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 and a state-of-the-art local navigation framework.
Original language | English (US) |
---|---|
Pages (from-to) | 294-300 |
Number of pages | 7 |
Journal | IJCAI International Joint Conference on Artificial Intelligence |
Volume | 2016-January |
State | Published - 2016 |
Event | 25th International Joint Conference on Artificial Intelligence, IJCAI 2016 - New York, United States Duration: Jul 9 2016 → Jul 15 2016 |
Bibliographical note
Funding Information:Partial support for this work is acknowledged from the University of Minnesota Informatics Institute and NSF through grants #CNS-1544887 and #CHS-1526693