Understanding Pedestrian Dynamics for Seamless Human-Robot Interaction

了解行人动力学以实现无缝人机交互

基本信息

批准号：
1825709
负责人：
Yi Guo
金额：
$ 35.85万
依托单位：
Stevens Institute of Technology
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2018
资助国家：
美国
起止时间：
2018-09-01 至 2023-08-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1825709&HistoricalAwards=false
关键词：
Understanding Pedestrian Dynamics Seamless Human

项目摘要

In the near future, robots will navigate alongside people in busy, crowded and unconstrained environments such as shopping malls, airports and elder-care facilities. Current mobile robot motion planners are inadequate because current models of pedestrian dynamics do not fully capture the complexity of human motion behavior in crowds. As a result, robots can "freeze" in places where crowd density is high, which further impedes pedestrian traffic flow. This project will use novel machine learning techniques to develop a robot motion planner with human-like navigations features. The project team will use objective and subjective performance measures to evaluate the predictability and acceptability of human-robot interactions with robots and their novel control algorithms deployed in shopping malls and campus buildings. This project serves the national interest because the resulting pedestrian dynamics modeling methods and robot controllers may result in public safety applications such as emergency evacuations and crowd planning/management. The project will involve an educational component that provides engineering and research methods training to graduate and undergraduate students, as well as STEM outreach to high-school and middle-school students. Additional efforts will be made to attract and retain women into careers in science and engineering. This research investigates new control methodologies that promise improved pedestrian/mobile-robot navigation through crowded and unconstrained environments. Methods include the extraction of features related to pedestrian behavior from existing datasets and their use in training a deep neural network (DNN) to model pedestrian dynamics; the use of inverse reinforcement learning to generate a cost map that humans follow to navigate; the implementation of the map within a robot motion controller; and the experimental testing and validation of the controller in real-world human environments using objective and subjective performance criteria. The experimental and evaluation data will be made available for use by the research community.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.

在不久的将来，机器人将在购物中心、机场和老年护理机构等繁忙、拥挤和不受约束的环境中与人们一起导航。当前的移动机器人运动规划器是不够的，因为当前的行人动力学模型没有完全捕捉人群中人类运动行为的复杂性。结果，机器人会在人群密度高的地方“冻结”，从而进一步阻碍行人交通流量。该项目将使用新颖的机器学习技术来开发具有类人导航功能的机器人运动规划器。项目团队将使用客观和主观性能测量来评估人机交互的可预测性和可接受性，以及机器人及其在购物中心和校园建筑中部署的新颖控制算法。该项目符合国家利益，因为由此产生的行人动力学建模方法和机器人控制器可能会导致公共安全应用，例如紧急疏散和人群规划/管理。该项目将涉及教育部分，为研究生和本科生提供工程和研究方法培训，并为高中生和中学生提供 STEM 推广。我们将做出更多努力来吸引和留住女性进入科学和工程领域。这项研究研究了新的控制方法，有望改善行人/移动机器人在拥挤和不受约束的环境中的导航。方法包括从现有数据集中提取与行人行为相关的特征，并将其用于训练深度神经网络（DNN）以建模行人动态；使用逆强化学习来生成人类可以遵循的导航成本图；机器人运动控制器内地图的实现；以及使用客观和主观性能标准在现实人类环境中对控制器进行实验测试和验证。实验和评估数据将可供研究界使用。该奖项反映了 NSF 的法定使命，并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，被认为值得支持。

项目成果

期刊论文数量（7）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Multi-Robot Guided Policy Search for Learning Decentralized Swarm Control

用于学习分散群体控制的多机器人引导策略搜索

DOI：
10.1109/lcsys.2020.3005441
发表时间：
2021-07-01
期刊：
IEEE Control Systems Letters
影响因子：
3
作者：
Chao Jiang;Yi Guo
通讯作者：
Yi Guo

Pedestrian Flow Optimization to Reduce the Risk of Crowd Disasters Through Human–Robot Interaction

通过人机交互优化人流，降低人群灾难风险

DOI：
10.1109/tetci.2019.2930249
发表时间：
2019-08
期刊：
IEEE Transactions on Emerging Topics in Computational Intelligence
影响因子：
5.3
作者：
Jiang, Chao;Ni, Zhen;Guo, Yi;He, Haibo
通讯作者：
He, Haibo

Distance-based Formation Control of a Three-Robot System

三机器人系统基于距离的编队控制

DOI：
10.1109/ccdc.2019.8833001
发表时间：
2019-06-01
期刊：
2019 Chinese Control And Decision Conference (CCDC)
影响因子：
0
作者：
Zhuo Chen;Chao Jiang;Yi Guo
通讯作者：
Yi Guo

Multi-robot formation control: a comparison between model-based and learning-based methods

多机器人编队控制：基于模型和基于学习的方法之间的比较

DOI：
10.1080/23307706.2019.1697970
发表时间：
2019-12-06
期刊：
J. Control. Decis.
影响因子：
0
作者：
Chao Jiang;Zhuo Chen;Yi Guo
通讯作者：
Yi Guo

Learning Human Navigation Behavior Using Measured Human Trajectories in Crowded Spaces

使用拥挤空间中测量的人体轨迹来学习人类导航行为

DOI：
10.1109/iros45743.2020.9341038
发表时间：
2020-10-24
期刊：
2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
影响因子：
0
作者：
M. Fahad;Guang Yang;Yi Guo
通讯作者：
Yi Guo