Proceedings

Deep Learning-Based Pedestrian Simulation with Limited Real-World Training Data: An Evaluation Framework

Vahid Mahzoon, Abigail Liu, Slobodan Vucetic

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 196-204.

https://doi.org/10.24963/ijcai.2025/23

Keywords

  • Machine Learning: ML: Benchmarks
  • Agent-based and Multi-agent Systems: MAS: Agent-based simulation and emergence
  • Machine Learning: ML: Multi-task and transfer learning

Abstract

Simulating pedestrian movement is important for applications such as disaster management, robotics, and game design. While deep learning models have been extensively used on related problems, their use as pedestrian simulators remains relatively unexplored. This paper aims to encourage more research in this direction in two ways. First, it proposes an evaluation framework that is applicable to both traditional and deep learning based simulators. Second, it proposes and evaluates several ideas related to input representation, choice of neural architecture, exploiting knowledge-based simulators in data poor regimes, and repurposing trajectory prediction models. Our extensive experiments provide several useful insights for future research in pedestrian simulation. The code is available at https://github.com/vmahzoon76/DL-Crowd-Sim.

Vahid Mahzoon, Abigail Liu, and Slobodan Vucetic. 2025. Deep Learning-Based Pedestrian Simulation with Limited Real-World Training Data: An Evaluation Framework. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 196–204. https://doi.org/10.24963/ijcai.2025/23
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards