Abstract
In the environment cognition, how to realize efficient behavioral learning is a great challenge for the autonomous robot. Traditional methods, such as the model predictive control algorithms, suffer from the less flexibility and low efficiency. Since the robot may encounter the similar or same scenario in the following environment cognition, if it can determine its moving direction in advance, it will improve the efficiency of environment cognition. Considering that the lateral excitation in the internal neurons in the neural network can fire more surrounding neurons to store similar information, this paper introduces the lateral excitation in the internal neurons in a motivated developmental network to set up the weight connections between the robot’s moving direction and environment information in advance during the off-task process. When the robot meets similar or same scenario in its following environment cognition, it can determine its corresponding moving direction quickly, and enhance the efficiency of behavioral learning. Simulation in the static environment of the autonomous robot navigation demonstrates its effect.
Supported by Scientific Problem Tackling of Henan Province under Grant 192102210256.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yuan, Y., et al.: Model predictive control strategy based on dynamic matrix control for robot. J. Chongqing Univ. Posts Telecommun. (Nat. Sci. Ed.) 30(4), 537–543 (2018)
Ebel, H., Ardakani, E.S., Eberhard, P.: Distributed model predictive formation control with discretization-free path planning for transporting a load. Robot. Auton. Syst. 96, 211–223 (2017)
Joos, A., Hoffmann, M., Stein, T.: Human center of mass trajectory models using nonlinear model predictive control. IFAC PapersOnLine 51(22), 366–371 (2018)
Cefalo, M., Magrini, E., Oriolo, G.: Sensor-based task-constrained motion planning using model predictive control. IFAC PapersOnLine 51(22), 220–225 (2018)
Kim, T., Kim, W., Choi, S., Kim, H.J.: Path tracking for a skid-steer vehicle using model predictive control with on-line sparse Gaussian process. IFAC PapersOnLine 50(1), 5755–5760 (2017)
Kamil, F., Hong, T., Khaksar, W., Moghrabiah, M.Y., Zulkifli, N., Ahmad, S.A.: New robot navigation algorithm for arbitrary unknown dynamic environments based on future prediction and priority behavior. Expert Syst. Appl. 86, 274–291 (2017)
Kwon, W.Y., Suh, I.H.: Planning of proactive behaviors for human–robot cooperative tasks under uncertainty. Knowl.-Based Syst. 72, 81–95 (2014)
Liu, D., Cong, M., Du, Y., Zou, Q., Cui, Y.: Robotic autonomous behavior selection using episodic memory and attention system. Ind. Robot: Int. J. 44(3), 353–362 (2017)
Weng, J.: Why have we passed “neural networks do not abstract well”. Nat. Intell.: INNS Mag. 1(1), 13–22 (2011)
Weng, J., Luciw, M.: Dually optimal neuronal layers: lobe component analysis. IEEE Trans. Auton. Ment. Dev. 1(1), 68–85 (2009)
Solgi, M., Liu, T., Weng, J.: A computational developmental model for specificity and transfer in perecptual learning. J. Vis. 13(1), 1–23 (2013)
Wang, D., Shan, H., Xin, J.: Brain-like emergent auditory learning: a developmental method. Hear. Res. 370, 283–293 (2018)
Merrick, K.E.: A comparative study of value systems for self-motivated exploration and learning by robots. IEEE Trans. Auton. Ment. Dev. 2(2), 119–131 (2010)
Kakade, S., Dayan, P.: Dopamine: generalization and bonuses. Neural Netw. 15, 549–559 (2002)
Wang, D., Duan, Y., Weng, J.: Motivated optimal developmental learning for sequential tasks without using rigid time discounts. IEEE Trans. Neural Netw. Learn. Syst. 29(10), 4917–4931 (2018)
Zeng, D.: Research on path planning and control method for free-floating space robot. Dissertation for the Doctoral Degree of Harbin Institute of Technology, Harbin (2018)
Deng, W.: Research on path planning and trajectory tracking of Tracked EOD. Dissertation for the Doctoral Degree of Shandong University, Jinan (2018)
Ji, P.: Research on critical technology of human-robot interaction and local autonomy for mobile reconnaissance robot. Dissertation for the Doctoral Degree of Southeast University, Nanjing (2017)
Weng, J.: Natural and Artificial Intelligence: Introduction to Computational Brain-Mind. BMI Press, Okemos (2012)
Weng, J., Paslaski, S., Daly, J., Vandam, C., Brown, J.: Modulation for emergent networks: serotonin and dopamine. Neural Netw. 41, 225–239 (2013)
Daly, J., Brown, J., Weng, J.: Neuromorphic motivated systems. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), San Jose, California, USA, pp. 2917–2924 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, D., Yang, K. (2020). A Developmental Model of Behavioral Learning for the Autonomous Robot. In: Pan, L., Liang, J., Qu, B. (eds) Bio-inspired Computing: Theories and Applications. BIC-TA 2019. Communications in Computer and Information Science, vol 1160. Springer, Singapore. https://doi.org/10.1007/978-981-15-3415-7_40
Download citation
DOI: https://doi.org/10.1007/978-981-15-3415-7_40
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3414-0
Online ISBN: 978-981-15-3415-7
eBook Packages: Computer ScienceComputer Science (R0)