In current city visualisations crowds are being included to increase realism in the scene. With the self-steering nature of crowds it is traditionally difficult to control the nu...
In real world applications, agents - be they software agents or autonomous robots - inevitably face erroneous situations that have not been planned for. Re-planning can sometimes ...
Robert J. Ross, Rem W. Collier, Gregory M. P. O'Ha...
The existing reinforcement learning approaches have been suffering from the policy alternation of others in multiagent dynamic environments such as RoboCup competitions since othe...
We give an overview of the EPFL indoor flying project, whose goal is to evolve neural controllers for autonomous, adaptive, indoor micro-flyers. Indoor flight is still a challenge ...
Context-aware computing in location-aware environments demands the combination of real world position with a computational world model to infer context. We present a novel approach...