Generation of Human-Like Movements Based on Environmental Features

A. Zonta; S. K. Smit; M. Hoogendoorn; A. E. Eiben

doi:10.1109/SSCI44817.2019.9002822

Generation of Human-Like Movements Based on Environmental Features

A. Zonta, S. K. Smit, M. Hoogendoorn, A. E. Eiben

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

Abstract

Modelling human behaviour in simulation is still an ongoing challenge that spaces between several fields like social science, artificial intelligence, and philosophy. Humans normally move driven by their intent (e.g. to get groceries) and the surrounding environment (e.g. curiosity to see new interesting places). Normal services available online and offline do not consider the environment when planning the path. Especially on a leisure trip, this is very important. This paper presents a comparison between different machine learning algorithms and a famous path planning algorithm in the task of generating human-like trajectories based on environmental features. We show how a modified version of the well known A∗ algorithm outperforms different machine learning algorithms by computed evaluation metrics and human evaluation in the task of generating bike trips in the area around Ljubljana, Slovenia.

Original language	English
Title of host publication	Proceedings - 2019 IEEE Symposium Series on Computational Intelligence (SSCI)
Subtitle of host publication	6-9 Dec. 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3079-3086
Number of pages	8
ISBN (Electronic)	9781728124858
DOIs	https://doi.org/10.1109/SSCI44817.2019.9002822
Publication status	Published - 20 Feb 2020
Event	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 - Xiamen, China Duration: 6 Dec 2019 → 9 Dec 2019

Publication series

Name	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

Conference

Conference	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019
Country/Territory	China
City	Xiamen
Period	6/12/19 → 9/12/19

Funding

ACKNOWLEDGEMENT The research for this paper was financially supported by the Netherlands Organisation for Applied Scientific Research (TNO).

Keywords

Trajectory Generation
Human-likeness
Human Trajectories
Neural Networks
Human Evaluation

Access to Document

10.1109/SSCI44817.2019.9002822

Persistent URL (handle)

Persistent link

Cite this

Zonta, A., Smit, S. K., Hoogendoorn, M., & Eiben, A. E. (2020). Generation of Human-Like Movements Based on Environmental Features. In Proceedings - 2019 IEEE Symposium Series on Computational Intelligence (SSCI): 6-9 Dec. 2019 (pp. 3079-3086). Article 9002822 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI44817.2019.9002822

@inproceedings{232b310582214ebf9522b683dc687d5b,

title = "Generation of Human-Like Movements Based on Environmental Features",

abstract = "Modelling human behaviour in simulation is still an ongoing challenge that spaces between several fields like social science, artificial intelligence, and philosophy. Humans normally move driven by their intent (e.g. to get groceries) and the surrounding environment (e.g. curiosity to see new interesting places). Normal services available online and offline do not consider the environment when planning the path. Especially on a leisure trip, this is very important. This paper presents a comparison between different machine learning algorithms and a famous path planning algorithm in the task of generating human-like trajectories based on environmental features. We show how a modified version of the well known A∗ algorithm outperforms different machine learning algorithms by computed evaluation metrics and human evaluation in the task of generating bike trips in the area around Ljubljana, Slovenia.",

keywords = "Trajectory Generation, Human-likeness, Human Trajectories, Neural Networks, Human Evaluation",

author = "A. Zonta and Smit, {S. K.} and M. Hoogendoorn and Eiben, {A. E.}",

year = "2020",

month = feb,

day = "20",

doi = "10.1109/SSCI44817.2019.9002822",

language = "English",

series = "2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019",

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

pages = "3079--3086",

booktitle = "Proceedings - 2019 IEEE Symposium Series on Computational Intelligence (SSCI)",

address = "United States",

note = "2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 ; Conference date: 06-12-2019 Through 09-12-2019",

}

Zonta, A, Smit, SK, Hoogendoorn, M & Eiben, AE 2020, Generation of Human-Like Movements Based on Environmental Features. in Proceedings - 2019 IEEE Symposium Series on Computational Intelligence (SSCI): 6-9 Dec. 2019., 9002822, 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019, Institute of Electrical and Electronics Engineers Inc., pp. 3079-3086, 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019, Xiamen, China, 6/12/19. https://doi.org/10.1109/SSCI44817.2019.9002822

Generation of Human-Like Movements Based on Environmental Features. / Zonta, A.; Smit, S. K.; Hoogendoorn, M. et al.
Proceedings - 2019 IEEE Symposium Series on Computational Intelligence (SSCI): 6-9 Dec. 2019. Institute of Electrical and Electronics Engineers Inc., 2020. p. 3079-3086 9002822 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019).

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

TY - GEN

T1 - Generation of Human-Like Movements Based on Environmental Features

AU - Zonta, A.

AU - Smit, S. K.

AU - Hoogendoorn, M.

AU - Eiben, A. E.

PY - 2020/2/20

Y1 - 2020/2/20

N2 - Modelling human behaviour in simulation is still an ongoing challenge that spaces between several fields like social science, artificial intelligence, and philosophy. Humans normally move driven by their intent (e.g. to get groceries) and the surrounding environment (e.g. curiosity to see new interesting places). Normal services available online and offline do not consider the environment when planning the path. Especially on a leisure trip, this is very important. This paper presents a comparison between different machine learning algorithms and a famous path planning algorithm in the task of generating human-like trajectories based on environmental features. We show how a modified version of the well known A∗ algorithm outperforms different machine learning algorithms by computed evaluation metrics and human evaluation in the task of generating bike trips in the area around Ljubljana, Slovenia.

AB - Modelling human behaviour in simulation is still an ongoing challenge that spaces between several fields like social science, artificial intelligence, and philosophy. Humans normally move driven by their intent (e.g. to get groceries) and the surrounding environment (e.g. curiosity to see new interesting places). Normal services available online and offline do not consider the environment when planning the path. Especially on a leisure trip, this is very important. This paper presents a comparison between different machine learning algorithms and a famous path planning algorithm in the task of generating human-like trajectories based on environmental features. We show how a modified version of the well known A∗ algorithm outperforms different machine learning algorithms by computed evaluation metrics and human evaluation in the task of generating bike trips in the area around Ljubljana, Slovenia.

KW - Trajectory Generation

KW - Human-likeness

KW - Human Trajectories

KW - Neural Networks

KW - Human Evaluation

UR - http://www.scopus.com/inward/record.url?scp=85080970103&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85080970103&partnerID=8YFLogxK

U2 - 10.1109/SSCI44817.2019.9002822

DO - 10.1109/SSCI44817.2019.9002822

M3 - Conference contribution

T3 - 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

SP - 3079

EP - 3086

BT - Proceedings - 2019 IEEE Symposium Series on Computational Intelligence (SSCI)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

Y2 - 6 December 2019 through 9 December 2019

ER -

Zonta A, Smit SK, Hoogendoorn M , Eiben AE. Generation of Human-Like Movements Based on Environmental Features. In Proceedings - 2019 IEEE Symposium Series on Computational Intelligence (SSCI): 6-9 Dec. 2019. Institute of Electrical and Electronics Engineers Inc. 2020. p. 3079-3086. 9002822. (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019). Epub 2019 Dec 6. doi: 10.1109/SSCI44817.2019.9002822

Generation of Human-Like Movements Based on Environmental Features

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this