aiqbench analysis
This research advances embodied AI by introducing Tactile Memory with Soft Robot, which uses a Masked Tactile Trajectory Transformer to enable robust manipulation in uncertain contact-rich environments. The system leverages retrieval-based control on soft wrists to adapt to unseen scenarios without explicit subtask segmentation, demonstrating superior success rates in real-robot peg-in-hole experiments.
Tactile Memory with Soft Robot: Robust Object Insertion via Masked Encoding and Soft Wrist
arXiv:2601.19275v2 Announce Type: replace-cross Abstract: Tactile memory, the ability to store and retrieve touch-based experience, is critical for contact-rich tasks such as key insertion under uncertainty. To replicate this capability, we introduce Tactile Memory with Soft Robot (TaMeSo-bot), a system that integrates a soft wrist with tactile retrieval-based control to enable safe and robust manipulation. The soft wrist allows safe contact exploration during data collection, while tactile memory reuses past demonstrations via retrieval for flexible adaptation to unseen scenarios. The core of this system is the Masked Tactile Trajectory Transformer (MAT$^\text{3}$), which jointly models spatiotemporal interactions between robot actions, distributed tactile cues, force-torque measurements, and proprioceptive signals. Through masked token prediction, MAT$^\text{3}$ learns rich spatiotemporal representations by inferring missing sensory information from context, autonomously extracting task-relevant features without explicit subtask segmentation. We validate our approach on peg-in-hole tasks with diverse pegs and conditions in real-robot experiments. Our extensive evaluation demonstrates that MAT$^\text{3}$ achieves higher success rates than the baselines over all conditions and shows remarkable capability to adapt to unseen pegs and conditions.
Abstract:Tactile memory, the ability to store and retrieve touch-based experience, is critical for contact-rich tasks such as key insertion under uncertainty. To replicate this capability, we introduce Tactile Memory with Soft Robot (TaMeSo-bot), a system that integrates a soft wrist with tactile retrieval-based control to enable safe and robust manipulation. The soft wrist allows safe contact exploration during data collection, while tactile memory reuses past demonstrations via retrieval for flexible adaptation to unseen scenarios. The core of this system is the Masked Tactile Trajectory Transformer (MAT$^\text{3}$), which jointly models spatiotemporal interactions between robot actions, distributed tactile cues, force-torque measurements, and proprioceptive signals. Through masked token prediction, MAT$^\text{3}$ learns rich spatiotemporal representations by inferring missing sensory information from context, autonomously extracting task-relevant features without explicit subtask segmentation. We validate our approach on peg-in-hole tasks with diverse pegs and conditions in real-robot experiments. Our extensive evaluation demonstrates that MAT$^\text{3}$ achieves higher success rates than the baselines over all conditions and shows remarkable capability to adapt to unseen pegs and conditions.
Accepted for publication in IEEE Robotics and Automation Letters (RA-L), 2026. Project page: this https URL
Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2601.19275 [cs.RO]
(or arXiv:2601.19275v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2601.19275 Focus to learn more arXiv-issued DOI via DataCite
IEEE Robotics and Automation Letters, vol. 11, no. 7, pp. 7844-7851, July 2026
https://doi.org/10.1109/LRA.2026.3692097 Focus to learn more DOI(s) linking to related resources
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 · 304 words
