Hearing the Slide: Acoustic-Guided Constraint Learning for Fast Non-Prehensile Transport

2025-06-10

AI Summary

In high-speed non-grasping object transport, mechanical vibrations degrade the accuracy of Coulomb friction models—causing dynamic friction constraints to fail and leading to object slippage. To address this, we propose an acoustic-sensing-based online dynamic friction modeling and real-time trajectory optimization method. For the first time, we leverage acoustic signals induced by pallet motion to learn the motion–friction coupling relationship, establishing a mapping from acoustic features to dynamic friction coefficients; trajectory constraints are then updated at each control step. Experiments on a UR5e platform demonstrate that, compared to the conventional Coulomb model, our approach reduces maximum object displacement by 86.0%, significantly enhancing both stability and transport speed for multi-object synchronous transport. This work overcomes the limitations of static friction assumptions and establishes a novel paradigm for high-precision non-grasping manipulation under vibratory conditions.

Technology Category

• Intelligent Robots: Manipulation
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Computer Vision: Motion & Tracking

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: The sharing economy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Object transport tasks are fundamental in robotic automation, emphasizing the importance of efficient and secure methods for moving objects. Non-prehensile transport can significantly improve transport efficiency, as it enables handling multiple objects simultaneously and accommodating objects unsuitable for parallel-jaw or suction grasps. Existing approaches incorporate constraints based on the Coulomb friction model, which is imprecise during fast motions where inherent mechanical vibrations occur. Imprecise constraints can cause transported objects to slide or even fall off the tray. To address this limitation, we propose a novel method to learn a friction model using acoustic sensing that maps a tray's motion profile to a dynamically conditioned friction coefficient. This learned model enables an optimization-based motion planner to adjust the friction constraint at each control step according to the planned motion at that step. In experiments, we generate time-optimized trajectories for a UR5e robot to transport various objects with constraints using both the standard Coulomb friction model and the learned friction model. Results suggest that the learned friction model reduces object displacement by up to 86.0% compared to the baseline, highlighting the effectiveness of acoustic sensing in learning real-world friction constraints.

Problem

• Improving non-prehensile transport efficiency with acoustic sensing
• Addressing imprecise friction constraints during fast robotic motions
• Reducing object displacement using learned dynamic friction models

Innovation

• Acoustic sensing learns dynamic friction model
• Optimization adjusts friction constraints per step
• Reduces object displacement by 86 percent