Enhancing Cognitive Robotics with Commonsense through LLM-Generated Preconditions and Subgoals
This addresses the problem of unreliable robot behavior in realistic scenarios for robotics applications, representing an incremental improvement by integrating LLMs into existing planning frameworks.
The researchers tackled the problem of robots failing at everyday tasks due to missing commonsense details in instructions by combining a Large Language Model with symbolic planning to generate plausible preconditions and subgoals. Their system produced more valid plans, achieved a higher task success rate, and adapted better to environmental changes compared to a baseline planner without the LLM step.
Robots often fail at everyday tasks because instructions skip commonsense details like hidden preconditions and small subgoals. Traditional symbolic planners need these details to be written explicitly, which is time consuming and often incomplete. In this project we combine a Large Language Model with symbolic planning. Given a natural language task, the LLM suggests plausible preconditions and subgoals. We translate these suggestions into a formal planning model and execute the resulting plan in simulation. Compared to a baseline planner without the LLM step, our system produces more valid plans, achieves a higher task success rate, and adapts better when the environment changes. These results suggest that adding LLM commonsense to classical planning can make robot behavior in realistic scenarios more reliable.