Manipulate as Human: Learning Task-oriented Manipulation Skills by Adversarial Motion Priors

TL;DR

This paper introduces HMAMP, a novel adversarial learning approach enabling robots to acquire human-like manipulation skills, demonstrated through improved hammering tasks in simulation and real-world settings.

Contribution

The paper presents a new adversarial motion prior method for learning human-style manipulation skills, advancing robot interaction capabilities.

Findings

HMAMP outperforms baseline methods in hammering tasks

Effective transfer from simulation to real robot applications

Generates realistic human-like manipulation trajectories

Abstract

In recent years, there has been growing interest in developing robots and autonomous systems that can interact with human in a more natural and intuitive way. One of the key challenges in achieving this goal is to enable these systems to manipulate objects and tools in a manner that is similar to that of humans. In this paper, we propose a novel approach for learning human-style manipulation skills by using adversarial motion priors, which we name HMAMP. The approach leverages adversarial networks to model the complex dynamics of tool and object manipulation, as well as the aim of the manipulation task. The discriminator is trained using a combination of real-world data and simulation data executed by the agent, which is designed to train a policy that generates realistic motion trajectories that match the statistical properties of human motion. We evaluated HMAMP on one challenging manipulation task: hammering, and the results indicate that HMAMP is capable of learning human-style manipulation skills that outperform current baseline methods. Additionally, we demonstrate that HMAMP has potential for real-world applications by performing real robot arm hammering tasks. In general, HMAMP represents a significant step towards developing robots and autonomous systems that can interact with humans in a more natural and intuitive way, by learning to manipulate tools and objects in a manner similar to how humans do.