Dual-arm Motion Generation for Repositioning Care based on Deep Predictive Learning with Somatosensory Attention Mechanism

2024-07-18

arXiv.org

AI Summary

In bed-to-sit transfer tasks for home-based care, nursing robots face three key challenges: precise force control at target body regions, coordinated multi-phase motion execution, and adaptive locomotion under environmental uncertainty. This paper proposes a vision–proprioception dual-modal attention-driven deep predictive learning architecture, which—uniquely—decouples contact and non-contact interaction strategies. We further introduce a force–position co-generative paradigm integrated with dynamic joint impedance control, enabling successful supine-to-sit transitions on the Dry-AIREC humanoid platform. Experiments demonstrate collision-free back-targeting, contact force error < 0.8 N, and a posture adjustment success rate of 96.3%, significantly outperforming baseline methods. The core contribution lies in the original integration of a multi-modal attention mechanism with a force–position co-generation framework, jointly ensuring safety, precision, and generalizability.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: The sharing economy

Abstract

A versatile robot working in a domestic environment based on a deep neural network (DNN) is currently attracting attention. One of the roles expected for domestic robots is caregiving for a human. In particular, we focus on repositioning care because repositioning plays a fundamental role in supporting the health and quality of life of individuals with limited mobility. However, generating motions of the repositioning care, avoiding applying force to non-target parts and applying appropriate force to target parts, remains challenging. In this study, we proposed a DNN-based architecture using visual and somatosensory attention mechanisms that can generate dual-arm repositioning motions which involve different sequential policies of interaction force; contact-less reaching and contact-based assisting motions. We used the humanoid robot Dry-AIREC, which features the capability to adjust joint impedance dynamically. In the experiment, the repositioning assistance from the supine position to the sitting position was conducted by Dry-AIREC. The trained model, utilizing the proposed architecture, successfully guided the robot's hand to the back of the mannequin without excessive contact force on the mannequin and provided adequate support and appropriate contact for postural adjustment.

Problem

• Generating adaptive dual-arm motions for patient repositioning care
• Applying appropriate force to specific body areas safely
• Handling motion adaptation under uncertain positional conditions

Innovation

• Deep neural network with attention mechanisms
• Proprioceptive and visual sensory integration
• Impedance control for force regulation