Fast and Accurate Tactile Object Recognition using a Random Convolutional Kernel Transform

Research output: Contribution to conferencePaperpeer-review

32 Downloads (Pure)

Abstract

The task of tactile object recognition is an ever-evolving research area comprising of the gathering and processing of features related to the physical interaction between a robotic system and an object or material. For a robotic system to be capable of interacting with the real-world, the ability to identify the object it is interacting with in real-time is required. Information about the object is often strongly enhanced using tactile sensing. Recent advancements in time series classifiers have allowed for the accuracy of real-time tactile object recognition to be improved, therefore generating opportunities for enhanced solutions within this field of robotics. In this paper, improvements are proposed to the state-of-the-art time series classifier ROCKET for analysis of tactile data for the purposes of object recognition. A variety of classifier heads are implemented within the ROCKET pipeline; these models are then trained and tested on the PHAC-2 tactile dataset, achieving state-of-the-art performance of 96.3% for single-modality tactile object recognition while only requiring 11 minutes to train.
Original languageEnglish
Pages599-604
Number of pages6
DOIs
Publication statusPublished online - 1 Feb 2024
EventInternational Conference on Advanced Robotics (ICAR) - , United Arab Emirates
Duration: 5 Dec 20238 Dec 2023

Conference

ConferenceInternational Conference on Advanced Robotics (ICAR)
Country/TerritoryUnited Arab Emirates
Period5/12/238/12/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Fingerprint

Dive into the research topics of 'Fast and Accurate Tactile Object Recognition using a Random Convolutional Kernel Transform'. Together they form a unique fingerprint.

Cite this