TactileVAD: Geometric Aliasing-Aware Dynamics for High-Resolution Tactile Control

Miquel Oller, Dmitry Berenson, Nima Fazeli
Proceedings of The 7th Conference on Robot Learning, PMLR 229:3083-3099, 2023.

Abstract

Touch-based control is a promising approach to dexterous manipulation. However, existing tactile control methods often overlook tactile geometric aliasing which can compromise control performance and reliability. This type of aliasing occurs when different contact locations yield similar tactile signatures. To address this, we propose TactileVAD, a generative decoder-only linear latent dynamics formulation compatible with standard control methods that is capable of resolving geometric aliasing. We evaluate TactileVAD on two mechanically-distinct tactile sensors, SoftBubbles (pointcloud data) and Gelslim 3.0 (RGB data), showcasing its effectiveness in handling different sensing modalities. Additionally, we introduce the tactile cartpole, a novel benchmarking setup to evaluate the ability of a control method to respond to disturbances based on tactile input. Evaluations comparing TactileVAD to baselines suggest that our method is better able to achieve goal tactile configurations and hand poses.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-oller23a, title = {TactileVAD: Geometric Aliasing-Aware Dynamics for High-Resolution Tactile Control}, author = {Oller, Miquel and Berenson, Dmitry and Fazeli, Nima}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {3083--3099}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/oller23a/oller23a.pdf}, url = {https://proceedings.mlr.press/v229/oller23a.html}, abstract = {Touch-based control is a promising approach to dexterous manipulation. However, existing tactile control methods often overlook tactile geometric aliasing which can compromise control performance and reliability. This type of aliasing occurs when different contact locations yield similar tactile signatures. To address this, we propose TactileVAD, a generative decoder-only linear latent dynamics formulation compatible with standard control methods that is capable of resolving geometric aliasing. We evaluate TactileVAD on two mechanically-distinct tactile sensors, SoftBubbles (pointcloud data) and Gelslim 3.0 (RGB data), showcasing its effectiveness in handling different sensing modalities. Additionally, we introduce the tactile cartpole, a novel benchmarking setup to evaluate the ability of a control method to respond to disturbances based on tactile input. Evaluations comparing TactileVAD to baselines suggest that our method is better able to achieve goal tactile configurations and hand poses.} }
Endnote
%0 Conference Paper %T TactileVAD: Geometric Aliasing-Aware Dynamics for High-Resolution Tactile Control %A Miquel Oller %A Dmitry Berenson %A Nima Fazeli %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-oller23a %I PMLR %P 3083--3099 %U https://proceedings.mlr.press/v229/oller23a.html %V 229 %X Touch-based control is a promising approach to dexterous manipulation. However, existing tactile control methods often overlook tactile geometric aliasing which can compromise control performance and reliability. This type of aliasing occurs when different contact locations yield similar tactile signatures. To address this, we propose TactileVAD, a generative decoder-only linear latent dynamics formulation compatible with standard control methods that is capable of resolving geometric aliasing. We evaluate TactileVAD on two mechanically-distinct tactile sensors, SoftBubbles (pointcloud data) and Gelslim 3.0 (RGB data), showcasing its effectiveness in handling different sensing modalities. Additionally, we introduce the tactile cartpole, a novel benchmarking setup to evaluate the ability of a control method to respond to disturbances based on tactile input. Evaluations comparing TactileVAD to baselines suggest that our method is better able to achieve goal tactile configurations and hand poses.
APA
Oller, M., Berenson, D. & Fazeli, N.. (2023). TactileVAD: Geometric Aliasing-Aware Dynamics for High-Resolution Tactile Control. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:3083-3099 Available from https://proceedings.mlr.press/v229/oller23a.html.

Related Material