MCENET
Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic
- verfasst von
- Hao Cheng, Wentong Liao, Michael Ying Yang, Monika Sester, Bodo Rosenhahn
- Abstract
Trajectory prediction in urban mixed-traffic zones (a.k. a. shared spaces) is critical for many intelligent transportation systems, such as intent detection for autonomous driving. However, there are many challenges to predict the trajectories of heterogeneous road agents (pedestrians, cyclists and vehicles) at a microscopical level. For example, an agent might be able to choose multiple plausible paths in complex interactions with other agents in varying environments. To this end, we propose an approach named Multi-Context Encoder Network (MCENET) that is trained by encoding both past and future scene context, interaction context and motion information to capture the patterns and variations of the future trajectories using a set of stochastic latent variables. In inference time, we combine the past context and motion information of the target agent with samplings of the latent variables to predict multiple realistic trajectories in the future. Through experiments on several datasets of varying scenes, our method outperforms some of the recent state-of-the-art methods for mixed traffic trajectory prediction by a large margin and more robust in a very challenging environment. The impact of each context is justified via ablation studies.
- Organisationseinheit(en)
-
Institut für Kartographie und Geoinformatik
Institut für Informationsverarbeitung
Leibniz Forschungszentrum FZ:GEO
- Externe Organisation(en)
-
University of Twente
- Typ
- Aufsatz in Konferenzband
- Anzahl der Seiten
- 9
- Publikationsdatum
- 2020
- Publikationsstatus
- Veröffentlicht
- Peer-reviewed
- Ja
- ASJC Scopus Sachgebiete
- Informationssysteme und -management, Artificial intelligence, Entscheidungswissenschaften (sonstige), Ausbildung bzw. Denomination, Modellierung und Simulation
- Ziele für nachhaltige Entwicklung
- SDG 11 – Nachhaltige Städte und Gemeinschaften
- Elektronische Version(en)
-
https://arxiv.org/abs/2002.05966 (Zugang:
Offen)
https://doi.org/10.1109/ITSC45102.2020.9294296 (Zugang: Geschlossen)