Active Perception, Manipulation, and Personalized Navigation for Advanced Service Robots

Service robots acting in human environments must actively perceive their environment, act foresightedly, and adapt to individual user preferences. In this talk, I will first present methods to enable robots to efficiently perceive the environment and carefully manipulate objects in cluttered scenes. In particular, I will introduce an active mapping approach for confined spaces such as household shelves or horticultural crop rows, where significant occlusions pose challenges for service robots. In these scenarios, robots need to manipulate objects to reduce occlusions and improve visibility. I will explain how to enable a robot to carefully pull or push objects for robust manipulation in cluttered spaces. In addition, robots operating in household scenarios must adapt to individual user preferences to ensure comfort. To address this, I will present a framework that enables users to teach a mobile robot their preferred navigation behavior using an intuitive virtual reality interface. Our user study demonstrates that this personalized approach greatly enhances user comfort over traditional methods.