A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning

Xiaofei Gong; Chenyang Cao; Xujun Xu; Wenzheng Chi; Lining Sun

doi:10.1109/ROBIO58561.2023.10354559

A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning

Xiaofei Gong
, Chenyang Cao
, Xujun Xu
, Wenzheng Chi^*
, Lining Sun

^*Corresponding author for this work

Soochow University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Recently, many researchers propose different methods to solve the motion planning problem in the human-robot co-existing environments. However, when encountering crowds that suddenly appear, conventional motion planning algorithms often generate similar homotopy paths with slight local variations, which may not generate new feasible paths in time and thus lead to congestion for the robot. In order to address this problem, this paper proposes a knowledge-based full-time non-homotopy path optimization method through online environmental learning, which generates heuristic paths to guide motion planning by combing the pedestrian knowledge and the environmental structure. Firstly, a pedestrian matrix based knowledge base is proposed to record the pedestrian flow pattern with respect to different locations, and the corresponding pedestrian matrix is extracted according to the perception during the robot navigation process. Secondly, the environmental perception is performed surrounding the key obstacles that appears around the crowds to extract the feature points. Then, the extracted feature points are reused as prior knowledge in subsequent navigation. When crowds suddenly appear in the global path, the algorithm will prioritize searching a non-homotopy path to avoid crowds. The experimental results show that the method proposed in this paper can significantly reduce the time required for the robot to navigate and improve the success rate of navigation in crowded environments.

Original language	English
Title of host publication	2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023
Editors	Mehmet Dogar, Bin Fang, Dimitrios Kanoulas, Jia Pan, Alessandra Sciutti, Moju Zhao, Guanjun Bao, Bimbo Joao, Boyle Jordan Hylke, He Chen, Chen Teng, Yunduan Cui, Dagnino Giulio, Wenbo Ding, Liang Du, Farinha Andre, Yuan Gao, Hasegawa Shun, Liang He, Taogang Hou, Zhe Hu, Zhong Huang, Jackson-Mills George, Yunfeng Ji, Jirak Doreen, Feng Ju, Kaddouh Bilal, Kim Wansoo, Takuya Kiyokawa, Haiyuan Li, Peng Li, Shihao Li, Xu Li, Jianfeng Liao, Ling Jie, Chunfang Liu, Quanquan Liu, Liang Lu, Qiuyue Luo, Yudong Luo, Zebing Mao, Martinez-Hernandez Uriel, Matsuno Takahiro, Nguyen Thanh Luan, Nishio Takuzumi, Pasquali Dario, Pierella Camilla, Chao Ren, Ricci Serena, Rossini Luca, Shi Fan, Summa Susanna, Rongchuan Sun, Zhenglong Sun, Vannucci Fabio, Gang Wang, Wei Wang, Xin Wang, Yuquan Wang, Ziya Wang, Qingxiang Wu, Xiaojun Wu, Yuxin Sun, Youcan Yan, Lei Yang, Yanokura Iori, Jingfan Zhang, Shuai Zhang, Tianwei Zhang, Jinglei Zhao, Na Zhao, Chengxu Zhou, Peng Zhou, Haifei Zhu
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350325706
DOIs	https://doi.org/10.1109/ROBIO58561.2023.10354559
State	Published - 2023
Externally published	Yes
Event	2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023 - Koh�Samui, Thailand Duration: 4 Dec 2023 → 9 Dec 2023

Publication series

Name	2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

Conference

Conference	2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023
Country/Territory	Thailand
City	Koh�Samui
Period	4/12/23 → 9/12/23

