Nudge Before You Push: Physics-Aware Navigation via Tactile Probing

2026-10-04

AI Summary

This study addresses the challenge of erroneous robotic navigation decisions caused by visually similar containers with varying masses. To mitigate this, we propose a "push-before-move" physics-aware safe navigation strategy. Methodologically, a Hall-effect array fingertip sensor is integrated with TacPhys, a force-sequence parsing model, to accurately estimate object mass through minimal-contact light pushing interactions. Furthermore, a repetitive patrol planning algorithm is designed to effectively balance exploration costs against path efficiency. Experimental results demonstrate that the offline mass estimation achieves a mean absolute error as low as 0.28 kg, reducing the missed-push rate to 5.5%. The proposed approach recovers 90% of the optimal path reward, significantly decreasing the need for human intervention during autonomous navigation tasks.

Abstract

Visually identical containers can conceal loads that require different handling decisions. We present TANav, which uses a brief nudge to measure push resistance for navigation under a site-defined handling boundary. TacPhys reads the force sequence, with optional RGB-D and kinematics, into a mass estimate for push authorization. A repeated-patrol planner weighs probe and route costs, requests a second contact when useful, and reuses observations across visits. In simulation, TacPhys approaches a resistance-only Bayes reference and reduces missed pushes from 28.7% to 5.5% relative to peak-force thresholding at comparable low-risk operating points. In repeated-patrol simulation, TANav recovers 90% of the oracle's path saving, more than halves human interventions relative to always-detour, and reduces boundary violations from 4.3% to 2.9% relative to RGB-D-only probing. On a quadruped manipulator with a Hall-array fingertip, offline zero-shot MAE is 0.28-1.07 kg on containers up to 2.82 kg. Force-rise calibration at 3 kg gives 93.5% pooled offline accuracy (86.4% on non-cube episodes); a separate raw-peak rule gives 15 of 20 correct online decisions on unseen boxes.

Problem

• tactile probing
• physics-aware navigation
• mass estimation
• push authorization
• container handling

Innovation

• tactile probing
• physics-aware navigation
• mass estimation
• repeated-patrol planning
• zero-shot transfer