NRI: FND: Mutually Aware Social Navigation

NRI：FND：相互感知的社交导航

• 批准号: 1734361
• 负责人: Aaron Steinfeld
• 金额: $ 74.35万
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1734361&HistoricalAwards=false
• 关键词: NRI; FND; Mutually; Aware; Social

This project seeks to provide robots with the social intelligence to be aware of the mutualdependency between their movements and the movements of humans around them. To thisend, the work will focus on (1) improving the way robots reason about spatial behavior, and (2)developing navigation methods that lead to understandable and appropriate motion patterns insocial environments. This project will build upon prior work in robot perception and socialbehavior in crowds and groups. This work will impact the future use of robots in many application domains, especially for those where people untrained in robotics are present (e.g., delivery robots, guide robots, etc.). Almost all robots that move near people will need to behave appropriately, so it is necessary to discoversocially intelligent navigation techniques, thereby increasing human acceptance and marketsuccess. The team will also continue established and successful efforts in fostering diversity,integrating education with research, disseminating new knowledge to the general public,industry stakeholders, and other researchers.Prior work has identified the importance of human-aware navigation, and has developedmethods to incorporate the social norms that govern human physical space into aspects of robotpath planning. Building on this foundational work, the team will address three main socialintelligence tasks: (1) enabling robots to reason jointly about nearby human spatial behavior andtheir own, (2) enabling robots to communicate their intentions as they navigate so that theirmotion is understandable by nearby humans, and (3) giving robots the ability to decide when it isacceptable to violate pre-established social conventions. Research in these areas isincomplete since most efforts do not include awareness or reasoning about mutual dependency.This makes it difficult for a robot to reason intelligently on how to alter crowd motions in asocially appropriate manner. Methods discovered by the team will also support the case wheremultiple robots must mix with multiple humans.

该项目旨在为机器人提供社交智能，使其能够意识到自己的动作与周围人类的动作之间的相互依赖性。为此，这项工作将侧重于（1）改进机器人推理空间行为的方式，以及（2）开发导航方法，以在社会环境中产生可理解且适当的运动模式。该项目将建立在机器人感知和人群和群体社交行为方面的先前工作的基础上。这项工作将影响机器人在许多应用领域的未来使用，特别是对于那些未经机器人技术培训的人来说（例如送货机器人、引导机器人等）。几乎所有靠近人类的机器人都需要做出适当的行为，因此有必要发现社交智能导航技术，从而提高人类的接受度和市场成功率。该团队还将继续在促进多样性、将教育与研究相结合、向公众、行业利益相关者和其他研究人员传播新知识方面做出既定且成功的努力。之前的工作已经确定了人类感知导航的重要性，并开发了将管理人类物理空间的社会规范纳入机器人路径规划的方法。在这项基础工作的基础上，该团队将解决三个主要的社会智能任务：（1）使机器人能够共同推理附近人类的空间行为和它们自己的空间行为，（2）使机器人能够在导航时传达其意图，以便附近的人类可以理解它们的动作，以及（3）使机器人能够决定何时可以违反预先制定的社会惯例。这些领域的研究还不完整，因为大多数努力不包括对相互依赖的认识或推理。这使得机器人很难智能地推理如何以适合社会的方式改变人群运动。该团队发现的方法也将支持多个机器人必须与多个人类混合的情况。

项目成果

Follow The Robot: Modeling Coupled Human-Robot Dyads During Navigation

跟随机器人：在导航过程中对耦合的人机二元体进行建模

• DOI: 10.1109/iros40897.2019.8967656
• 发表时间: 2019
• 期刊: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS
• 作者: Nanavati, Amal;Tan, Xiang Zhi;Connolly, Joe;Steinfeld, Aaron
• 通讯作者: Steinfeld, Aaron

Core Challenges of Social Robot Navigation: A Survey

• DOI: 10.1145/3583741
• 发表时间: 2021-03
• 期刊: ACM Transactions on Human-Robot Interaction
• 影响因子: 5.1
• 作者: Christoforos Mavrogiannis;Francesca Baldini;Allan Wang;Dapeng Zhao;Aaron Steinfeld;Pete Trautman;Jean Oh

Group-based Motion Prediction for Navigation in Crowded Environments

• 发表时间: 2021-07
• 期刊: ArXiv
• 作者: Allan Wang;Christoforos Mavrogiannis;Aaron Steinfeld

Group Split and Merge Prediction With 3D Convolutional Networks

• DOI: 10.1109/lra.2020.2969947
• 发表时间: 2020-04
• 期刊: IEEE Robotics and Automation Letters
• 影响因子: 5.2
• 作者: Allan Wang;Aaron Steinfeld

SocNavBench: A Grounded Simulation Testing Framework for Evaluating Social Navigation

• DOI: 10.1145/3476413
• 发表时间: 2021-02
• 期刊: ACM Transactions on Human-Robot Interaction (THRI)
• 作者: Abhijat Biswas;Allan Wang;Gustavo Silvera;Aaron Steinfeld;H. Admoni