Pedestrians Walking on Reachable Sets and Manifolds

Michael Hartmann; Daniel Watzenig

doi:10.1109/ICMECH.2019.8722888

Pedestrians Walking on Reachable Sets and Manifolds

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Abstract

It is a challenge to find safe trajectories for automated vehicles. Especially in urban environments with pedestrians there exist many different situations. The prediction of future movements with absolute certainty is impossible if the intention of the pedestrian is unknown. This paper is intended to offer a new concept of decision-making for motion planning with vulnerable road-users in urban environments. Reachability analysis is used to define spatial areas based on physical constraints, where the pedestrian might go. The approach is physically inspired and it can be proven for all kind of pedestrians. A new approach to cluster spatial areas is introduced to store specific environmental information about the pedestrian. The maximum values for jerk, acceleration and velocity of the pedestrian are necessary to find reachable areas.

Originalsprache	englisch
Titel	Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019
Herausgeber (Verlag)	Institute of Electrical and Electronics Engineers
Seiten	562-569
Seitenumfang	8
ISBN (elektronisch)	9781538669594
DOIs	https://doi.org/10.1109/ICMECH.2019.8722888
Publikationsstatus	Veröffentlicht - 24 Mai 2019
Veranstaltung	IEEE 2019 International Conference on Mechatronics: ICM 2019 - TU Ilmenau, Ilmenau, Deutschland Dauer: 18 März 2019 → 20 März 2019 https://ieee-icm2019.org/

Publikationsreihe

Name	Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019

Konferenz

Konferenz	IEEE 2019 International Conference on Mechatronics
Kurztitel	ICM 2019
Land/Gebiet	Deutschland
Ort	Ilmenau
Zeitraum	18/03/19 → 20/03/19
Internetadresse	https://ieee-icm2019.org/

ASJC Scopus subject areas

Artificial intelligence
Human-computer interaction
Fahrzeugbau
Maschinenbau
Steuerung und Optimierung
Wirtschaftsingenieurwesen und Fertigungstechnik

Zugriff auf Dokument

10.1109/ICMECH.2019.8722888

Andere Dateien und Links

http://www.scopus.com/inward/record.url?scp=85067100606&partnerID=8YFLogxK

Dieses zitieren

Hartmann, M., & Watzenig, D. (2019). Pedestrians Walking on Reachable Sets and Manifolds. in Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019 (S. 562-569). Artikel 8722888 (Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICMECH.2019.8722888

Pedestrians Walking on Reachable Sets and Manifolds. / Hartmann, Michael; Watzenig, Daniel.
Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019. Institute of Electrical and Electronics Engineers, 2019. S. 562-569 8722888 (Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019).

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Hartmann, M & Watzenig, D 2019, Pedestrians Walking on Reachable Sets and Manifolds. in Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019., 8722888, Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019, Institute of Electrical and Electronics Engineers, S. 562-569, IEEE 2019 International Conference on Mechatronics, Ilmenau, Thüringen, Deutschland, 18/03/19. https://doi.org/10.1109/ICMECH.2019.8722888

@inproceedings{cc4d18dca54e43fba4dc401228e06542,

title = "Pedestrians Walking on Reachable Sets and Manifolds",

abstract = "It is a challenge to find safe trajectories for automated vehicles. Especially in urban environments with pedestrians there exist many different situations. The prediction of future movements with absolute certainty is impossible if the intention of the pedestrian is unknown. This paper is intended to offer a new concept of decision-making for motion planning with vulnerable road-users in urban environments. Reachability analysis is used to define spatial areas based on physical constraints, where the pedestrian might go. The approach is physically inspired and it can be proven for all kind of pedestrians. A new approach to cluster spatial areas is introduced to store specific environmental information about the pedestrian. The maximum values for jerk, acceleration and velocity of the pedestrian are necessary to find reachable areas.",

keywords = "Automated Vehicles, Machine Learning, Motion Planning, Pedestrian, Reachability Analysis, Safety, Vehicles",

author = "Michael Hartmann and Daniel Watzenig",

year = "2019",

month = may,

day = "24",

doi = "10.1109/ICMECH.2019.8722888",

language = "English",

series = "Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "562--569",

booktitle = "Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019",

address = "United States",

note = "2019 IEEE International Conference on Mechatronics : ICM 2019, ICM 2019 ; Conference date: 18-03-2019 Through 20-03-2019",

url = "https://ieee-icm2019.org/",

}

TY - GEN

T1 - Pedestrians Walking on Reachable Sets and Manifolds

AU - Hartmann, Michael

AU - Watzenig, Daniel

PY - 2019/5/24

Y1 - 2019/5/24

N2 - It is a challenge to find safe trajectories for automated vehicles. Especially in urban environments with pedestrians there exist many different situations. The prediction of future movements with absolute certainty is impossible if the intention of the pedestrian is unknown. This paper is intended to offer a new concept of decision-making for motion planning with vulnerable road-users in urban environments. Reachability analysis is used to define spatial areas based on physical constraints, where the pedestrian might go. The approach is physically inspired and it can be proven for all kind of pedestrians. A new approach to cluster spatial areas is introduced to store specific environmental information about the pedestrian. The maximum values for jerk, acceleration and velocity of the pedestrian are necessary to find reachable areas.

AB - It is a challenge to find safe trajectories for automated vehicles. Especially in urban environments with pedestrians there exist many different situations. The prediction of future movements with absolute certainty is impossible if the intention of the pedestrian is unknown. This paper is intended to offer a new concept of decision-making for motion planning with vulnerable road-users in urban environments. Reachability analysis is used to define spatial areas based on physical constraints, where the pedestrian might go. The approach is physically inspired and it can be proven for all kind of pedestrians. A new approach to cluster spatial areas is introduced to store specific environmental information about the pedestrian. The maximum values for jerk, acceleration and velocity of the pedestrian are necessary to find reachable areas.

KW - Automated Vehicles

KW - Machine Learning

KW - Motion Planning

KW - Pedestrian

KW - Reachability Analysis

KW - Safety

KW - Vehicles

UR - http://www.scopus.com/inward/record.url?scp=85067100606&partnerID=8YFLogxK

U2 - 10.1109/ICMECH.2019.8722888

DO - 10.1109/ICMECH.2019.8722888

M3 - Conference paper

AN - SCOPUS:85067100606

T3 - Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019

SP - 562

EP - 569

BT - Proceedings - 2019 IEEE International Conference on Mechatronics, ICM 2019

PB - Institute of Electrical and Electronics Engineers

T2 - 2019 IEEE International Conference on Mechatronics

Y2 - 18 March 2019 through 20 March 2019

ER -

Pedestrians Walking on Reachable Sets and Manifolds

Abstract

Publikationsreihe

Konferenz

ASJC Scopus subject areas

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Dieses zitieren