Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structures
This addresses robot task planning for unstructured environments, but it is incremental as it builds on existing LLM methods with specific prompt and decomposition strategies.
The paper tackles robot task planning in unstructured environments by combining human expertise with an LLM using a directed graph prompt template, achieving good performance in code format handling and task-subtask relationship understanding, but faces limitations in task logic complexity and ambiguity.
Traditional robot task planning methods face challenges when dealing with highly unstructured environments and complex tasks. We propose a task planning method that combines human expertise with an LLM and have designed an LLM prompt template, Think_Net_Prompt, with stronger expressive power to represent structured professional knowledge. We further propose a method to progressively decompose tasks and generate a task tree to reduce the planning volume for each task, and we have designed a strategy to decouple robot task planning. By dividing different planning entities and separating the task from the actual machine binding process, the task planning process becomes more flexible. Research results show that our method performs well in handling specified code formats, understanding the relationship between tasks and subtasks, and extracting parameters from text descriptions. However, there are also problems such as limited complexity of task logic handling, ambiguity in the quantity of parts and the precise location of assembly. Improving the precision of task description and cognitive structure can bring certain improvements. https://github.com/NOMIzy/Think_Net_Prompt