Learning to Simulate Crowds with Crowds
Document Type
Conference Proceeding
Publication Date
7-23-2023
Abstract
Controlling agent behaviors with Reinforcement Learning is of continuing interest in multiple areas. One major focus is to simulate multi-Agent crowds that avoid collisions while locomoting to their goals. Although avoiding collisions is important, it is also necessary to capture realistic anticipatory navigation behaviors. We introduce a novel methodology that includes: 1) an RL method for learning an optimal navigational policy, 2) position-based constraints for correcting policy navigational decisions, and 3) a crowd-sourcing framework for selecting policy control parameters. Based on optimally selected parameters, we train a multi-Agent navigation policy, which we demonstrate on crowd benchmarks. We compare our method to existing works, and demonstrate that our approach achieves superior multi-Agent behaviors.
Identifier
85167946538 (Scopus)
ISBN
[9798400701528]
Publication Title
Proceedings SIGGRAPH 2023 Posters
External Full Text Location
https://doi.org/10.1145/3588028.3603670
Recommended Citation
Talukdar, Bilas; Zhang, Yunhao; and Weiss, Tomer, "Learning to Simulate Crowds with Crowds" (2023). Faculty Publications. 1570.
https://digitalcommons.njit.edu/fac_pubs/1570