Curiosity-based Robot Navigation under Uncertainty in Crowded Environments

被引:3
|
作者
Cai, Kuanqi [1 ]
Chen, Weinan [2 ]
Wang, Chaoqun [3 ]
Zhang, Hong [1 ]
Meng, Max Q. -H. [4 ,5 ,6 ]
机构
[1] Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen 518055, Peoples R China
[2] Guangdong Univ Technol, Sch Electromech Engn, Guangzhou, Peoples R China
[3] Shandong Univ, Sch control Sci & Engn, Jinan 250061, Shandong, Peoples R China
[4] Southern Univ Sci & Technol, Shenzhen Key Lab Robot Percept & Intelligence, Shenzhen 518055, Peoples R China
[5] Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen 518055, Peoples R China
[6] Shenzhen Res Inst Chinese Univ Hong Kong, Shenzhen 518057, Peoples R China
基金
中国国家自然科学基金;
关键词
Robots; Location awareness; Uncertainty; Navigation; Trajectory; Collision avoidance; Robot kinematics; Autonomous vehicle navigation; localization; motion and path planning; service robotics;
D O I
10.1109/LRA.2022.3232270
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Mobile robots have become more and more popular in large-scale and crowded environments, such as airports, shopping malls, etc. However, due to sparse landmarks and crowd noise, localization in this environment is a great challenge. Furthermore, it is unreliable for the robot to navigate safely in crowds while considering human comfort. Thus, how to navigate safely with localization precision in that environment is a critical problem. To solve this problem, we proposed a curiosity-based framework that can find an effective path with the consideration of human comfort and crowds, localization uncertainty, and the cost-to-go to the target. Three parts are involved in the proposed framework: the distance assessment module, the Curiosity for Positive Content (CPC), namely information-rich areas, and the Curiosity for Negative Content (CNC), namely crowded areas. CPC is introduced when the real-time localization uncertainty evaluation is not satisfied. This factor is predicted through the propagation of uncertainty along the candidate trajectory to provoke the robot to approach localization-referenced landmarks. The Human Comfort and Crowd Density Map (HCCDM) based on the Gaussian Mixture Model (GMM) is established to calculate CNC, which drives the robot to bypass the crowd and consider human comfort. The evaluation is conducted in a series of large-scale and crowded environments. The results show that our method can find a feasible path that can consider the localization uncertainty while simultaneously avoiding the crowded area.
引用
收藏
页码:800 / 807
页数:8
相关论文
共 50 条
  • [21] A Curiosity-Based Learning Method for Spiking Neural Networks
    Shi, Mengting
    Zhang, Tielin
    Zeng, Yi
    FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2020, 14
  • [22] Planning of vision-based navigation for a mobile robot under uncertainty
    Moon, IH
    Miura, J
    Yanagi, Y
    Shirai, Y
    IROS '97 - PROCEEDINGS OF THE 1997 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOT AND SYSTEMS: INNOVATIVE ROBOTICS FOR REAL-WORLD APPLICATIONS, VOLS 1-3, 1996, : 1202 - 1207
  • [23] Model inductive bias enhanced deep reinforcement learning for robot navigation in crowded environments
    Chen, Man
    Huang, Yongjie
    Wang, Weiwen
    Zhang, Yao
    Xu, Lei
    Pan, Zhisong
    COMPLEX & INTELLIGENT SYSTEMS, 2024, 10 (05) : 6965 - 6982
  • [24] CCTV-Informed Human-Aware Robot Navigation in Crowded Indoor Environments
    Kim, Mincheul
    Kwon, Youngsun
    Lee, Sebin
    Yoon, Sung-eui
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (06): : 5767 - 5774
  • [25] Curiosity-Based Learning Algorithm for Distributed Interactive Sculptural Systems
    Chan, Matthew T. K.
    Gorbet, Rob
    Beesley, Philip
    Kulic, Dana
    2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2015, : 3435 - 3441
  • [26] Uncertainty-aware Navigation in Crowded Environment
    Alao, Emmanuel
    Martinet, Philippe
    2022 17TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV), 2022, : 293 - 298
  • [27] An Approach of Social Navigation Based on Proxemics for Crowded Environments of Humans and Robots
    Daza, Marcos
    Barrios-Aranibar, Dennis
    Diaz-Amado, Jose
    Cardinale, Yudith
    Vilasboas, Joao
    MICROMACHINES, 2021, 12 (02)
  • [28] Robot Subgoal-guided Navigation in Dynamic Crowded Environments with Hierarchical Deep Reinforcement Learning
    Zhang, Tianle
    Liu, Zhen
    Pu, Zhiqiang
    Yi, Jianqiang
    Liang, Yanyan
    Zhang, Du
    INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, 2023, 21 (07) : 2350 - 2362
  • [29] A Comprehensive Review of Mobile Robot Navigation Using Deep Reinforcement Learning Algorithms in Crowded Environments
    Le, Hoangcong
    Saeedvand, Saeed
    Hsu, Chen-Chien
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2024, 110 (04)
  • [30] Interactive Navigation of Multiple Agents in Crowded Environments
    van den Berg, Jur
    Patil, Sachin
    Sewall, Jason
    Manocha, Dinesh
    Lin, Ming
    I3D 2008: SYMPOSIUM ON INTERACTIVE 3D GRAPHICS AND GAMES, PROCEEDINGS, 2008, : 139 - 147