Abstract
Algorithms are the heart of each robotics system. A specific class of algorithm embedded in robotics systems is the so-called behavior – or action – selection algorithm. These algorithms select an action a robot should take, when performing a specific task. The action selection is determined by the parameters of the algorithm. However, manually choosing a proper configuration within the high-dimensional parameter space of the behavior selection algorithm is a non-trivial and demanding task. In this paper, we show how this problem can be addressed with supervised learning techniques. Our method starts by learning the algorithm behavior from the parameter space according to environment features, then bootstrap itself into a more robust framework capable of self-adjusting robot parameters in real-time. We demonstrate our concept on a set of examples, including simulations and real world experiments.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bajcsy, A., Losey, D. P., O’Malley, M. K., Dragan, A.D.: Learning from physical human corrections, one feature at a time. In: Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction, pp. 141–149 (2018)
DeMers, D., Kreutz-Delgado, K.: Learning global direct inverse kinematics. In: Advances in Neural Information Processing Systems, pp. 589–595 (1992)
Fox, D., Burgard, W., Thrun, S.: The dynamic window approach to collision avoidance. IEEE Robot. Autom. Mag. 4(1), 23–33 (1997)
Frochte, J., Marsland, S.: A learning approach for Ill-posed optimization problems. In: Le, T.D., et al. (eds.) AusDM 2019. CCIS, vol. 1127, pp. 16–27. Springer, Singapore (2019). https://doi.org/10.1007/978-981-15-1699-3_2
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)
Huang, Z., Chen, Y.: An improved artificial fish swarm algorithm based on hybrid behavior selection. Int. J. Control Autom. 6(5), 103–116 (2013)
Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
Izumi, K., Habib, M.K., Watanabe, K., Sato, R.: Behavior selection based navigation and obstacle avoidance approach using visual and ultrasonic sensory information for quadruped robots. Int. J. Adv. Robot. Syst. 5(4), 41 (2008)
Khatib, O.: Real-time obstacle avoidance for manipulators and mobile robots. In: Autonomous Robot Vehicles, pp. 396–404. Springer (1986). https://doi.org/10.1007/978-1-4613-8997-2_29
Kim, G., Chung, W.: Navigation behavior selection using generalized stochastic petri nets for a service robot. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 37(4), 494–503 (2007)
LaValle, S.M.: Rapidly-exploring random trees: A new tool for path planning
Liu, D., Cong, M., Du, Y., Gao, S.: Robot behavior selection using salient landmarks and object-based attention. In: 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1101–1106. IEEE (2013)
Murphy, T.G., Lyons, D.M., Hendriks, A.J.: Stable grasping with a multi-fingered robot hand: a behavior-based approach. In: Proceedings of 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 1993), vol. 2, pp. 867–874. IEEE (1993)
Wang, X., Ray, A., Lee, P., Fu, J.: Optimal control of robot behavior using language measure. In: Quantitative Measure for Discrete Event Supervisory Control, pp. 157–181. Springer (2005). https://doi.org/10.1007/0-387-23903-0_6
Wang, Y., Li, S., Chen, Q., Hu, W.: Biology inspired robot behavior selection mechanism: using genetic algorithm. In: Li, K., Fei, M., Irwin, G.W., Ma, S. (eds.) LSMS 2007. LNCS, vol. 4688, pp. 777–786. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74769-7_82
Acknowledgments
This work was funded by the federal state of North Rhine-Westphalia and the European Regional Development Fund FKZ: ERFE-040021.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Tousside, B., Mohr, J., Schmidt, M., Frochte, J. (2020). A Learning Approach for Optimizing Robot Behavior Selection Algorithm. In: Chan, C.S., et al. Intelligent Robotics and Applications. ICIRA 2020. Lecture Notes in Computer Science(), vol 12595. Springer, Cham. https://doi.org/10.1007/978-3-030-66645-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-66645-3_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66644-6
Online ISBN: 978-3-030-66645-3
eBook Packages: Computer ScienceComputer Science (R0)