In this paper, we investigate the hypothesis that plan recognition can significantly improve the performance of a casebased reinforcement learner in an adversarial action selectio...
Subsumption architectures are a well-known model for behaviour-based robotic control. The overall behaviour is achieved by defining a hierarchy of increasingly sophisticated behav...
— This paper introduces a hybrid control scheme for steering a non-holonomic agent with limited sensing capabilities and input constraints through a stationary but unknown worksp...
Apollo S. Oikonomopoulos, Savvas G. Loizou, Kostas...
Abstract. Continuous and synchronized whole-body motions are essential for achieving believable autonomous virtual humans in interactive applications. We present a new motion contr...
Abstract. Gaussian process models provide a probabilistic non-parametric modelling approach for black-box identification of nonlinear dynamic systems. The Gaussian processes can h...