A robotic agent must coordinate its coupled concurrent behaviors to produce a coherent response to stimuli. Reinforcement learning has been used extensively in coordinating sensin...
This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches...
This paper presents an action selection method using fuzzy logic. The objective is to solve behaviour conflict in behaviour-based architectures for virtual agent navigation in un...
Abstract- We present a method that enhances evolutionary behavior testing of commercial computer games, as introduced in [CD+04], to deal with parameterized actions. The basic idea...
—In this paper we evaluate the use of Restricted Bolzmann Machines (RBM) in the context of learning and recognizing human actions. The features used as basis are binary silhouett...
Manuel Jesus Marin-Jimenez, Nicolas Perez De La Bl...