Socially Aware Mobile Robot Navigation System - An Open-source Software Platform

具有社交意识的移动机器人导航系统 - 开源软件平台

• 批准号: 538083-2019
• 负责人: Ngo, TrungDung
• 金额: $ 1.68万
• 依托单位: University of Prince Edward Island
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2019
• 资助国家: 加拿大
• 起止时间: 2019-01-01 至 2020-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=679418
• 关键词: Socially; Aware; Mobile; Robot; Navigation

A socially aware robot navigation systems that enables a mobile robot to autonomously navigate in social environments such as airports, shopping malls, museums is highly expected to deploy mobile robots for our daily services. The first and most important issue to allow a mobile robot to work in a social environment is that the robot must avoid not only regular obstacles but also humans while navigating safely and socially towards a given goal.We will investigate and develop a socially aware robot navigation system by incorporating socio-spatio-temporal characteristics of humans on a social reactive motion model. In this project, we will develop a social reactive motion model (SRM) added on the conventional robot navigation scheme to enable the mobile robot to deal with different social situations of individuals and human groups when navigating in social environments. SRM is composed of four functional blocks: (1) human detection and tracking is to detect and track humans in the vicinity of the robot; (2) human state extraction is to extract human position, orientation, velocity and human postures; (3) human group estimation is to estimate groups of interactive humans; (4) social reactive control incorporates information of individuals and human groups into an extended social force model. SRM can be integrated on a conventional path planning, e.g. D*, RRT, to generate a socially aware robot motion planning that enables the robot to navigate towards the given goal while socially and reactively avoiding individuals, human group, other robots, and environmental obstacles. The socially aware robot navigation system will be developed on a ROS-based software platform that will be integrated and tested on QBot2 provided by Quanser.

能够在机场、购物中心、博物馆等社会环境中自主导航的移动机器人的“社会感知机器人导航系统”，有望在我们的日常服务中部署移动机器人。让移动机器人在社交环境中工作的第一个也是最重要的问题是，机器人不仅要避开常规障碍，还要在安全、社交地朝着既定目标前进的同时避开人类。我们将通过在社会反应运动模型上结合人类的社会时空特征来研究和开发一个社会感知机器人导航系统。在这个项目中，我们将开发一个社会反应运动模型（social reactive motion model， SRM），添加到传统的机器人导航方案中，使移动机器人在社交环境中导航时能够处理不同的个人和人类群体的社交情况。SRM由四个功能块组成：(1)人的检测和跟踪是对机器人附近的人进行检测和跟踪；(2)人体状态提取，提取人体的位置、方向、速度和姿势；(3)人类群体估计是对交互人类群体的估计；(4)社会反应性控制将个体和人类群体的信息纳入一个扩展的社会力量模型。SRM可以集成到传统的路径规划中，例如D*、RRT，生成具有社会意识的机器人运动规划，使机器人能够在社交和反应性地避开个人、人类群体、其他机器人和环境障碍的同时，向给定目标导航。社会感知机器人导航系统将在基于ros的软件平台上开发，该软件平台将在Quanser提供的QBot2上进行集成和测试。