PP-Tac: Paper Picking Using Tactile Feedback in Dexterous Robotic Hands

2025-04-23

AI Summary

Grasping thin, flat, and highly deformable objects—such as paper—is challenged by poor perceptual robustness and inadequate motion planning, leading to frequent slippage. Method: This work proposes a novel tactile-driven dexterous manipulation paradigm. It introduces, for the first time, a joint tactile-action learning framework that integrates high-resolution omnidirectional tactile sensing with diffusion-based policy learning. An online friction modulation mechanism is incorporated, and trajectory synthesis is performed in real time by fusing pinch-grasp motion priors. The approach leverages a custom-built tactile sensor, a slip-detection algorithm, and a multi-finger dexterous hand platform. Results: The method achieves an average grasping success rate of 87.5% across diverse paper types varying in material, thickness, and stiffness—significantly outperforming conventional vision- or force-based control methods—and demonstrates the effectiveness and generalizability of tactile closed-loop control for manipulating highly deformable planar objects.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Search and Optimization: Learning to Search

Application Category

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

Abstract

Robots are increasingly envisioned as human companions, assisting with everyday tasks that often involve manipulating deformable objects. Although recent advances in robotic hardware and embodied AI have expanded their capabilities, current systems still struggle with handling thin, flat, and deformable objects such as paper and fabric. This limitation arises from the lack of suitable perception techniques for robust state estimation under diverse object appearances, as well as the absence of planning techniques for generating appropriate grasp motions. To bridge these gaps, this paper introduces PP-Tac, a robotic system for picking up paper-like objects. PP-Tac features a multi-fingered robotic hand with high-resolution omnidirectional tactile sensors sensorname. This hardware configuration enables real-time slip detection and online frictional force control that mitigates such slips. Furthermore, grasp motion generation is achieved through a trajectory synthesis pipeline, which first constructs a dataset of finger's pinching motions. Based on this dataset, a diffusion-based policy is trained to control the hand-arm robotic system. Experiments demonstrate that PP-Tac can effectively grasp paper-like objects of varying material, thickness, and stiffness, achieving an overall success rate of 87.5%. To our knowledge, this work is the first attempt to grasp paper-like deformable objects using a tactile dexterous hand. Our project webpage can be found at: https://peilin-666.github.io/projects/PP-Tac/

Problem

• Handling thin, flat, deformable objects like paper
• Lack of robust perception for diverse object appearances
• Absence of planning techniques for grasp motions

Innovation

• High-resolution omnidirectional tactile sensors for slip detection
• Online frictional force control to mitigate slips
• Diffusion-based policy for grasp motion generation