Fuzzy Modeling, Control and Prediction in Human-Robot Systems
A safe and synchronized interaction between human agents and robots in shared areas requires both long distance prediction of their motions and an appropriate control policy for short distance reaction. In this connection recognition of mutual intentions
- PDF / 1,699,007 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 2 Downloads / 213 Views
Abstract A safe and synchronized interaction between human agents and robots in shared areas requires both long distance prediction of their motions and an appropriate control policy for short distance reaction. In this connection recognition of mutual intentions in the prediction phase is crucial to improve the performance of short distance control. We suggest an approach for short distance control in which the expected human movements relative to the robot are being summarized in a so-called “compass dial” from which fuzzy control rules for the robot’s reactions are derived. To predict possible collisions between robot and human at the earliest possible time, the travel times to predicted human-robot intersections are calculated and fed into a hybrid controller for collision avoidance. By applying the method of velocity obstacles, the relation between a change in robot’s motion direction and its velocity during an interaction is optimized and a combination with fuzzy expert rules is used for a safe obstacle avoidance. For a prediction of human intentions to move to certain goals pedestrian tracks are modeled by fuzzy clustering, and trajectories of human and robot agents are extrapolated to avoid collisions at intersections. Examples with both simulated and real data show the applicability of the presented methods and the high performance of the results. Keywords Fuzzy control · Fuzzy modeling · Prediction · Human-robot interaction · Human intentions · Obstacle avoidance · Velocity obstacles Rainer Palm is adjunct professor at the AASS, Department of Technology, Orebro University. R. Palm (B) · R. Chadalavada · A. J. Lilienthal AASS MRO Lab, School of Science and Technology, Orebro University, 70182 Orebro, Sweden e-mail: [email protected] R. Chadalavada e-mail: [email protected] A. J. Lilienthal e-mail: [email protected] © Springer Nature Switzerland AG 2019 J. J. Merelo et al. (eds.), Computational Intelligence, Studies in Computational Intelligence 792, https://doi.org/10.1007/978-3-319-99283-9_8
149
150
R. Palm et al.
1 Introduction Interaction of humans and autonomous robots in common working areas is a challenging research field as to to system stability and performance and human safety. When human agents and robots share the same working area, both of them have to adapt their behavior, to either support their cooperation, or to enable them to do their own task separately. Research results on planning of mobile robot tasks, learning of repeated situations, navigation and obstacle avoidance have been published by [9, 15, 20, 22, 31]. In a scenario like this it is difficult to predict the behavior, motions and goals of a human agent. Even more it is important to predict the human behavior for a limited time horizon with a certain probability to enable the robot to perform adequate reactions. One class of solutions to this problem is the building of models of the human behavior by clustering methods [20, 24, 29]. Further research activities focus on Bayesian networks [12, 32], Hidden Markov
Data Loading...
