DeepAI AI Chat
Log In Sign Up

MidasTouch: Monte-Carlo inference over distributions across sliding touch

by   Sudharshan Suresh, et al.

We present MidasTouch, a tactile perception system for online global localization of a vision-based touch sensor sliding on an object surface. This framework takes in posed tactile images over time, and outputs an evolving distribution of sensor pose on the object's surface, without the need for visual priors. Our key insight is to estimate local surface geometry with tactile sensing, learn a compact representation for it, and disambiguate these signals over a long time horizon. The backbone of MidasTouch is a Monte-Carlo particle filter, with a measurement model based on a tactile code network learned from tactile simulation. This network, inspired by LIDAR place recognition, compactly summarizes local surface geometries. These generated codes are efficiently compared against a precomputed tactile codebook per-object, to update the pose distribution. We further release the YCB-Slide dataset of real-world and simulated forceful sliding interactions between a vision-based tactile sensor and standard YCB objects. While single-touch localization can be inherently ambiguous, we can quickly localize our sensor by traversing salient surface geometries. Project page:


page 6

page 7

page 8

page 14

page 15

page 16

page 18

page 19


Tactile Mapping and Localization from High-Resolution Tactile Imprints

This work studies the problem of shape reconstruction and object localiz...

PatchGraph: In-hand tactile tracking with learned surface normals

We address the problem of tracking 3D object poses from touch during in-...

Tactile-Filter: Interactive Tactile Perception for Part Mating

Humans rely on touch and tactile sensing for a lot of dexterous manipula...

Tac2Structure: Object Surface Reconstruction Only through Multi Times Touch

Inspired by the ability of humans to perceive the surface texture of unf...

Cable Manipulation with a Tactile-Reactive Gripper

Manipulation of flexible cables is relevant to both industrial and house...

FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback

In this paper, we address the problem of using visuo-tactile feedback fo...