Keywords

Heuristic Path
Knowledge Base
Non-Homotopy Path
Obstacle Perception

Access to Document

10.1109/ROBIO58561.2023.10354559

Cite this

Gong, X., Cao, C., Xu, X., Chi, W., & Sun, L. (2023). A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning. In M. Dogar, B. Fang, D. Kanoulas, J. Pan, A. Sciutti, M. Zhao, G. Bao, B. Joao, B. J. Hylke, H. Chen, C. Teng, Y. Cui, D. Giulio, W. Ding, L. Du, F. Andre, Y. Gao, H. Shun, L. He, T. Hou, Z. Hu, Z. Huang, J.-M. George, Y. Ji, J. Doreen, F. Ju, K. Bilal, K. Wansoo, T. Kiyokawa, H. Li, P. Li, S. Li, X. Li, J. Liao, L. Jie, C. Liu, Q. Liu, L. Lu, Q. Luo, Y. Luo, Z. Mao, M.-H. Uriel, M. Takahiro, N. T. Luan, N. Takuzumi, P. Dario, P. Camilla, C. Ren, R. Serena, R. Luca, S. Fan, S. Susanna, R. Sun, Z. Sun, V. Fabio, G. Wang, W. Wang, X. Wang, Y. Wang, Z. Wang, Q. Wu, X. Wu, Y. Sun, Y. Yan, L. Yang, Y. Iori, J. Zhang, S. Zhang, T. Zhang, J. Zhao, N. Zhao, C. Zhou, P. Zhou, ... H. Zhu (Eds.), 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023 (2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROBIO58561.2023.10354559

Gong, Xiaofei ; Cao, Chenyang ; Xu, Xujun et al. / A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning. 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023. editor / Mehmet Dogar ; Bin Fang ; Dimitrios Kanoulas ; Jia Pan ; Alessandra Sciutti ; Moju Zhao ; Guanjun Bao ; Bimbo Joao ; Boyle Jordan Hylke ; He Chen ; Chen Teng ; Yunduan Cui ; Dagnino Giulio ; Wenbo Ding ; Liang Du ; Farinha Andre ; Yuan Gao ; Hasegawa Shun ; Liang He ; Taogang Hou ; Zhe Hu ; Zhong Huang ; Jackson-Mills George ; Yunfeng Ji ; Jirak Doreen ; Feng Ju ; Kaddouh Bilal ; Kim Wansoo ; Takuya Kiyokawa ; Haiyuan Li ; Peng Li ; Shihao Li ; Xu Li ; Jianfeng Liao ; Ling Jie ; Chunfang Liu ; Quanquan Liu ; Liang Lu ; Qiuyue Luo ; Yudong Luo ; Zebing Mao ; Martinez-Hernandez Uriel ; Matsuno Takahiro ; Nguyen Thanh Luan ; Nishio Takuzumi ; Pasquali Dario ; Pierella Camilla ; Chao Ren ; Ricci Serena ; Rossini Luca ; Shi Fan ; Summa Susanna ; Rongchuan Sun ; Zhenglong Sun ; Vannucci Fabio ; Gang Wang ; Wei Wang ; Xin Wang ; Yuquan Wang ; Ziya Wang ; Qingxiang Wu ; Xiaojun Wu ; Yuxin Sun ; Youcan Yan ; Lei Yang ; Yanokura Iori ; Jingfan Zhang ; Shuai Zhang ; Tianwei Zhang ; Jinglei Zhao ; Na Zhao ; Chengxu Zhou ; Peng Zhou ; Haifei Zhu. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023).

@inproceedings{925632942369482ea3bd9cc729450a91,

title = "A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning",

abstract = "Recently, many researchers propose different methods to solve the motion planning problem in the human-robot co-existing environments. However, when encountering crowds that suddenly appear, conventional motion planning algorithms often generate similar homotopy paths with slight local variations, which may not generate new feasible paths in time and thus lead to congestion for the robot. In order to address this problem, this paper proposes a knowledge-based full-time non-homotopy path optimization method through online environmental learning, which generates heuristic paths to guide motion planning by combing the pedestrian knowledge and the environmental structure. Firstly, a pedestrian matrix based knowledge base is proposed to record the pedestrian flow pattern with respect to different locations, and the corresponding pedestrian matrix is extracted according to the perception during the robot navigation process. Secondly, the environmental perception is performed surrounding the key obstacles that appears around the crowds to extract the feature points. Then, the extracted feature points are reused as prior knowledge in subsequent navigation. When crowds suddenly appear in the global path, the algorithm will prioritize searching a non-homotopy path to avoid crowds. The experimental results show that the method proposed in this paper can significantly reduce the time required for the robot to navigate and improve the success rate of navigation in crowded environments.",

