DA-GRD: Decision-Aware Grasp-Relevant Disambiguation for tactile recovery under perception-to-execution mismatches

2026-09-24

AI Summary

This study addresses the failure of visually pre-planned grasps caused by object displacement and the difficulty of recovery without visual feedback. To overcome this, it proposes a decision-aware grasp disambiguation framework that maintains a belief distribution over object poses and employs information gain to drive sparse tactile exploration. Rather than pursuing full object relocalization, the method terminates upon identifying a feasible shared grasp. Evaluations in both MuJoCo simulations and real-world experiments demonstrate that the proposed approach significantly outperforms baselines. In simulation, it achieves an 84.7% physical grasping success rate with only 4.13 exploratory touches on average, while real-world trials yield a 71.7% success rate. These results highlight substantial improvements in interaction efficiency under vision-deprived conditions.

Abstract

Grasping is a fundamental robotic capability that bridges perception and physical task execution. This paper studies grasp pose recovery under a perception-to-execution mismatch, where a grasp generated from visual perception may become spatially stale if the object moves before execution, using only sparse tactile interactions and no further visual observations. We propose DA-GRD, Decision-Aware Grasp-Relevant Disambiguation, which maintains a weighted planar belief over possible object configurations and selects tactile probes according to their ability to eliminate hypotheses and improve agreement among candidate task grasps. Rather than fully relocalizing the object, DA-GRD stops when the remaining hypotheses support a common executable grasp. In MuJoCo experiments on ten rigid objects with translations up to 5~cm and yaw perturbations up to $\pm45^\circ$, DA-GRD achieves an 84.7% physical lift success rate, compared with 9.1% for stale AnyGrasp, 21.2% for the original fix-scan baseline, and 63.7% for fix-scan method adapted with an SE(2) belief. DA-GRD also achieves a 57.3% Task conditioned Success rate. Across objects, it uses a success-average of 4.13 tactile probes over the ten per-object means, corresponding to a 72.5% reduction relative to the fixed 15-probe baselines. Real-world experiments on six objects achieve 71.7% physical lift success and 38.3% task-conditioned success with 4.20 probes on average. These results show that tactile sensing can recover task-relevant grasps under vision-off conditions with limited physical interaction, without requiring complete object localization.

Problem

• grasp pose recovery
• perception-to-execution mismatch
• tactile sensing
• object disambiguation

Innovation

• Tactile Recovery
• Decision-Aware Disambiguation
• Perception-to-Execution Mismatch
• Belief Space Planning
• Grasp Pose Recovery