aiqbench analysis
This research advances human-robot collaboration by integrating temporal tactile encoding with compliance control within a Vision-Language-Action (VLA) framework to improve the safety and reliability of bimanual handovers. The study demonstrates that combining force reduction strategies with history-aware tactile feedback significantly outperforms visual-only or non-compliant baselines in distinguishing user intent from accidental contact. This work represents a significant step forward in multimodal machine learning for physical robotics, specifically addressing the critical challenge of safe human-robot interaction.
Temporal Tactile Encoding and Compliance for Intent-Aware Robot-to-Human Bimanual Handover
arXiv:2609.05282v1 Announce Type: new Abstract: Reliable robot-to-human handover requires the robot to infer when the person is ready to receive the object, and release it safely, comfortably, and at the right time. This is challenging because visual observations alone may not disambiguate clear taking intent from accidental contact, weak grasping, wrong-direction forces, or transient interactions. In this work we treat human-robot handover as an intrinsically multimodal problem. Our approach couples a VLA model with a compliance controller that reduces interaction forces during object transfer. We finetune the VLA model with human demonstrations using RGB observation, temporally encoded tactile feedback and proprioception. We evaluate the complete system in a human-subject study against two baselines: one without tactile feedback and one using tactile feedback without compliance control. We hypothesize that combining compliance and temporal tactile encoding yields the most reliable and comfortable handovers, as compliance facilitates physical interaction while tactile history captures sustained taking intent. Performance is measured through objective metrics and an ad-hoc questionnaire. The results show that the two components provide complementary benefits and substantially outperform the baselines. Code and data will be released upon acceptance.
Abstract:Reliable robot-to-human handover requires the robot to infer when the person is ready to receive the object, and release it safely, comfortably, and at the right time. This is challenging because visual observations alone may not disambiguate clear taking intent from accidental contact, weak grasping, wrong-direction forces, or transient interactions. In this work we treat human-robot handover as an intrinsically multimodal problem. Our approach couples a VLA model with a compliance controller that reduces interaction forces during object transfer. We finetune the VLA model with human demonstrations using RGB observation, temporally encoded tactile feedback and proprioception. We evaluate the complete system in a human-subject study against two baselines: one without tactile feedback and one using tactile feedback without compliance control. We hypothesize that combining compliance and temporal tactile encoding yields the most reliable and comfortable handovers, as compliance facilitates physical interaction while tactile history captures sustained taking intent. Performance is measured through objective metrics and an ad-hoc questionnaire. The results show that the two components provide complementary benefits and substantially outperform the baselines. Code and data will be released upon acceptance.
Robotics (cs.RO)
arXiv:2609.05282 [cs.RO]
(or arXiv:2609.05282v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.05282 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 274 words
Related coverage
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
RGB-D Video Generation for Improving Human-to-Robot Object Handover Prediction
arXiv · Sep 2, 2026
Links #5: 2026/07
LessWrong · Jul 31, 2026
Uncertainty-Aware Intention Prediction for Human-to-Robot Assembly Teleoperation
arXiv · Jun 9, 2026