Large Language Model-Based Robot Planning

This field studies how robots can use large language models to interpret instructions, reason about their surroundings, and plan tasks such as navigation, manipulation, and team coordination. Common approaches combine language or vision-language models with symbolic methods such as PDDL, behavior trees, scene graphs, and temporal logic, then use robot controllers to carry out the resulting plans. Systems also use visual feedback, memory, verification, and replanning to respond to changing environments and execution failures. A central challenge is making plans reliably feasible and safe in the physical world while keeping reasoning fast and affordable.