High-Bandwidth Tactile-Reactive Control for Grasp Adjustment

2025-09-19

AI Summary

Vision-based grasping suffers from significant contact uncertainty during the terminal phase due to calibration errors, sensor noise, and pose estimation inaccuracies, severely compromising grasp stability. To address this, we propose a purely tactile feedback-driven grasp adjustment algorithm that eliminates reliance on object geometry priors or precise initial pose estimates. Instead, it leverages high-bandwidth (200 Hz) fingertip tactile signals to enable real-time closed-loop control of a 15-degree-of-freedom arm-hand system. Our tactile闭环 control framework is rigorously validated in both simulation and physical experiments. Under conditions of coarse initial pose estimation and unknown contact points, it substantially improves grasp success rate and robustness. This approach decouples grasping performance from high-fidelity visual perception, thereby overcoming the strong dependency on perceptual accuracy inherent in conventional vision-dominated methods. It establishes a new paradigm for dexterous manipulation in weak-prior scenarios.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Vision-only grasping systems are fundamentally constrained by calibration errors, sensor noise, and grasp pose prediction inaccuracies, leading to unavoidable contact uncertainty in the final stage of grasping. High-bandwidth tactile feedback, when paired with a well-designed tactile-reactive controller, can significantly improve robustness in the presence of perception errors. This paper contributes to controller design by proposing a purely tactile-feedback grasp-adjustment algorithm. The proposed controller requires neither prior knowledge of the object's geometry nor an accurate grasp pose, and is capable of refining a grasp even when starting from a crude, imprecise initial configuration and uncertain contact points. Through simulation studies and real-world experiments on a 15-DoF arm-hand system (featuring an 8-DoF hand) equipped with fingertip tactile sensors operating at 200 Hz, we demonstrate that our tactile-reactive grasping framework effectively improves grasp stability.

Problem

• Addresses vision-only grasping constraints from calibration errors
• Develops tactile-reactive controller without object geometry knowledge
• Improves grasp stability from imprecise initial configurations

Innovation

• Tactile-feedback grasp-adjustment algorithm
• No prior object geometry knowledge needed
• 200 Hz fingertip sensors for stability