Real-time collision avoidance in a dynamic environment for an industrial robotic arm

Uchenna Emeoha Ogenyi, Qing Gao, Dalin Zhou, Charles Chimwemwe Phiri, Zhaojie Ju, Honghai Liu

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

Abstract

This paper proposed learning from demonstration control policy that permits generalisation in an unstructured and dynamic environment. The approach combines a probabilistic model with a reactive approach that learns the cost function of an unknown state of the environmental constraints. The approach redefines the robot’s behaviour towards a trajectory that satisfies both the task and scene constraints, facilitating enhanced human-robot coexistence.
Original languageEnglish
Title of host publicationICIRA 2021: International Conference on Intelligent Robotics and Applications
Subtitle of host publication14th International Conference, ICIRA 2021, Yantai, China, October 22–25, 2021, Proceedings, Part II
EditorsXin-Jun Liu, Zhenguo Nie, Jingjun Yu, Fugui Xie, Rui Song
PublisherSpringer
Pages111-121
Number of pages11
ISBN (Electronic)9783030890988
ISBN (Print)9783030890971
DOIs
Publication statusPublished - 18 Oct 2021
EventICIRA 2021: 14th International Conference on Intelligent Robotics and Applications - Yantai, China
Duration: 22 Oct 202125 Oct 2021

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume13014
ISSN (Print)0302-9743
NameLecture Notes in Artificial Intelligence
PublisherSpringer
Volume13014
ISSN (Electronic)1611-3349

Conference

ConferenceICIRA 2021: 14th International Conference on Intelligent Robotics and Applications
Country/TerritoryChina
CityYantai
Period22/10/2125/10/21

Keywords

  • robot learning from demonstration
  • dynamic obstacle
  • probabilistic modelling

Fingerprint

Dive into the research topics of 'Real-time collision avoidance in a dynamic environment for an industrial robotic arm'. Together they form a unique fingerprint.

Cite this