Non-linear system identification and state estimation in a pneumatic based soft continuum robot

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

16 Citations (Scopus)

Abstract

Sensory data play a significant role in the control of robots. While soft robots are promising for operation in unstructured environments, it may be difficult to sensorize them due to their inherent softness. One way to overcome this challenge is to use an observer/filter to estimate the variables (states) that would have been measured by those sensors. Nevertheless, applying an observer/filter to a soft robot introduces the challenge of requiring an analytical model of these highly nonlinear systems. In this paper, we develop a framework based on nonlinear system identification and state estimation to estimate the curvature angle of a pneumatic-based tentacle soft robot. We model the tentacle using the wavelet/sigmoid network, and use an Extended Kalman Filter (EKF) to estimate the curvature and verify the estimate using camera vision. The results show that EKF can estimate the curvature angle at a low error, even when the identified system model is not accurate and the sensor measurement is noisy.

Original languageEnglish
Title of host publicationCCTA 2019 - 3rd IEEE Conference on Control Technology and Applications
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages39-46
Number of pages8
ISBN (Electronic)9781728127675
DOIs
Publication statusPublished - Aug 2019
EventIEEE Conference on Control Technology and Applications 2019 - Hong Kong, China
Duration: 19 Aug 201921 Aug 2019
Conference number: 3rd
https://ieeexplore.ieee.org/xpl/conhome/8911117/proceeding (Proceedings)

Publication series

NameCCTA 2019 - 3rd IEEE Conference on Control Technology and Applications

Conference

ConferenceIEEE Conference on Control Technology and Applications 2019
Abbreviated titleCCTA 2019
Country/TerritoryChina
CityHong Kong
Period19/08/1921/08/19
Internet address

Cite this