Exploring shared autonomy in assistive and service robots makes human-aware navigation of a person following robot (PFR) a required behaviour. In this paper, we propose a control framework for a non-holonomic wheeled robot that not only tracks a target person in sight but also anticipates the human movement patterns to predict the future sequence of its path when the person is out of sight. Human beings form a crowd and can exhibit complex random movement compared to vehicles while indoor environments with intersections can pose serious challenges for long-distance path-following without the breakdown of tracking. Thus, a nonlinear model predictive controller is designed with long-term prediction and socially compliant rules for natural person-following behaviour. It can generate the collision-free path and optimized control inputs using a single optimization framework Finally, the integrated navigation-control stack is evaluated using simulations for real-time operation. We also present a hardware configuration for its real-world implementation.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Followman: Control of Social Person Following Robot


    Contributors:


    Publication date :

    2021-09-19


    Size :

    1928490 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Gesture Based Social Interaction and Person Following with a Flying Robot

    Naseer, Tayyab / Sturm, Jürgen / Burgard, Wolfram et al. | Tema Archive | 2014


    Visual person identification using a distance-dependent appearance model for a person following robot

    Satake, J. / Chiba, M. / Miura, J. | British Library Online Contents | 2013


    Behavior of a Person-Following Robot in Pedestrian Environments: Laboratory Experimentation and Simulation

    Li, Ruowei / Ghizzawi, Farah / Le, Tho V. et al. | Transportation Research Record | 2025