GTP-Force: Game-Theoretic Trajectory Prediction through Distributed Reinforcement Learning

Emami, Negar; Di Maio, Antonio; Braun, Torsten (2023). GTP-Force: Game-Theoretic Trajectory Prediction through Distributed Reinforcement Learning. In: The 20th IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS 2023). IEEE Xplore: IEEE

[img] Text
GTP_Force_EmamiNegar_9pages.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB)
[img]
Preview
Text
GTP_Force_EmamiNegar_Camera_Ready.pdf - Submitted Version
Available under License Publisher holds Copyright.

Download (629kB) | Preview

This paper introduces Game-theoretic Trajectory Prediction through distributed reinForcement learning (GTPForce), a system that tackles the challenge of predicting joint pedestrian trajectories in multi-agent scenarios. GTP-Force utilizes decentralized reinforcement learning agents to personalize neural networks for each competing player based on their noncooperative preferences and social interactions with others. By identifying the Nash Equilibria, GTP-Force accurately predicts joint trajectories while minimizing overall system loss in noncooperative environments. The system outperforms existing stateof- the-art trajectory predictors, achieving an average displacement error of 0.19m on the ETH+UCY dataset and 80% accuracy on the Orange dataset, which is -0.03m and 5% better than the best-performing baseline, respectively. Additionally, GTP-Force considerably reduces the model size of social mobility predictors compared to approaches with classical game theory.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

08 Faculty of Science > Institute of Computer Science (INF) > Communication and Distributed Systems (CDS)
08 Faculty of Science > Institute of Computer Science (INF)

UniBE Contributor:

Emami, Negar, Di Maio, Antonio, Braun, Torsten

Subjects:

000 Computer science, knowledge & systems
500 Science > 510 Mathematics
500 Science

Publisher:

IEEE

Language:

English

Submitter:

Dimitrios Xenakis

Date Deposited:

03 May 2023 10:56

Last Modified:

28 Sep 2023 11:59

Related URLs:

Uncontrolled Keywords:

Trajectory Prediction; Multi-Agent Social Interactions; Transformers; Reinforcement Learning; Neural Architecture Search; Non-cooperative Game Theory; Clustering

BORIS DOI:

10.48350/182255

URI:

https://boris.unibe.ch/id/eprint/182255

Actions (login required)

Edit item Edit item
Provide Feedback