TY - JOUR
T1 - The human-following strategy for mobile robots in mixed environments
AU - Toan, Nguyen Van
AU - Do Hoang, Minh
AU - Khoi, Phan Bui
AU - Yi, Soo Yeong
N1 - Publisher Copyright:
© 2022 Elsevier B.V.
PY - 2023/2
Y1 - 2023/2
N2 - The robot behavior strategy is considered as a crucial part in the human-following task to help the robot maintain an appropriate distance and orientation to the selected target person (STP) with a smooth and safe manner. As usual, the robot is uniquely considered to follow the STP in a specific class of environments, such as unknown environments (non-mapped environments) or known environments (mapped environments). However, in real-life applications, the robot is sometimes requested to follow the STP in various types of environments, both in known and unknown ones. This observation raises the need to propose an alternative method to challenge the mentioned issue, as well as to break the current limit of the human-following function. In this paper, a new approach for the human-following strategy is proposed in which the mobile robot is enabled to follow the STP in mixed environments (non-mapped and mapped). In non-mapped environments, only the STP and the obstacle information with respect to the robot local coordinates are considered, whose purpose is to make the robot work without any prior understandings about its working environment. However, after the robot entered mapped environments, its prior knowledge of the working environment is leveraged to fulfill some additional requirements during the cooperation, such as the mobile robot in factories is not allowed to enter some specific areas even when the STP is executing technical tasks inside. Additionally, in this paper, a human-like inference mechanism is also introduced for the human-following strategy by using an extended hedge algebras. The proposed method is experimentally verified both in factories and laboratories. Demo Video Link: https://www.youtube.com/watch?v=YGrWU6ldKuw Since real videos in the factory are not allowed to publish, only visualization (in Rviz) is presented for demos in such kinds of environments. The visualization is synchronous with the real executions of the human–robot interactions. The robot used in the factory is an autonomous mobile robot (dimension 0.5 (m) ×1.0 (m), weight 120 (kg), carrying a tool cabinet around 300(kg))). The mobile robot is following the worker to support them during the technical processes in the car production line. In the video, the robot is represented by a green rectangular, and the STP is represented by a cylinder (with a sphere on its head) The events in the demo video are described more clearly in Appendix A.
AB - The robot behavior strategy is considered as a crucial part in the human-following task to help the robot maintain an appropriate distance and orientation to the selected target person (STP) with a smooth and safe manner. As usual, the robot is uniquely considered to follow the STP in a specific class of environments, such as unknown environments (non-mapped environments) or known environments (mapped environments). However, in real-life applications, the robot is sometimes requested to follow the STP in various types of environments, both in known and unknown ones. This observation raises the need to propose an alternative method to challenge the mentioned issue, as well as to break the current limit of the human-following function. In this paper, a new approach for the human-following strategy is proposed in which the mobile robot is enabled to follow the STP in mixed environments (non-mapped and mapped). In non-mapped environments, only the STP and the obstacle information with respect to the robot local coordinates are considered, whose purpose is to make the robot work without any prior understandings about its working environment. However, after the robot entered mapped environments, its prior knowledge of the working environment is leveraged to fulfill some additional requirements during the cooperation, such as the mobile robot in factories is not allowed to enter some specific areas even when the STP is executing technical tasks inside. Additionally, in this paper, a human-like inference mechanism is also introduced for the human-following strategy by using an extended hedge algebras. The proposed method is experimentally verified both in factories and laboratories. Demo Video Link: https://www.youtube.com/watch?v=YGrWU6ldKuw Since real videos in the factory are not allowed to publish, only visualization (in Rviz) is presented for demos in such kinds of environments. The visualization is synchronous with the real executions of the human–robot interactions. The robot used in the factory is an autonomous mobile robot (dimension 0.5 (m) ×1.0 (m), weight 120 (kg), carrying a tool cabinet around 300(kg))). The mobile robot is following the worker to support them during the technical processes in the car production line. In the video, the robot is represented by a green rectangular, and the STP is represented by a cylinder (with a sphere on its head) The events in the demo video are described more clearly in Appendix A.
KW - Hedge algebras fuzzy
KW - Human-following mobile robots
KW - Human-like inference mechanism
KW - Mixed environments
KW - Robot behavior strategy
UR - http://www.scopus.com/inward/record.url?scp=85143783008&partnerID=8YFLogxK
U2 - 10.1016/j.robot.2022.104317
DO - 10.1016/j.robot.2022.104317
M3 - Article
AN - SCOPUS:85143783008
SN - 0921-8890
VL - 160
JO - Robotics and Autonomous Systems
JF - Robotics and Autonomous Systems
M1 - 104317
ER -