In recent years, personal mobility vehicles have been required to operate autonomously in places with numerous pedestrians. A navigation method using a single human-following scheme is used to avoid collision with pedestrians. However, in many cases, a single human-following method cannot be successfully used for guidance. In crowded places, pedestrians do not always keep walking in the desired direction a user wants to go, and the vehicle must change the target pedestrian frequently. Instead of following a single pedestrian, we propose a method for the vehicle to follow a cluster of pedestrians for stable and robust following. First, the pedestrians around the vehicle are detected by multiple RGB-D cameras, and the pedestrians are tracked using YOLO and Deep Sort. Pedestrians are classified according to their walking direction, and the cluster of pedestrians walking toward the goal is selected and followed. However, the position of pedestrian is sometimes lost in occlusions and the accuracy of the walking direction depends on the distance and pose detected by the sensors. A notable problem is that the cluster of pedestrians is unstable in the cluster following; therefore, a median of candidate vectors (MCV) observer is used to remove outliers caused by observation errors. The proposed method is applied to a scenario involving pedestrians walking toward an elevator hall in a building, and its effectiveness is verified through experiments.

1. [1] Y. Kanuki, N. Ohta, and N. Nakazawa, “Development of autonomous robot with simple navigation system for Tsukuba Challenge 2015,” J. Robot. Mechatron., Vol.28, No.4, pp. 432-4401, 2016. https://doi.org/10.20965/jrm.2016.p0432
2. [2] J. Lambert, L. Liang, L. Y. Morales, N. Akai, A. Carballo, E. Takeuchi, P. Narksri, S. Seiya, and K. Takeda, “Tsukuba Challenge 2017 dynamic object tracks dataset for pedestrian behavior analysis,” J. Robot. Mechatron., Vol.30, No.4, pp. 598-612, 2018. https://doi.org/10.20965/jrm.2018.p0598
3. [3] Y. Kanuki, N. Ohta, and N. Nakazawa, “Development of autonomous moving robot using appropriate technology for Tsukuba Challenge,” J. Robot. Mechatron., Vol.35, No.2, pp. 279-287, 2023. https://doi.org/10.20965/jrm.2023.p0279
4. [4] H. Darweesh, E. Takeuchi, K. Takeda, Y. Ninomiya, A. Sujiwo, L. Y. Morales, N. Akai, T. Tomizawa, and S. Kato, “Open source integrated planner for autonomous navigation in highly dynamic environments,” J. Robot. Mechatron., Vol.29, No.4, pp. 668-684, 2017. https://doi.org/10.20965/jrm.2017.p0668
5. [5] R. Matsumi, P. Raksincharoensak, and M. Nagai, “Study on autonomous intelligent drive system based on potential field with hazard anticipation,” J. Robot. Mechatron., Vol.27, No.1, pp. 5-11, 2015. https://doi.org/10.20965/jrm.2015.p0005
6. [6] A. Özdemir and V. Sezer, “A hybrid obstacle avoidance method: Follow the gap with dynamic window approach,” Proc. of IEEE Int. Conf. on Robotic Computing, 2017. https://doi.org/10.1109/IRC.2017.25
7. [7] Y. Zhang, X. Shen, and P. Raksincharoensak, “Study on collision avoidance strategies based on social force model considering stochastic motion of pedestrians in mixed traffic scenario,” J. Robot. Mechatron., Vol.35, No.2, pp. 240-254, 2023. https://doi.org/10.20965/jrm.2023.p0240
8. [8] H. Yoshitake, Y. Isono, and M. Shino, “Pedestrian avoidance method considering passenger comfort for autonomous personal mobility vehicles,” J. Robot. Mechatron., Vol.35, No.2, pp. 231-239, 2023. https://doi.org/10.20965/jrm.2023.p0231
9. [9] L. Joseph and J. Cacace, “Mastering ROS for robotics programming: Best practices and troubleshooting solutions when working with ROS,” 3rd edition, Packt Publishing, 2021.