keywords = "Heuristic Path, Knowledge Base, Non-Homotopy Path, Obstacle Perception",

author = "Xiaofei Gong and Chenyang Cao and Xujun Xu and Wenzheng Chi and Lining Sun",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023 ; Conference date: 04-12-2023 Through 09-12-2023",

year = "2023",

doi = "10.1109/ROBIO58561.2023.10354559",

language = "英语",

series = "2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Mehmet Dogar and Bin Fang and Dimitrios Kanoulas and Jia Pan and Alessandra Sciutti and Moju Zhao and Guanjun Bao and Bimbo Joao and Hylke, \{Boyle Jordan\} and He Chen and Chen Teng and Yunduan Cui and Dagnino Giulio and Wenbo Ding and Liang Du and Farinha Andre and Yuan Gao and Hasegawa Shun and Liang He and Taogang Hou and Zhe Hu and Zhong Huang and Jackson-Mills George and Yunfeng Ji and Jirak Doreen and Feng Ju and Kaddouh Bilal and Kim Wansoo and Takuya Kiyokawa and Haiyuan Li and Peng Li and Shihao Li and Xu Li and Jianfeng Liao and Ling Jie and Chunfang Liu and Quanquan Liu and Liang Lu and Qiuyue Luo and Yudong Luo and Zebing Mao and Martinez-Hernandez Uriel and Matsuno Takahiro and Luan, \{Nguyen Thanh\} and Nishio Takuzumi and Pasquali Dario and Pierella Camilla and Chao Ren and Ricci Serena and Rossini Luca and Shi Fan and Summa Susanna and Rongchuan Sun and Zhenglong Sun and Vannucci Fabio and Gang Wang and Wei Wang and Xin Wang and Yuquan Wang and Ziya Wang and Qingxiang Wu and Xiaojun Wu and Yuxin Sun and Youcan Yan and Lei Yang and Yanokura Iori and Jingfan Zhang and Shuai Zhang and Tianwei Zhang and Jinglei Zhao and Na Zhao and Chengxu Zhou and Peng Zhou and Haifei Zhu",

booktitle = "2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023",

address = "美国",

}

Gong, X, Cao, C, Xu, X, Chi, W & Sun, L 2023, A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning. in M Dogar, B Fang, D Kanoulas, J Pan, A Sciutti, M Zhao, G Bao, B Joao, BJ Hylke, H Chen, C Teng, Y Cui, D Giulio, W Ding, L Du, F Andre, Y Gao, H Shun, L He, T Hou, Z Hu, Z Huang, J-M George, Y Ji, J Doreen, F Ju, K Bilal, K Wansoo, T Kiyokawa, H Li, P Li, S Li, X Li, J Liao, L Jie, C Liu, Q Liu, L Lu, Q Luo, Y Luo, Z Mao, M-H Uriel, M Takahiro, NT Luan, N Takuzumi, P Dario, P Camilla, C Ren, R Serena, R Luca, S Fan, S Susanna, R Sun, Z Sun, V Fabio, G Wang, W Wang, X Wang, Y Wang, Z Wang, Q Wu, X Wu, Y Sun, Y Yan, L Yang, Y Iori, J Zhang, S Zhang, T Zhang, J Zhao, N Zhao, C Zhou, P Zhou & H Zhu (eds), 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023. 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023, Koh�Samui, Thailand, 4/12/23. https://doi.org/10.1109/ROBIO58561.2023.10354559

