Proceedings of the Nineteenth International Conference on Principles of Knowledge Representation and Reasoning最新文献

筛选

英文中文

Online Grounding of Symbolic Planning Domains in Unknown Environments 未知环境下符号规划域的在线接地

Proceedings of the Nineteenth International Conference on Principles of Knowledge Representation and Reasoning Pub Date : 2021-12-18 DOI: 10.24963/kr.2022/53

Leonardo Lamanna, L. Serafini, A. Saetti, A. Gerevini, P. Traverso

{"title":"Online Grounding of Symbolic Planning Domains in Unknown Environments","authors":"Leonardo Lamanna, L. Serafini, A. Saetti, A. Gerevini, P. Traverso","doi":"10.24963/kr.2022/53","DOIUrl":"https://doi.org/10.24963/kr.2022/53","url":null,"abstract":"If a robotic agent wants to exploit symbolic planning techniques to achieve some goal, it must be able to properly ground an abstract planning domain in the environment in which it operates. However, if the environment is initially unknown by the agent, the agent needs to explore it and discover the salient aspects of the environment necessary to reach its goals. Namely, the agent has to discover: (i) the objects present in the environment, (ii) the properties of these objects and their relations, and finally (iii) how abstract actions can be successfully executed. The paper proposes a framework that aims to accomplish the aforementioned perspective for an agent that perceives the environment partially and subjectively, through real value sensors (e.g., GPS, and on-board camera) and can operate in the environment through low level actuators (e.g., move forward of 20 cm). We evaluate the proposed architecture in photo-realistic simulated environments, where the sensors are RGB-D on-board camera, GPS and compass, and low level actions include movements, grasping/releasing objects, and manipulating objects. The agent is placed in an unknown environment and asked to find objects of a certain type, place an object on top of another, close or open an object of a certain type. We compare our approach with a state of the art method on object goal navigation based on reinforcement learning, showing better performances.","PeriodicalId":351970,"journal":{"name":"Proceedings of the Nineteenth International Conference on Principles of Knowledge Representation and Reasoning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126189775","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}

引用次数: 3

Discovering User-Interpretable Capabilities of Black-Box Planning Agents 发现黑匣子规划代理的用户可解释能力

Proceedings of the Nineteenth International Conference on Principles of Knowledge Representation and Reasoning Pub Date : 2021-07-28 DOI: 10.24963/kr.2022/36

Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava

{"title":"Discovering User-Interpretable Capabilities of Black-Box Planning Agents","authors":"Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava","doi":"10.24963/kr.2022/36","DOIUrl":"https://doi.org/10.24963/kr.2022/36","url":null,"abstract":"Several approaches have been developed for answering users' specific questions about AI behavior and for assessing their core functionality in terms of primitive executable actions. However, the problem of summarizing an AI agent's broad capabilities for a user is comparatively new. This paper presents an algorithm for discovering from scratch the suite of high-level \"capabilities\" that an AI system with arbitrary internal planning algorithms/policies can perform. It computes conditions describing the applicability and effects of these capabilities in user-interpretable terms. Starting from a set of user-interpretable state properties, an AI agent, and a simulator that the agent can interact with, our algorithm returns a set of high-level capabilities with their parameterized descriptions. Empirical evaluation on several game-based scenarios shows that this approach efficiently learns descriptions of various types of AI agents in deterministic, fully observable settings. User studies show that such descriptions are easier to understand and reason with than the agent's primitive actions.","PeriodicalId":351970,"journal":{"name":"Proceedings of the Nineteenth International Conference on Principles of Knowledge Representation and Reasoning","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127699224","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}

引用次数: 5

首页上一页