Competition Results and Ceremony
-
Track 1: Pedestrian Intent Prediction
- First Prize: Queen Mary University of London [Leader: Chiang, Chiayen]
- Second Prize: The Hong Kong Polytechnic University [Leader: Hu, Fengqing]
- Third Prize: Nan Jing University [Leader: Jin, Zhiyu]
- First Prize: Kookmin University [Leader: Lee, Seungju]
- Second Prize: Southeast University [Leader: Ji, Yufei]
- Third Prize:Chongqing University of Technology [Leader: Du, Xin]
- First Prize: University of Alcalá [Leader: Manzour Hussien, Mohamed]
- University of Alcalá [Leader: MELO CASTILLO, Angie Nataly]
- Peking University [Leader: Zhang, Jinyan]
- Tianjin Normal University [Leader: Zhou, Jianglin]
The detailed prize information will be announced in ITSC 2023 workshop - 3rd Workshop On The Prediction Of Pedestrian Behaviors For Automated Driving.
Introduction
Pedestrian behavior prediction is one of the most critical challenges for fully automated driving in urban settings, as it requires autonomous vehicles to interact safely and efficiently with pedestrians in diverse and dynamic environments. Accurate and robust pedestrian behavior prediction is crucial to ensure the safety of both pedestrians and the autonomous vehicles.Competition Tasks
- Pedestrian Intent Prediction (PIP): to predict the intention of a pedestrian crossing a street, such as whether they intend to cross or stop.
- Pedestrian Trajectory Prediction (PTP): to predict the future trajectory of the pedestrian, given the pedestrian’s current position and intention.
- Driver Decision Prediction (DDP): to predict the decision of the autonomous vehicle, given the pedestrian's intent and trajectory, to ensure safe and efficient interactions.
Timeline:
[Preparing Date]: until 23:59 GMT, August 30, 2023[Final Competition Date]: 00:00 - 23:59 UTC, August 30, 2023
[Workshop Time] September 24 - 28, 2023, Bilbao, Spain [Link]
Qualification:
We welcome competitors from all round the world. The leading attendee must be a student, graduate student or undergraduate student. Each team can join more than one track. Please check more details in the below website.Registration:
Please first register through Google Form using your university email [Click Here!], then participate the competition on CodaLab: [Track 1] [Track 2] [Track 3]For more information, please visit the competition webpage: [Click Here!]
All PSI data and annotations are public for further exploration! [Dataset Homepage]
Question and Answering:
Please contact this email for any questions: psi.intent.benchmark@gmail.comRequirement:
The winners are required to attend our ITSC Workshop remotely or in person.
Sponsor:
