Moving in a Crowd: Safe and Efficient Navigation Among Heterogeneous Agents
Abstract
Multi-agent navigation methods typically assume that all agents use the same underlying framework to navigate to their goal while avoiding colliding with each other. However, such assumption does not hold when agents do not know how other agents will move. We address this issue by proposing a Bayesian inference approach where an agent estimates the navigation model and goal of each neighbor, and uses this to compute a plan that minimizes collisions while driving it to its goal. Simulation experiments performed in many scenarios demonstrate that an agent using our approach computes safer and more time-efficient paths as compared to those generated without our inference approach anda state-of-the-art local navigation framework. PDF
Cite
Text
Godoy et al. "Moving in a Crowd: Safe and Efficient Navigation Among Heterogeneous Agents." International Joint Conference on Artificial Intelligence, 2016.Markdown
[Godoy et al. "Moving in a Crowd: Safe and Efficient Navigation Among Heterogeneous Agents." International Joint Conference on Artificial Intelligence, 2016.](https://mlanthology.org/ijcai/2016/godoy2016ijcai-moving/)BibTeX
@inproceedings{godoy2016ijcai-moving,
title = {{Moving in a Crowd: Safe and Efficient Navigation Among Heterogeneous Agents}},
author = {Godoy, Julio and Karamouzas, Ioannis and Guy, Stephen J. and Gini, Maria L.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2016},
pages = {294-300},
url = {https://mlanthology.org/ijcai/2016/godoy2016ijcai-moving/}
}