CAREER: Generalizable and Reliable Behavior Synthesis in Uncertain Open-World Environments

职业：不确定开放世界环境中的可推广且可靠的行为综合

• 批准号: 1942856
• 负责人: Siddharth Srivastava
• 金额: $ 56.27万
• 依托单位: Arizona State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-01 至 2025-07-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1942856&HistoricalAwards=false
• 关键词: CAREER; Generalizable; Reliable; Behavior; Synthesis

There is broad consensus on the need for AI systems that are reliable and useful in situations going beyond carefully controlled environments. The focus of this project is on developing autonomous agents that can plan and act safely in “open-world” settings, where the agent has limited information about the environment where it will be used. Such agents may be uncertain about the numbers, types and identities of objects that they may encounter, as well as about the relationships between them. Furthermore, the nature of uncertainty about these properties may be “non-stationary”, meaning the environment may change during the agent’s deployment. The outcomes of this project will help increase the scope and applicability of AI systems by developing new methods for computing safe and reliable AI behavior in realistic non-stationary, open-world settings. In order to make AI systems more broadly accessible, this project will also develop an autonomous interactive tutorial system for teaching students about different types of AI planning problems and their solution representations. The proposed activity will develop new principles and analytical methods for understanding the computational nature of open-world planning problems. It will engender broad convergence of principles and algorithms from logic-based and probabilistic approaches to AI, as well as from theoretical computer science. In particular, it will develop new representations for efficiently expressing qualitative and decision-theoretic formulations of open-world planning problems along with efficient algorithms and implementations for solving them while using abstractions for efficiency and generalizability. New methods will be developed to utilize statistical learning techniques for enhancing computational efficiency while ensuring that the computed agent behavior meets desired requirements on safety and reliability in open-world settings. The results and progress made during the project will be evaluated on physical and simulated testbeds featuring contemporary robotics platforms. Problem generators and simulated testbeds will be made publicly available as benchmarks to aid reproducibility and spur progress in this area of research.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人们普遍认为，人工智能系统需要在超出精心控制的环境的情况下可靠和有用。该项目的重点是开发自主代理，可以在“开放世界”环境中安全地计划和行动，其中代理对使用环境的信息有限。这些代理人可能不确定他们可能遇到的对象的数量，类型和身份，以及它们之间的关系。此外，关于这些属性的不确定性的性质可以是“非静止的”，这意味着环境可以在代理的部署期间改变。该项目的成果将有助于通过开发新方法来增加人工智能系统的范围和适用性，以便在现实的非静态开放世界环境中计算安全可靠的人工智能行为。为了使人工智能系统更广泛地使用，该项目还将开发一个自主的交互式教程系统，用于教授学生不同类型的人工智能规划问题及其解决方案。拟议的活动将开发新的原则和分析方法，以了解开放世界规划问题的计算性质。它将产生广泛的原则和算法的融合，从基于逻辑和概率的方法到人工智能，以及从理论计算机科学。特别是，它将开发新的表示，有效地表达定性和决策理论的配方，开放世界的规划问题，沿着有效的算法和实现解决这些问题，同时使用抽象的效率和概括性。将开发新的方法来利用统计学习技术来提高计算效率，同时确保计算的代理行为满足开放世界环境中安全性和可靠性的要求。项目期间取得的成果和进展将在具有现代机器人平台的物理和模拟试验台上进行评估。问题发生器和模拟试验台将作为基准公开提供，以帮助再现性和刺激在这一领域的研究进展。该奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

项目成果

Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems

符号问题广义强化学习的关系抽象

• DOI: 10.24963/ijcai.2022/435
• 发表时间: 2022
• 期刊: IJCAI
• 作者: Karia, Rushang;Srivastava, Siddharth
• 通讯作者: Srivastava, Siddharth

JEDAI: A System for Skill-Aligned Explainable Robot Planning

JEDAI：技能一致的可解释机器人规划系统

• 发表时间: 2022
• 期刊: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems
• 作者: Shah, N.;Verma, P.;Angle, T.;Srivastava, S.
• 通讯作者: Srivastava, S.

Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning

学习广义关系启发式网络以进行与模型无关的规划

• 发表时间: 2021
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Rushang Karia, Siddharth Srivastava