Many modern robotic applications require robots to function autonomously in dynamic environments including other decision making agents, such as people or other robots. This calls for fast and scalable interactive motion planning that is intention-aware.
We focus on real-time distributed navigation, constructing interactive motion models of other agents for counterfactual reasoning over their possible intentions. We develop a light-weight iterative planner for fluid pedestrian avoidance, utilising goal inference for long-range movement prediction. We implement on-line learning of a parameterised behaviour model as a computationally efficient alternative to offline training. This produces a scalable framework for navigation and intention prediction in dense multi-agent setups.
Our approach provides scientific insight into characteristics of human motion, such as agent awareness or share-of-effort in navigation. Our ultimate goal is performing interaction shaping in natural environments through robots, with connections to causal structure learning and language.