Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Octopi: Object Property Reasoning with Large Tactile-Language Models

About

Physical reasoning is important for effective robot manipulation. Recent work has investigated both vision and language modalities for physical reasoning; vision can reveal information about objects in the environment and language serves as an abstraction and communication medium for additional context. Although these works have demonstrated success on a variety of physical reasoning tasks, they are limited to physical properties that can be inferred from visual or language inputs. In this work, we investigate combining tactile perception with language, which enables embodied systems to obtain physical properties through interaction and apply commonsense reasoning. We contribute a new dataset PhysiCLeAR, which comprises both physical/property reasoning tasks and annotated tactile videos obtained using a GelSight tactile sensor. We then introduce Octopi, a system that leverages both tactile representation learning and large vision-language models to predict and reason about tactile inputs with minimal language fine-tuning. Our evaluations on PhysiCLeAR show that Octopi is able to effectively use intermediate physical property predictions to improve its performance on various tactile-related tasks. PhysiCLeAR and Octopi are available at https://github.com/clear-nus/octopi.

Samson Yu, Kelvin Lin, Anxing Xiao, Jiafei Duan, Harold Soh• 2024

Related benchmarks

TaskDatasetResultRank
Tactile ReasoningTouchReason-Bench
H-Acc58.1
12
Tactile Property UnderstandingPHYSICLEAR
PC Accuracy55.06
6
Commonsense-Driven ReasoningTactileBench 1.0 (test)
METEOR25.04
4
Fundamental property UnderstandingTactileBench 1.0 (test)
METEOR Score29.7
4
Tactile Commonsense ReasoningTactileBench
METEOR Score28.83
4
Tactile Interaction PerceptionTactileBench 1.0 (test)
METEOR Score29.89
4
Tactile Question AnsweringPHYSICLEAR
CIDEr141.2
3
Showing 7 of 7 rows

Other info

Follow for update