… comfort embedded, via active preference learning. Then, the … RL process to guide the robot
agent to explore the latent … preference learning, we introduce hybrid experience learning, …

… learning (RL) is being actively studied for robot navigation due to its promise of superior
performance and robustness. However, most existing deep RL navigation … RL navigation method …

… learning framework for crowd-aware robot navigation problems to learn policies over multiple
competing objectives whose relative importance preference is dynamic to the robot. First, a …

… off-policy learning and preference learning to train a robot policy that … Related Works Deep
reinforcement learning based … performance in socially aware robot navigation. In optimizing …

… to reuse robot’s previous experiences to meet user’s preferences while maintaining the
planning flexible. We extend this approach to consider preferences for robot navigation also in …

… robots. In this work, we investigate physical interaction for communicating robot navigation
preferences… human preferences in the robot navigation domain. So far, force-sensitive mobile …

… robot navigation controller that adapts to user preferences by learning from demonstrations
of robot … human avoidance taking into account user-specific preference. Both human and …

… a vector reflecting the reaction of the robot to its perceived world. The desired … D navigation
problem into several 2-D navigation problems. Each 2-D navigation system uses a preference…

… in home scenarios, users are particularly looking forward to being able to restrict the
mobile (service) robot’s work area and control the robot navigation behavior according to their …

… robot’s plans and rationale for clarity also known as Explainable Artificial Intelligence (XAI)
[6], is the other key aspect of robot navigation in … human preferences for robot navigational XAI …