Learning-enabled multi-modal motion prediction in urban environments

Vinicius Trentin; Chenxu Ma; Jorge Villagra; Zaid Al-Ars

doi:10.1109/IV55152.2023.10186684

Learning-enabled multi-modal motion prediction in urban environments

Vinicius Trentin, Chenxu Ma, Jorge Villagra, Zaid Al-Ars

Computer Engineering

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

3 Downloads (Pure)

Abstract

Motion prediction is a key factor towards the full deployment of autonomous vehicles. It is fundamental in order to assure safety while navigating through highly interactive complex scenarios. In this work, the framework IAMP (Interaction-Aware Motion Prediction), producing multi-modal probabilistic outputs from the integration of a Dynamic Bayesian Network and Markov Chains, is extended with a learning-based approach. The integration of a machine learning model tackles the limitations of the ruled-based mechanism since it can better adapt to different driving styles and driving situations. The method here introduced generates context-dependent acceleration distributions used in a Markov-chain-based motion prediction. This hybrid approach results in better evaluation metrics when compared with the baseline in the four highly-interactive scenarios obtained from publicly available datasets.

Original language	English
Title of host publication	IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)	9798350346916
DOIs	https://doi.org/10.1109/IV55152.2023.10186684
Publication status	Published - 2023
Event	34th IEEE Intelligent Vehicles Symposium, IV 2023 - Anchorage, United States Duration: 4 Jun 2023 → 7 Jun 2023

Publication series

Name	IEEE Intelligent Vehicles Symposium, Proceedings
Volume	2023-June

Conference

Conference	34th IEEE Intelligent Vehicles Symposium, IV 2023
Country/Territory	United States
City	Anchorage
Period	4/06/23 → 7/06/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

interaction-aware
learning-based
motion-prediction

Access to Document

10.1109/IV55152.2023.10186684

Learning-enabled_multi-modal_motion_prediction_in_urban_environmentsFinal published version, 1.72 MB

Cite this

@inproceedings{35626924a6884084883f1a48734b8bca,

title = "Learning-enabled multi-modal motion prediction in urban environments",

abstract = "Motion prediction is a key factor towards the full deployment of autonomous vehicles. It is fundamental in order to assure safety while navigating through highly interactive complex scenarios. In this work, the framework IAMP (Interaction-Aware Motion Prediction), producing multi-modal probabilistic outputs from the integration of a Dynamic Bayesian Network and Markov Chains, is extended with a learning-based approach. The integration of a machine learning model tackles the limitations of the ruled-based mechanism since it can better adapt to different driving styles and driving situations. The method here introduced generates context-dependent acceleration distributions used in a Markov-chain-based motion prediction. This hybrid approach results in better evaluation metrics when compared with the baseline in the four highly-interactive scenarios obtained from publicly available datasets.",

keywords = "interaction-aware, learning-based, motion-prediction",

author = "Vinicius Trentin and Chenxu Ma and Jorge Villagra and Zaid Al-Ars",

note = "Green Open Access added to TU Delft Institutional Repository {\textquoteleft}You share, we take care!{\textquoteright} – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. ; 34th IEEE Intelligent Vehicles Symposium, IV 2023 ; Conference date: 04-06-2023 Through 07-06-2023",

year = "2023",

doi = "10.1109/IV55152.2023.10186684",

language = "English",

series = "IEEE Intelligent Vehicles Symposium, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

booktitle = "IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings",

address = "United States",

}

Trentin, V, Ma, C, Villagra, J & Al-Ars, Z 2023, Learning-enabled multi-modal motion prediction in urban environments. in IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings. IEEE Intelligent Vehicles Symposium, Proceedings, vol. 2023-June, Institute of Electrical and Electronics Engineers (IEEE), 34th IEEE Intelligent Vehicles Symposium, IV 2023, Anchorage, United States, 4/06/23. https://doi.org/10.1109/IV55152.2023.10186684

Learning-enabled multi-modal motion prediction in urban environments. / Trentin, Vinicius; Ma, Chenxu; Villagra, Jorge et al.
IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings. Institute of Electrical and Electronics Engineers (IEEE), 2023. (IEEE Intelligent Vehicles Symposium, Proceedings; Vol. 2023-June).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Learning-enabled multi-modal motion prediction in urban environments

AU - Trentin, Vinicius

AU - Ma, Chenxu

AU - Villagra, Jorge

AU - Al-Ars, Zaid

N1 - Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2023

Y1 - 2023

N2 - Motion prediction is a key factor towards the full deployment of autonomous vehicles. It is fundamental in order to assure safety while navigating through highly interactive complex scenarios. In this work, the framework IAMP (Interaction-Aware Motion Prediction), producing multi-modal probabilistic outputs from the integration of a Dynamic Bayesian Network and Markov Chains, is extended with a learning-based approach. The integration of a machine learning model tackles the limitations of the ruled-based mechanism since it can better adapt to different driving styles and driving situations. The method here introduced generates context-dependent acceleration distributions used in a Markov-chain-based motion prediction. This hybrid approach results in better evaluation metrics when compared with the baseline in the four highly-interactive scenarios obtained from publicly available datasets.

AB - Motion prediction is a key factor towards the full deployment of autonomous vehicles. It is fundamental in order to assure safety while navigating through highly interactive complex scenarios. In this work, the framework IAMP (Interaction-Aware Motion Prediction), producing multi-modal probabilistic outputs from the integration of a Dynamic Bayesian Network and Markov Chains, is extended with a learning-based approach. The integration of a machine learning model tackles the limitations of the ruled-based mechanism since it can better adapt to different driving styles and driving situations. The method here introduced generates context-dependent acceleration distributions used in a Markov-chain-based motion prediction. This hybrid approach results in better evaluation metrics when compared with the baseline in the four highly-interactive scenarios obtained from publicly available datasets.

KW - interaction-aware

KW - learning-based

KW - motion-prediction

UR - http://www.scopus.com/inward/record.url?scp=85167996893&partnerID=8YFLogxK

U2 - 10.1109/IV55152.2023.10186684

DO - 10.1109/IV55152.2023.10186684

M3 - Conference contribution

AN - SCOPUS:85167996893

T3 - IEEE Intelligent Vehicles Symposium, Proceedings

BT - IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 34th IEEE Intelligent Vehicles Symposium, IV 2023

Y2 - 4 June 2023 through 7 June 2023

ER -

Learning-enabled multi-modal motion prediction in urban environments

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this