aiqbench analysis
This review surveys tactile sensing for robot manipulation, contrasting classical contact-mechanics models with learned approaches like imitation learning, reinforcement learning, and vision-language-action models. Its data-driven half is squarely ML, so the piece is relevant to ML readers even though robotics is the host field. Readers should note that it is a review of an accepted manuscript, not a source of new benchmark results.
Tactile-Based Robotic Manipulation: From Mechanics-Driven to Data-Driven Perspectives
arXiv:2610.30438v1 Announce Type: new Abstract: Tactile sensing provides robots with direct access to physical interactions at the contact interface, making it a critical modality for robust and dexterous manipulation. Over the past several decades, tactile-based manipulation research has evolved from mechanics-driven approaches, which explicitly interpret tactile signals through contact mechanics and task-specific reasoning, to data-driven approaches that learn tactile representations and manipulation policies directly from data. This paper reviews the development of tactile-based manipulation from these two complementary perspectives. We first introduce the fundamentals of tactile sensing, and then review, from a mechanics-driven perspective, how those signals form manipulation-relevant state representations and subsequently influence the robot action. We then examine the recent advances in data-driven tactile manipulation, covering imitation learning, reinforcement learning, vision-language-action models, and predictive models. Finally, we discuss open challenges and future opportunities toward scalable, generalizable, and robust tactile-enabled robotic systems.
Abstract:Tactile sensing provides robots with direct access to physical interactions at the contact interface, making it a critical modality for robust and dexterous manipulation. Over the past several decades, tactile-based manipulation research has evolved from mechanics-driven approaches, which explicitly interpret tactile signals through contact mechanics and task-specific reasoning, to data-driven approaches that learn tactile representations and manipulation policies directly from data. This paper reviews the development of tactile-based manipulation from these two complementary perspectives. We first introduce the fundamentals of tactile sensing, and then review, from a mechanics-driven perspective, how those signals form manipulation-relevant state representations and subsequently influence the robot action. We then examine the recent advances in data-driven tactile manipulation, covering imitation learning, reinforcement learning, vision-language-action models, and predictive models. Finally, we discuss open challenges and future opportunities toward scalable, generalizable, and robust tactile-enabled robotic systems.
30 pages. Author accepted manuscript. Posted with permission from the Annual Review of Control, Robotics, and Autonomous Systems, Volume 10; copyright 2027 the author(s), this https URL. Published version: this https URL
Robotics (cs.RO)
arXiv:2610.30438 [cs.RO]
(or arXiv:2610.30438v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.30438 arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.1146/annurev-control-032125-030330 DOI(s) linking to related resources
Full text under the publisher's open licence · 193 words