Physics Residual Dynamics and Reduced Order Whole-Body Planning for Obstacle Aware Human Robot Cloth CoTransportation

2026-10-05

AI Summary

This study addresses the challenge of predicting obstacle collisions caused by underactuated deformations during human-robot collaborative transport of flexible objects. To this end, a hierarchical planning framework is proposed. Methodologically, a physics-residual conditional recurrent variational autoencoder (p-cRVAE) is constructed to correct errors in linear cloth models. Additionally, a reduced-order dual-arm mobile manipulator model preserving nonholonomic constraints is introduced, integrated with Model Predictive Path Integral (MPPI) control and Model Predictive Control (MPC) to achieve efficient cooperative manipulation. Experimental results demonstrate that the proposed framework reduces computation time by 80% while maintaining collision-free trajectories throughout the task. Furthermore, the final cloth deformation is significantly decreased from 0.93 m to 0.28 m, validating the effectiveness of the approach in mitigating unactuated deformations during collaborative transport scenarios.

Abstract

Human--robot co-transportation of deformable objects requires predicting object deformation during motion, since obstacle clearance depends on both the grasp points and the unactuated interior. We present a hierarchical planning framework that combines a learned cloth model with a reduced-order whole-body model of a dual-arm mobile manipulator. A physics-residual conditional recurrent variational autoencoder (p-cRVAE) predicts the full cloth configuration from grasp-point observations by learning a residual correction to a computationally efficient linearized physics model, limiting error accumulation over 40-step planning horizon. The predicted cloth dynamics are embedded in a model predictive path integral (MPPI) planner using a reduced-order representation of a dual-arm mobile manipulator that preserves the non-holonomic base constraint and arm workspace limits. An MPC layer subsequently refines the sampled motion into smooth, executable references for whole-body control. The reduced-order formulation achieves tracking performance comparable to the full 17-DoF model while reducing computation time by approximately 80%. Across four co-transportation scenarios and two carrying speeds, the proposed framework maintains cloth-obstacle clearance where a corner-following baseline results in collisions, while whole-body refinement reduces final cloth deformation from 0.93\,m to 0.28\,m.

Problem

• human-robot co-transportation
• deformable object manipulation
• cloth dynamics prediction
• obstacle avoidance
• whole-body planning

Innovation

• physics-residual dynamics
• reduced-order whole-body planning
• cloth co-transportation
• model predictive path integral (MPPI)
• conditional recurrent variational autoencoder