A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning. / Gong, Xiaofei; Cao, Chenyang; Xu, Xujun et al.
2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023. ed. / Mehmet Dogar; Bin Fang; Dimitrios Kanoulas; Jia Pan; Alessandra Sciutti; Moju Zhao; Guanjun Bao; Bimbo Joao; Boyle Jordan Hylke; He Chen; Chen Teng; Yunduan Cui; Dagnino Giulio; Wenbo Ding; Liang Du; Farinha Andre; Yuan Gao; Hasegawa Shun; Liang He; Taogang Hou; Zhe Hu; Zhong Huang; Jackson-Mills George; Yunfeng Ji; Jirak Doreen; Feng Ju; Kaddouh Bilal; Kim Wansoo; Takuya Kiyokawa; Haiyuan Li; Peng Li; Shihao Li; Xu Li; Jianfeng Liao; Ling Jie; Chunfang Liu; Quanquan Liu; Liang Lu; Qiuyue Luo; Yudong Luo; Zebing Mao; Martinez-Hernandez Uriel; Matsuno Takahiro; Nguyen Thanh Luan; Nishio Takuzumi; Pasquali Dario; Pierella Camilla; Chao Ren; Ricci Serena; Rossini Luca; Shi Fan; Summa Susanna; Rongchuan Sun; Zhenglong Sun; Vannucci Fabio; Gang Wang; Wei Wang; Xin Wang; Yuquan Wang; Ziya Wang; Qingxiang Wu; Xiaojun Wu; Yuxin Sun; Youcan Yan; Lei Yang; Yanokura Iori; Jingfan Zhang; Shuai Zhang; Tianwei Zhang; Jinglei Zhao; Na Zhao; Chengxu Zhou; Peng Zhou; Haifei Zhu. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning

AU - Gong, Xiaofei

AU - Cao, Chenyang

AU - Xu, Xujun

AU - Chi, Wenzheng

AU - Sun, Lining

PY - 2023

Y1 - 2023

N2 - Recently, many researchers propose different methods to solve the motion planning problem in the human-robot co-existing environments. However, when encountering crowds that suddenly appear, conventional motion planning algorithms often generate similar homotopy paths with slight local variations, which may not generate new feasible paths in time and thus lead to congestion for the robot. In order to address this problem, this paper proposes a knowledge-based full-time non-homotopy path optimization method through online environmental learning, which generates heuristic paths to guide motion planning by combing the pedestrian knowledge and the environmental structure. Firstly, a pedestrian matrix based knowledge base is proposed to record the pedestrian flow pattern with respect to different locations, and the corresponding pedestrian matrix is extracted according to the perception during the robot navigation process. Secondly, the environmental perception is performed surrounding the key obstacles that appears around the crowds to extract the feature points. Then, the extracted feature points are reused as prior knowledge in subsequent navigation. When crowds suddenly appear in the global path, the algorithm will prioritize searching a non-homotopy path to avoid crowds. The experimental results show that the method proposed in this paper can significantly reduce the time required for the robot to navigate and improve the success rate of navigation in crowded environments.

AB - Recently, many researchers propose different methods to solve the motion planning problem in the human-robot co-existing environments. However, when encountering crowds that suddenly appear, conventional motion planning algorithms often generate similar homotopy paths with slight local variations, which may not generate new feasible paths in time and thus lead to congestion for the robot. In order to address this problem, this paper proposes a knowledge-based full-time non-homotopy path optimization method through online environmental learning, which generates heuristic paths to guide motion planning by combing the pedestrian knowledge and the environmental structure. Firstly, a pedestrian matrix based knowledge base is proposed to record the pedestrian flow pattern with respect to different locations, and the corresponding pedestrian matrix is extracted according to the perception during the robot navigation process. Secondly, the environmental perception is performed surrounding the key obstacles that appears around the crowds to extract the feature points. Then, the extracted feature points are reused as prior knowledge in subsequent navigation. When crowds suddenly appear in the global path, the algorithm will prioritize searching a non-homotopy path to avoid crowds. The experimental results show that the method proposed in this paper can significantly reduce the time required for the robot to navigate and improve the success rate of navigation in crowded environments.

