Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2401.07868 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911781833670656 |
|---|---|
| author | Sakib, Md Sadman Sun, Yu |
| author_facet | Sakib, Md Sadman Sun, Yu |
| contents | The inherent probabilistic nature of Large Language Models (LLMs) introduces an element of unpredictability, raising concerns about potential discrepancies in their output. This paper introduces an innovative approach aims to generate correct and optimal robotic task plans for diverse real-world demands and scenarios. LLMs have been used to generate task plans, but they are unreliable and may contain wrong, questionable, or high-cost steps. The proposed approach uses LLM to generate a number of task plans as trees and amalgamates them into a graph by removing questionable paths. Then an optimal task tree can be retrieved to circumvent questionable and high-cost nodes, thereby improving planning accuracy and execution efficiency. The approach is further improved by incorporating a large knowledge network. Leveraging GPT-4 further, the high-level task plan is converted into a low-level Planning Domain Definition Language (PDDL) plan executable by a robot. Evaluation results highlight the superior accuracy and efficiency of our approach compared to previous methodologies in the field of task planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07868 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability Sakib, Md Sadman Sun, Yu Robotics Artificial Intelligence Computation and Language The inherent probabilistic nature of Large Language Models (LLMs) introduces an element of unpredictability, raising concerns about potential discrepancies in their output. This paper introduces an innovative approach aims to generate correct and optimal robotic task plans for diverse real-world demands and scenarios. LLMs have been used to generate task plans, but they are unreliable and may contain wrong, questionable, or high-cost steps. The proposed approach uses LLM to generate a number of task plans as trees and amalgamates them into a graph by removing questionable paths. Then an optimal task tree can be retrieved to circumvent questionable and high-cost nodes, thereby improving planning accuracy and execution efficiency. The approach is further improved by incorporating a large knowledge network. Leveraging GPT-4 further, the high-level task plan is converted into a low-level Planning Domain Definition Language (PDDL) plan executable by a robot. Evaluation results highlight the superior accuracy and efficiency of our approach compared to previous methodologies in the field of task planning. |
| title | Consolidating Trees of Robotic Plans Generated Using Large Language Models to Improve Reliability |
| topic | Robotics Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2401.07868 |