Abstract— Navigating through unknown outdoor environments requires a robot to be able to see and model the far field terrain. In recent years this problem of seeing beyond relia...
The circular sensing model has been widely used to estimate performance of sensing applications in existing analysis and simulations. While this model provides valuable high-level...
Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achi...
— This paper establishes the equivalence between cognitive medium access and the competitive multi-armed bandit problem. First, the scenario in which a single cognitive user wish...
Lifeng Lai, Hesham El Gamal, Hai Jiang, H. Vincent...
— A novel probabilistic online learning framework for autonomous off-road robot navigation is proposed. The system is purely vision-based and is particularly designed for predict...
Ayse Erkan, Raia Hadsell, Pierre Sermanet, Jan Ben...