MorphoGuard: A Morphology-Based Whole-Body Interactive Motion Controller

TL;DR

MorphoGuard introduces a morphology-constrained whole-body control network enabling robots to handle complex multi-contact interactions with high precision, demonstrated through experiments on a dual-arm platform.

Contribution

This work presents a novel morphology-based control network that explicitly manages arbitrary contact combinations for enhanced whole-body robotic interaction.

Findings

Achieves approximately 1 cm contact point management error

Effectively handles complex multi-contact tasks in experiments

Demonstrates improved control in multi-object manipulation

Abstract

Whole-body control (WBC) has demonstrated significant advantages in complex interactive movements of high-dimensional robotic systems. However, when a robot is required to handle dynamic multi-contact combinations along a single kinematic chain-such as pushing open a door with its elbow while grasping an object-it faces major obstacles in terms of complex contact representation and joint configuration coupling. To address this, we propose a new control approach that explicitly manages arbitrary contact combinations, aiming to endow robots with whole-body interactive capabilities. We develop a morphology-constrained WBC network (MorphoGuard)-which is trained on a self-constructed dual-arm physical and simulation platform. A series of model recommendation experiments are designed to systematically investigate the impact of backbone architecture, fusion strategy, and model scale on network performance. To evaluate the control performance, we adopt a multi-object interaction task as the benchmark, requiring the model to simultaneously manipulate multiple target objects to specified positions. Experimental results show that the proposed method achieves a contact point management error of approximately 1 cm, demonstrating its effectiveness in whole-body interactive control.