Pub Date : 2024-03-01DOI: 10.1142/s2972335324010026
Yu Sun, Dong Xu, Xiaorui Zhu
For the inaugural issue of the International Journal of Artificial Intelligence and Robotics Research (IJAIRR), I am honored to present an editorial that encapsulates the essence and ambition of this cutting-edge publication. IJAIRR emerges at a time when Artificial Intelligence and Robotics (AIR) are not merely technological novelties but fundamental drivers of progress across various scientific and practical domains. This journal aims to be at the forefront of documenting, analyzing, and guiding the interdisciplinary integration of AI, robotics, and fundamental sciences.
{"title":"Inaugural Issue of the International Journal of Artificial Intelligence and Robotics Research (IJAIRR): The Emergence of an Interdisciplinary Nexus","authors":"Yu Sun, Dong Xu, Xiaorui Zhu","doi":"10.1142/s2972335324010026","DOIUrl":"https://doi.org/10.1142/s2972335324010026","url":null,"abstract":"For the inaugural issue of the International Journal of Artificial Intelligence and Robotics Research (IJAIRR), I am honored to present an editorial that encapsulates the essence and ambition of this cutting-edge publication. IJAIRR emerges at a time when Artificial Intelligence and Robotics (AIR) are not merely technological novelties but fundamental drivers of progress across various scientific and practical domains. This journal aims to be at the forefront of documenting, analyzing, and guiding the interdisciplinary integration of AI, robotics, and fundamental sciences.","PeriodicalId":516715,"journal":{"name":"International Journal of Artificial Intelligence and Robotics Research","volume":"121 43","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140089312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-15DOI: 10.1142/s2972335324500029
Md. Sadman Sakib, Yu Sun
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","authors":"Md. Sadman Sakib, Yu Sun","doi":"10.1142/s2972335324500029","DOIUrl":"https://doi.org/10.1142/s2972335324500029","url":null,"abstract":"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.","PeriodicalId":516715,"journal":{"name":"International Journal of Artificial Intelligence and Robotics Research","volume":" 56","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139640608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：