Suicidal Pedestrian : Generation of Safety-Critical Scenarios for Autonomous Vehicles

Yuhang Yang*, Kalle Kujanpää, Amin Babadi, Joni Pajarinen, Alexander Ilin

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

Abstrakti

Developing reliable autonomous driving algorithms poses challenges in testing, particularly when it comes to safety-critical traffic scenarios involving pedestrians. An open question is how to simulate rare events, not necessarily found in autonomous driving datasets or scripted simulations, but which can occur in testing, and, in the end may lead to severe pedestrian related accidents. This paper presents a method for designing a suicidal pedestrian agent within the CARLA simulator, enabling the automatic generation of traffic scenarios for testing safety of autonomous vehicles (AVs) in dangerous situations with pedestrians. The pedestrian is modeled as a reinforcement learning (RL) agent with two custom reward functions that allow the agent to either arbitrarily or with high velocity to collide with the AV. Instead of significantly constraining the initial locations and the pedestrian behavior, we allow the pedestrian and autonomous car to be placed anywhere in the environment and the pedestrian to roam freely to generate diverse scenarios. To assess the performance of the suicidal pedestrian and the target vehicle during testing, we propose three collision-oriented evaluation metrics. Experimental results involving two state-of-the-art autonomous driving algorithms trained end-to-end with imitation learning from sensor data demonstrate the effectiveness of the suicidal pedestrian in identifying decision errors made by autonomous vehicles controlled by the algorithms.

AlkuperäiskieliEnglanti
Otsikko2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023
KustantajaIEEE
Sivut1983-1988
Sivumäärä6
ISBN (elektroninen)979-8-3503-9946-2
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE International Conference on Intelligent Transportation Systems - Bilbao, Espanja
Kesto: 24 syysk. 202328 syysk. 2023
Konferenssinumero: 26

Julkaisusarja

NimiIEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
KustantajaIEEE
ISSN (painettu)2153-0009
ISSN (elektroninen)2153-0017

Conference

ConferenceIEEE International Conference on Intelligent Transportation Systems
LyhennettäITSC
Maa/AlueEspanja
KaupunkiBilbao
Ajanjakso24/09/202328/09/2023

Sormenjälki

Sukella tutkimusaiheisiin 'Suicidal Pedestrian : Generation of Safety-Critical Scenarios for Autonomous Vehicles'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä