Tac2Pose: Tactile Object Pose Estimation from the First Touch
Maria Bauza, Antonia Bronars, Alberto Rodriguez

TL;DR
Tac2Pose introduces a novel tactile pose estimation method that uses simulation and contrastive learning to accurately determine object poses from the first tactile contact, accommodating pose uncertainty.
Contribution
It presents a new simulation-based, object-specific perception model for tactile pose estimation that leverages contrastive learning and can incorporate additional constraints.
Findings
High accuracy pose estimation for 20 objects.
Robustness to object model uncertainty.
Outperforms baseline tactile pose estimation methods.
Abstract
In this paper, we present Tac2Pose, an object-specific approach to tactile pose estimation from the first touch for known objects. Given the object geometry, we learn a tailored perception model in simulation that estimates a probability distribution over possible object poses given a tactile observation. To do so, we simulate the contact shapes that a dense set of object poses would produce on the sensor. Then, given a new contact shape obtained from the sensor, we match it against the pre-computed set using an object-specific embedding learned using contrastive learning. We obtain contact shapes from the sensor with an object-agnostic calibration step that maps RGB tactile observations to binary contact shapes. This mapping, which can be reused across object and sensor instances, is the only step trained with real sensor data. This results in a perception model that localizes objects…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTactile and Sensory Interactions · Robot Manipulation and Learning · EEG and Brain-Computer Interfaces
