current state-of-the-art in simulated control tasks

Successfully transfers learned tasks from human demonstration to a 7DoF robot

Abstract

In recent years, there has been a booming shift in the development of versatile, autonomous robots by introducing means to intuitively teach robots task-oriented behaviour by demonstration. In this paper, a method based on programming by demonstration is proposed to learn null space policies from constrained motion data. The main advantage to using this is generalisation of a task by retargeting a systems redundancy as well as the capability to fully replace an entire system with another of varying link number and lengths while still accurately repeating a task subject to the same constraints. The effectiveness of the method has been demonstrated in a 3-link simulation and a real world experiment using a human subject as the demonstrator and is verified through task reproduction on a 7DoF physical robot. In simulation, the method works accurately with even as little as five data points producing errors less than 10^-14. The approach is shown to outperform the current state-of-the-art approach in a simulated 3DoF robot manipulator control problem where motions are reproduced using learnt constraints. Retargeting of a systems null space component is also demonstrated in a task where controlling how redundancy is resolved allows for obstacle avoidance. Finally, the approach is verified in a real world experiment using demonstrations from a human subject where the learnt task space trajectory is transferred onto a 7DoF physical robot of a different embodiment.