TAMEn: Tactile-Aware Manipulation Engine for Closed-Loop Data Collection in Contact-Rich Tasks
2026-04-08 • Robotics
Robotics
AI summaryⓘ
The authors created TAMEn, a new system to help robots learn complex two-hand tasks by using a wearable interface that works with many types of robot grippers. Their system collects high-quality data in two ways: one with precise motion capture and another portable method using VR tracking, which also helps recover from mistakes during robot actions. This combined approach improves how well robots can repeat tasks and raises their success rate from 34% to 75%. They also share their hardware design and data to help other researchers.
bimanual manipulationtactile sensingrobotic grippersmotion captureVR trackingclosed-loop controlteleoperationpolicy refinementdemonstration learningvisuo-tactile learning
Authors
Longyan Wu, Jieji Ren, Chenghang Jiang, Junxi Zhou, Shijia Peng, Ran Huang, Guoying Gu, Li Chen, Hongyang Li
Abstract
Handheld paradigms offer an efficient and intuitive way for collecting large-scale demonstration of robot manipulation. However, achieving contact-rich bimanual manipulation through these methods remains a pivotal challenge, which is substantially hindered by hardware adaptability and data efficacy. Prior hardware designs remain gripper-specific and often face a trade-off between tracking precision and portability. Furthermore, the lack of online feasibility checking during demonstration leads to poor replayability. More importantly, existing handheld setups struggle to collect interactive recovery data during robot execution, lacking the authentic tactile information necessary for robust policy refinement. To bridge these gaps, we present TAMEn, a tactile-aware manipulation engine for closed-loop data collection in contact-rich tasks. Our system features a cross-morphology wearable interface that enables rapid adaptation across heterogeneous grippers. To balance data quality and environmental diversity, we implement a dual-modal acquisition pipeline: a precision mode leveraging motion capture for high-fidelity demonstrations, and a portable mode utilizing VR-based tracking for in-the-wild acquisition and tactile-visualized recovery teleoperation. Building on this hardware, we unify large-scale tactile pretraining, task-specific bimanual demonstrations, and human-in-the-loop recovery data into a pyramid-structured data regime, enabling closed-loop policy refinement. Experiments show that our feasibility-aware pipeline significantly improves demonstration replayability, and that the proposed visuo-tactile learning framework increases task success rates from 34% to 75% across diverse bimanual manipulation tasks. We further open-source the hardware and dataset to facilitate reproducibility and support research in visuo-tactile manipulation.