From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network

• URL: http://arxiv.org/abs/2309.09181v1
• Date: Sun, 17 Sep 2023 07:09:16 GMT
• Title: From Cooking Recipes to Robot Task Trees -- Improving Planning Correctness and Task Efficiency by Leveraging LLMs with a Knowledge Network
• Authors: Md Sadman Sakib and Yu Sun
• Abstract summary: Our method first uses a large language model (LLM) to retrieve recipe instructions and then utilizes a fine-tuned GPT-3 to convert them into a task tree. The pipeline then mitigates the uncertainty and unreliable features of LLM outputs using task tree retrieval. Our evaluation results show its superior performance compared to previous works in task planning accuracy and efficiency.
• Score: 6.4111574364474215
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Task planning for robotic cooking involves generating a sequence of actions for a robot to prepare a meal successfully. This paper introduces a novel task tree generation pipeline producing correct planning and efficient execution for cooking tasks. Our method first uses a large language model (LLM) to retrieve recipe instructions and then utilizes a fine-tuned GPT-3 to convert them into a task tree, capturing sequential and parallel dependencies among subtasks. The pipeline then mitigates the uncertainty and unreliable features of LLM outputs using task tree retrieval. We combine multiple LLM task tree outputs into a graph and perform a task tree retrieval to avoid questionable nodes and high-cost nodes to improve planning correctness and improve execution efficiency. Our evaluation results show its superior performance compared to previous works in task planning accuracy and efficiency.

Related papers

• Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability [6.4111574364474215]
  The inherent probabilistic nature of Large Language Models (LLMs) introduces an element of unpredictability. This paper introduces an innovative approach aims to generate correct and optimal robotic task plans for diverse real-world demands and scenarios.
  arXiv  Detail & Related papers  (2024-01-15T18:01:59Z)
• TaskBench: Benchmarking Large Language Models for Task Automation [85.3879908356586]
  We introduce TaskBench to evaluate the capability of large language models in task automation. To generate high-quality evaluation datasets, we introduce the concept of Tool Graph. We also propose TaskEval to evaluate the capability of LLMs from different aspects, including task decomposition, tool invocation, and parameter prediction.
  arXiv  Detail & Related papers  (2023-11-30T18:02:44Z)
• ADaPT: As-Needed Decomposition and Planning with Language Models [131.063805299796]
  We introduce As-Needed Decomposition and Planning for complex Tasks (ADaPT) ADaPT explicitly plans and decomposes complex sub-tasks as-needed, when the Large Language Models is unable to execute them. Our results demonstrate that ADaPT substantially outperforms established strong baselines.
  arXiv  Detail & Related papers  (2023-11-08T17:59:15Z)
• Tree Prompting: Efficient Task Adaptation without Fine-Tuning [112.71020326388029]
  Tree Prompting builds a decision tree of prompts, linking multiple LM calls together to solve a task. Experiments on classification datasets show that Tree Prompting improves accuracy over competing methods and is competitive with fine-tuning.
  arXiv  Detail & Related papers  (2023-10-21T15:18:22Z)
• Tree-Planner: Efficient Close-loop Task Planning with Large Language Models [63.06270302774049]
  Tree-Planner reframes task planning with Large Language Models into three distinct phases. Tree-Planner achieves state-of-the-art performance while maintaining high efficiency.
  arXiv  Detail & Related papers  (2023-10-12T17:59:50Z)
• Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structures [2.3698227130544547]
  We propose a task planning method that combines human expertise with an LLM and have designed an LLM prompt template, Think_Net_Prompt. We further propose a method to progressively decompose tasks and generate a task tree to reduce the planning volume for each task.
  arXiv  Detail & Related papers  (2023-06-08T13:10:00Z)
• Learning to Plan with Natural Language [111.76828049344839]
  Large Language Models (LLMs) have shown remarkable performance in various basic natural language tasks. For completing the complex task, we still need a plan for the task to guide LLMs to generate the specific solutions step by step. We propose the Learning to Plan method, which involves two phases: (1) In the first learning task plan phase, it iteratively updates the task plan with new step-by-step solutions and behavioral instructions, which are obtained by prompting LLMs to derive from training error feedback.
  arXiv  Detail & Related papers  (2023-04-20T17:09:12Z)
• Reinforcement Learning with Success Induced Task Prioritization [68.8204255655161]
  We introduce Success Induced Task Prioritization (SITP), a framework for automatic curriculum learning. The algorithm selects the order of tasks that provide the fastest learning for agents. We demonstrate that SITP matches or surpasses the results of other curriculum design methods.
  arXiv  Detail & Related papers  (2022-12-30T12:32:43Z)
• Extracting task trees using knowledge retrieval search algorithms in functional object-oriented network [0.0]
  The functional object-oriented network (FOON) has been developed as a knowledge representation method that can be used by robots. A FOON can be observed as a graph that can provide an ordered plan for robots to retrieve a task tree.
  arXiv  Detail & Related papers  (2022-11-15T17:20:08Z)
• Evaluating Recipes Generated from Functional Object-Oriented Network [4.94338660039249]
  The functional object-oriented network (FOON) has been introduced as a knowledge representation, which takes the form of a graph. To get a sequential plan for a manipulation task, a robot can obtain a task tree through a knowledge retrieval process from the FOON. We compare the quality of an acquired task tree with a conventional form of task knowledge, such as recipes or manuals.
  arXiv  Detail & Related papers  (2021-06-01T19:00:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.