10. [10] P. Trautman and A. Krause, “Unfreezing the robot: Navigation in dense, interacting crowds,” Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, 2010. https://doi.org/10.1109/IROS.2010.5654369
11. [11] T. Yoshimi, M. Nishiyama, T. Sonoura, H. Nakamoto, S. Tokura, H. Sato, F. Ozaki, N. Matsuhira, and H. Mizoguchi, “Development of a person following robot with vision based target detection,” Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pp. 5286-5291, 2006. https://doi.org/10.1109/IROS.2006.282029
12. [12] R. Gockley, J. Forlizzi, and R. Simmons, “Natural person-following behavior for social robots,” Proc. of ACM/IEEE Int. Conf. on Human-Robot Interaction, pp. 17-24, 2007. https://doi.org/10.1145/1228716.1228720
13. [13] J. Satake and J. Miura, “Robust stereo-based person detection and tacking for a person following robot,” Proc. of ICRA-2009 Workshop on Person Detection and Tracking, pp. 1-6, 2009.
14. [14] C. Chen, C. Chou, and F. Lian, “Trajectory planning for human host tracking and following of slave mobile robot on service-related tasks,” Proc. of IEEE Int. Conf. on Robotics and Biomimetics, 2011. https://doi.org/10.1109/ROBIO.2011.6181666
15. [15] M. Ota, T. Ogitsu, H. Hisahara, H. Takemura, Y. Ishii, and H. Mizoguchi, “Recovery function for human following robot losing target,” Proc. of 39th Annual Conf. of the IEEE Industrial Electronics Society, 2013. https://doi.org/10.1109/IECON.2013.6699818
16. [16] M. J. Islam, J. Hong, and J. Sattar, “Person-following by autonomous robots: A categorical overview,” The Int. J. of Robotics Research, Vol.38, No.14, pp. 1581-1618, 2019. https://doi.org/10.1177/0278364919881683
17. [17] K. Ichihara, T. Hasegawa, S. Yuta, H. Ichikawa, and Y. Naruse, “Waypoint-based human-tracking navigation for museum guide robot,” J. Robot. Mechatron., Vol.34, No.5, pp. 1192-1204, 2022. https://doi.org/10.20965/jrm.2022.p1192
18. [18] R. L. Hughes, “The flow of human crowds,” Annual Review of Fluid Mechanics, Vol.35, pp. 169-182, 2003. https://doi.org/10.1146/annurev.fluid.35.101101.161136
19. [19] G. C. Dachner and W. H. Warren, “Behavioral dynamics of heading alignment in pedestrian following,” Transportation Research Procedia, Vol.2, pp. 69-76, 2014. https://doi.org/10.1016/j.trpro.2014.09.010
20. [20] H. Okajima, Y. Kaneda, and N. Matsunaga, “State estimation method using median of multiple candidates for observation signals including outliers,” SICE J. of Control, Measurement, and System Integration, Vol.14, No.1, pp. 257-267, 2021. https://doi.org/10.1080/18824889.2021.1985702
21. [21] J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv:1804.02767, 2018. https://doi.org/10.48550/arXiv.1804.02767
22. [22] N. Wojke, A. Bewley, and D. Paulus, “Simple online and realtime tacking with a deep association metric,” arXiv:1703.07402, 2017. https://doi.org/10.48550/arXiv.1703.07402
23. [23] S. Thrun, W. Burgard, and D. Fox, “Probabilistic robotics,” The MIT Press, 2005.
24. [24] I. Yamamoto, K. Nakamura, N. Matsunaga, and H. Okajima, “Crowd tracking of electric wheelchair using RGB-D camera with median of candidate vectors observer,” Proc. of 61st Annual Conf. of the Society of Instrument and Control Engineers (SICE), 2022. https://doi.org/10.23919/SICE56594.2022.9905807
25. [25] M. Roux, “Basic procedures in hierarchical cluster analysis, applied multivariate analysis in SAR and environmental studies,” Chemical and Environmental Science, Vol.2, pp. 115-135, Springer, 1991.
26. [26] J. H. Ward Jr., “Hierarchical grouping to optimize an objective function,” J. of the American Statistical Association, Vol.58, No.301, pp. 235-244, 1963. https://doi.org/10.1080/01621459.1963.10500845
27. [27] T. Yu and H. Zhu, “Hyper-parameter optimization: A review of algorithms and applications,” arXiv preprint, arXiv:2003.05689, 2020. https://doi.org/10.48550/arXiv.2003.05689
28. [28] T. Sugano, H. Okajima, S. Samura, and N. Matsunaga, “Narrow space driving of welfare vehicles using robust platoon control with adaptive way point tracking,” Proc. of 55th Annual Conf. of the Society of Instrument and Control Engineers (SICE), pp. 1436-1441, 2016. https://doi.org/10.1109/SICE.2016.7749175