Towards Enhancing Social Navigation through Contextual and Human-related Knowledge

Robots acting in real-world environments usually need to interact with humans. Interactions may occur at different levels of abstraction (e.g., process, task, physical), entailing different research challenges (e.g., task allocation, human-robot joint actions, robot navigation). For social navigation, we propose a conceptual integration of task and motion planning to contextualize robot behaviors. The main idea is to leverage the contextual knowledge of a task planner to dynamically contextualize the navigation skills of a robot. More specifically, we propose a holistic model of tasks and human features and a mapping from task-level knowledge to motion-level knowledge to constrain the generation of robot trajectories.