Saved in:
Bibliographic Details
Main Authors: Yang, Yifei, Chen, Lu, Song, Zherui, Chen, Yenan, Sun, Wentao, Zhou, Zhongxiang, Xiong, Rong, Wang, Yue
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.23835
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917972440776704
author Yang, Yifei
Chen, Lu
Song, Zherui
Chen, Yenan
Sun, Wentao
Zhou, Zhongxiang
Xiong, Rong
Wang, Yue
author_facet Yang, Yifei
Chen, Lu
Song, Zherui
Chen, Yenan
Sun, Wentao
Zhou, Zhongxiang
Xiong, Rong
Wang, Yue
contents Grasp-based manipulation tasks are fundamental to robots interacting with their environments, yet gripper state ambiguity significantly reduces the robustness of imitation learning policies for these tasks. Data-driven solutions face the challenge of high real-world data costs, while simulation data, despite its low costs, is limited by the sim-to-real gap. We identify the root cause of gripper state ambiguity as the lack of tactile feedback. To address this, we propose a novel approach employing pseudo-tactile as feedback, inspired by the idea of using a force-controlled gripper as a tactile sensor. This method enhances policy robustness without additional data collection and hardware involvement, while providing a noise-free binary gripper state observation for the policy and thus facilitating pure simulation learning to unleash the power of simulation. Experimental results across three real-world grasp-based tasks demonstrate the necessity, effectiveness, and efficiency of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2503_23835
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Disambiguate Gripper State in Grasp-Based Tasks: Pseudo-Tactile as Feedback Enables Pure Simulation Learning
Yang, Yifei
Chen, Lu
Song, Zherui
Chen, Yenan
Sun, Wentao
Zhou, Zhongxiang
Xiong, Rong
Wang, Yue
Robotics
Grasp-based manipulation tasks are fundamental to robots interacting with their environments, yet gripper state ambiguity significantly reduces the robustness of imitation learning policies for these tasks. Data-driven solutions face the challenge of high real-world data costs, while simulation data, despite its low costs, is limited by the sim-to-real gap. We identify the root cause of gripper state ambiguity as the lack of tactile feedback. To address this, we propose a novel approach employing pseudo-tactile as feedback, inspired by the idea of using a force-controlled gripper as a tactile sensor. This method enhances policy robustness without additional data collection and hardware involvement, while providing a noise-free binary gripper state observation for the policy and thus facilitating pure simulation learning to unleash the power of simulation. Experimental results across three real-world grasp-based tasks demonstrate the necessity, effectiveness, and efficiency of our approach.
title Disambiguate Gripper State in Grasp-Based Tasks: Pseudo-Tactile as Feedback Enables Pure Simulation Learning
topic Robotics
url https://arxiv.org/abs/2503.23835