Relaxation-Aware Multimodal Sensing of Soft Gripper Driven by Structure-Perception-Learning

Venue: RSS 2026 (Sydney, Jul 13–17) · Session: Perception and Estimation · paper #177 Authors: Yanzhe Wang, Hao Wu, Ziyi Zheng, Huixu Dong Program page: https://roboticsconference.org/program/papers/177/

No public preprint found (searched arXiv, Aug 6 2026); summary derived from the verified program abstract. Trend placement and neighbors: RSS 2026 survey.

Summary

Problem. Soft grippers grasp safely thanks to compliance, but the viscoelasticity of soft polymers causes stress relaxation — grasping force continuously decays during holding, undermining stable, sustained grasps. Method. The authors present an integrated structure-perception-learning framework: a variable-stiffness soft gripper with onboard vision and infrared thermography that tracks deformation and the temperature field in real time, combined with a temperature-coupled viscoelastic force representation and a physics-informed learning model that reconstructs the force trend and explicitly compensates relaxation-induced decay during holding. Results. In a 280 s force-controlled grasp-and-hold task, the method holds the desired force with 0.066 N mean absolute error, outperforming fixed-aperture and instantaneous-only baselines by 80% and 95% respectively — supporting the paper's mechanism-AI co-design thesis (mechanisms shape feasible interactions; learning compensates residual viscoelastic uncertainty).

Abstract

Achieving stable, sustained grasping with soft robotic hands remains a fundamental challenge. Compliance enables safe and adaptive contact, yet the intrinsic viscoelasticity of soft polymers leads to stress relaxation and a continuous decay of grasping force during holding. Inspired by human grasping, which combines phase-dependent stiffness regulation with continuous sensing and feedback, this paper presents an integrated structure–perception–learning framework. We develop a variable-stiffness soft gripper that uses onboard vision and infrared thermography to track deformation and the temperature field in real time, preserving continuous tracking of the interaction state. To mitigate relaxation-induced force decay, we propose a temperature-coupled viscoelastic force representation, together with a physics-informed learning model, to reconstruct the force trend and provide explicit compensation during holding. Experiments show that, in a 280s force-controlled grasp-and-hold task, the proposed method maintains the desired force with a mean absolute error of 0.066N, outperforming fixed-aperture and instantaneous-only baselines by 80% and 95%, respectively. Overall, the results support a mechanism–AI co-design view: mechanisms shape feasible interactions, while learning compensates remaining uncertainty in viscoelastic dynamics, together enabling stable, sustained grasping.

Wiki context

Related topic reviews: Review-Independent-Visual-Representation · Review-Tactile-VLA

← Back to RSS 2026 survey · Home