KW - Heuristic Path

KW - Knowledge Base

KW - Non-Homotopy Path

KW - Obstacle Perception

UR - https://www.scopus.com/pages/publications/85182548276

U2 - 10.1109/ROBIO58561.2023.10354559

DO - 10.1109/ROBIO58561.2023.10354559

M3 - 会议稿件

AN - SCOPUS:85182548276

T3 - 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

BT - 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

A2 - Dogar, Mehmet

A2 - Fang, Bin

A2 - Kanoulas, Dimitrios

A2 - Pan, Jia

A2 - Sciutti, Alessandra

A2 - Zhao, Moju

A2 - Bao, Guanjun

A2 - Joao, Bimbo

A2 - Hylke, Boyle Jordan

A2 - Chen, He

A2 - Teng, Chen

A2 - Cui, Yunduan

A2 - Giulio, Dagnino

A2 - Ding, Wenbo

A2 - Du, Liang

A2 - Andre, Farinha

A2 - Gao, Yuan

A2 - Shun, Hasegawa

A2 - He, Liang

A2 - Hou, Taogang

A2 - Hu, Zhe

A2 - Huang, Zhong

A2 - George, Jackson-Mills

A2 - Ji, Yunfeng

A2 - Doreen, Jirak

A2 - Ju, Feng

A2 - Bilal, Kaddouh

A2 - Wansoo, Kim

A2 - Kiyokawa, Takuya

A2 - Li, Haiyuan

A2 - Li, Peng

A2 - Li, Shihao

A2 - Li, Xu

A2 - Liao, Jianfeng

A2 - Jie, Ling

A2 - Liu, Chunfang

A2 - Liu, Quanquan

A2 - Lu, Liang

A2 - Luo, Qiuyue

A2 - Luo, Yudong

A2 - Mao, Zebing

A2 - Uriel, Martinez-Hernandez

A2 - Takahiro, Matsuno

A2 - Luan, Nguyen Thanh

A2 - Takuzumi, Nishio

A2 - Dario, Pasquali

A2 - Camilla, Pierella

A2 - Ren, Chao

A2 - Serena, Ricci

A2 - Luca, Rossini

A2 - Fan, Shi

A2 - Susanna, Summa

A2 - Sun, Rongchuan

A2 - Sun, Zhenglong

A2 - Fabio, Vannucci

A2 - Wang, Gang

A2 - Wang, Wei

A2 - Wang, Xin

A2 - Wang, Yuquan

A2 - Wang, Ziya

A2 - Wu, Qingxiang

A2 - Wu, Xiaojun

A2 - Sun, Yuxin

A2 - Yan, Youcan

A2 - Yang, Lei

A2 - Iori, Yanokura

A2 - Zhang, Jingfan

A2 - Zhang, Shuai

A2 - Zhang, Tianwei

A2 - Zhao, Jinglei

A2 - Zhao, Na

A2 - Zhou, Chengxu

A2 - Zhou, Peng

A2 - Zhu, Haifei

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

Y2 - 4 December 2023 through 9 December 2023

ER -

Gong X, Cao C, Xu X, Chi W, Sun L. A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning. In Dogar M, Fang B, Kanoulas D, Pan J, Sciutti A, Zhao M, Bao G, Joao B, Hylke BJ, Chen H, Teng C, Cui Y, Giulio D, Ding W, Du L, Andre F, Gao Y, Shun H, He L, Hou T, Hu Z, Huang Z, George JM, Ji Y, Doreen J, Ju F, Bilal K, Wansoo K, Kiyokawa T, Li H, Li P, Li S, Li X, Liao J, Jie L, Liu C, Liu Q, Lu L, Luo Q, Luo Y, Mao Z, Uriel MH, Takahiro M, Luan NT, Takuzumi N, Dario P, Camilla P, Ren C, Serena R, Luca R, Fan S, Susanna S, Sun R, Sun Z, Fabio V, Wang G, Wang W, Wang X, Wang Y, Wang Z, Wu Q, Wu X, Sun Y, Yan Y, Yang L, Iori Y, Zhang J, Zhang S, Zhang T, Zhao J, Zhao N, Zhou C, Zhou P, Zhu H, editors, 2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023). doi: 10.1109/ROBIO58561.2023.10354559

A Knowledge-based Full-time Non-homotopy Path Optimization Method Through Online Environmental Learning

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this