Abstract
It would be a very challenging task for mobile robot to track a person walking ahead on hilly terrains with a 2D lidar sensor instead of a 3D lidar or a rotating 2D lidar sensor. But it is clear that the 2D lidar based method is much more efficient in terms of computational costs and sensor cost only. For successful leader-following of the mobile robot with the 2D lidar sensor on such hilly roads, it is necessary to develop a classifier capable of recognizing a specific body part of the leader differently from other parts. In this study, the Mahalanobis distance kernel based on two features extracted from the leader’s torso profiles is used to construct the elliptical decision boundaries for the classification problem. In addition, based on that classifier, the roll and pitch angle of the 2D lidar sensor are controlled to continuously track the leader’s body part and to estimate the relative distance between the leader and the robot. As a result, even when the leader walks along paths with flat-to-hill transitions in day and night, the mobile robot successfully follows the leader with 80 % detection rate by stable pitching not exceed 1° of the 2D lidar sensor for keeping the torso inside its field of view. The proposed approach will be useful to improve the performances of multi-sensor based leader detection system using not only lidar sensor but also vision sensor with switching control scheme.
Similar content being viewed by others
Abbreviations
- {S}:
-
Spatial coordinate frame
- {B}:
-
Body coordinate frame attached to the mobile robot
- {T}:
-
Tool coordinate frame attached to the LRF
- W:
-
Width of human torso profile scanned by the lidar
- G:
-
Girth of human torso profile scanned by the lidar
- σ XY :
-
Covariance of X and Y
- d follow :
-
Designated distance between the leader and the following robot
- θ1, θ2 :
-
Angular position of 2-DOF module motors
- θp :
-
Pitching motion profile for pitching motion of LRF
- R XY :
-
Rotation matrix of body coordinate frame {Y} relative to spatial coordinate frame {X}
- J XY :
-
Configuration-dependent matrix that maps the joint velocities
- \(\omega _{XY}^z\) :
-
Instantaneous angular velocity of body coordinate frame {Y} relative to spatial coordinate frame {X}, expressed in {Z}
References
R. Bogue, Exoskeletons and robotic prosthetics: a review of recent developments, Industrial Robot: An International Journal, 36 (5) (2009) 421–427.
J. Kruger, T. K. Lien and A. Verl, Cooperation of human machines in assembly lines, CIRP Annals — Manufacturing Technology, 58 (2009) 628–646.
M. Kobilarov, G. Sukhatme, J. Hyams and P. Batavia, People tracking and following with mobile robot using an omnidirectional camera and a laser, Proceedings of 2006 IEEE International Conference on Robotics and Automation, Orland, Florida, USA (2006) 557–562.
N. Bellotto and H. Hu, Multisensor-based human detection and tracking for mobile service robots, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 39 (1) (2009) 167–181.
T. Shimizu, M. Awai, A. Yamashita and T. Kaneko, Mobile robot system realizing human following and autonomous returning using laser range finder and camera, Proceedings of the 18th Korea-Japan Joint Workshop on Frontiers of Computer Vision, Okinawa, Japan (2012) 97–102.
Boston Dynamics, LS3 — Legend Squad Support System, YouTube LLC (2012).
Y. Khassanov, N. Imanberdiyev and H. A. Varol, Inertial motion capture based reference trajectory generation for a mobile manipulator, Proceedings of the 2014 ACM/IEEE International Conference on Human-robot Interaction (2014) 202–203.
Maryland Robotics Center, Follow Behavior for Unmanned Ground Vehicle, YouTube LLC (2012).
N. V. Duc, Human Following Mobile Robot, YouTube LLC (2011).
I. Lee et al., Camera-laser fusion sensor system and environmental recognition for humanoids in disaster scenarios, Journal of Mechanical Science and Technology, 31 (6) (2017) 2997–3003.
K. Cho, S. H. Baeg and S. Park, Object tracking with enhanced data association using a 3D range sensor for an unmanned ground vehicle, Journal of Mechanical Science and Technology, 28 (11) (2014) 4381–4388.
A. V. Gulalkari et al., Object tracking and following six-legged robot system using kinect camera based on Kalman filter and backstepping controller, Journal of Mechanical Science and Technology, 29 (12) (2015) 5425–5436.
R. C. Luo, Y. J. Chen, C. T. Liao and A. C. Tsai, Mobile robot based human detection and tracking using range and intensity data fusion, IEEE Workshop on Advanced Robotics and Its Social Impacts, Hsinchu, China (2007) 1–6.
D. Hähnel, W. Burgard and S. Thrun, Learning compact 3D models of indoor and outdoor environments with a mobile robot, Robotics and Autonomous Systems, 44 (1) (2003) 15–27.
J. H. Kim, J. Lyou and H. K. Kwak, Vision coupled GPS/INS scheme for helicopter navigation, Journal of Mechanical Science and Technology, 24 (2) (2010) 489–496.
M. Ilyas, S. Park and S.-H. Baeg, Improving unmanned ground vehicle navigation by exploiting virtual sensors and multisensor fusion, Journal of Mechanical Science and Technology, 28 (11) (2014) 4369–4379.
S.-J. Huang, S. Liu and C.-H. Wu, Intelligent humanoid mobile robot with embedded control and stereo visual feedback, Journal of Mechanical Science and Technology, 29 (9) (2015) 3919–3931.
E. J. Jung, J. H. Lee and B. J. Yi, Development of a laser-ragne-finder-based human tracking and control algorithm for a marathoner service robot, Transactions on Mechatronics, 19 (6) (2014) 1963–1976.
B. Choi, G. Park and Y. Lee, Practical control of a rescue robot while maneuvering on uneven terrain, Journal of Mechanical Science and Technology, 32 (5) (2018) 2021–2028.
W. J. Chung, H. Y. Kim, Y. K. Yoo, C. B. Moon and J. Y. Park, The detection and following of human legs through inductive approaches for a mobile robot with a single laser range finder, Transactions on Mechatronics, 59 (8) (2012) 3156–3166.
S. Lee et al., Anomaly detection of tripod shafts using modified Mahalanobis distance, Journal of Mechanical Science and Technology, 32 (6) (2018) 2473–2478.
dhlee04, IROL — Leader Following on Hilly Terrains Exp#1, YouTube LLC (2016).
Acknowledgments
This work was supported by the Basic Science Research Program through the National Research Foundation of Korea, funded by the Ministry of Education [2014R1A1A2055 334]. This work supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2019R1F1A1045834).
Author information
Authors and Affiliations
Corresponding author
Additional information
Jihoon Kim received his B.S. degree in 2012 from the School of Mechanical and Aerospace Engineering, Seoul National University, Seoul, Korea, He is currently a Staff Engineer of Samsung Electronics Mechanical Development Core Technology R&D Team.
Hyungjin Jeong received his B.S. degree in 2014 from the School of Mechanical Engineering, Soongsil University, Seoul, Korea, where he is currently working toward his Master’s degree.
Donghun Lee received his B.S. degree in Mechanical Engineering from Soongsil University, Korea, in 2004, and his Ph.D. degree in Mechanical Engineering from Seoul National University, Korea, in 2009. He is currently an Associate Professor at the School of Mechanical Engineering, Soongsil University, Korea. His current research interests include field robots, human motion recognition, machine learning and redundant mechanism.
Rights and permissions
About this article
Cite this article
Kim, J., Jeong, H. & Lee, D. Single 2D lidar based follow-me of mobile robot on hilly terrains. J Mech Sci Technol 34, 3845–3854 (2020). https://doi.org/10.1007/s12206-020-0835-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-020-0835-7