Abstract
A design scheme for probabilistic planning and decision-making of mobile agents is proposed, which realizes the functions of probabilistic planning and grab control of mobile agents. How to use MC-POMDP algorithm to perform sensing and control in an unknown environment is described in detail. Combined with the particle filter algorithm to approximate the confidence state space, the existing POMDP technology was improved, and the probability planning was optimized. The actual operation results show the feasibility and effectiveness of the scheme. The system uses its own sensors to sense the environmental information, performs dynamic probabilistic path planning, successfully approaches the target object, and implements the mobile grabbing function of the mobile agent. Based on the example application of reinforcement learning principles, a new direction for the probability planner to deal with the generalized uncertainty of mobile agents is prospected.
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
Zhao, L., Wang, J., Liu, J., et al.: Routing for crowd management in smart cities: a deep reinforcement learning perspective. IEEE Commun. Mag. 57(4), 88–93 (2019)
Wang, C., Ju, P., Lei, S., et al.: Markov decision process-based resilience enhancement for distribution systems: an approximate dynamic programming approach. IEEE Trans. Smart Grid PP(99), 1 (2019)
Heydari, A.: Stability analysis of optimal adaptive control under value iteration using a stabilizing initial policy. IEEE Trans. Neural Netw. Learn. Syst. 29(9), 4522–4527 (2018)
López-Araquistain, J., Jarama, Á.J., Besada, J.A., et al.: A new approach to map-assisted Bayesian tracking filtering. Inf. Fusion 45, 79–95 (2018)
Wang, D., Tan, X.: Bayesian neighborhood component analysis. IEEE Trans. Neural Netw. Learn. Syst. 29(7), 3140–3151 (2017)
Chen, H.N., Mao, Z.L.: Study on the failure probability of occupant evacuation with the method of Monte Carlo sampling. Procedia Eng. 211, 55–62 (2018)
Kragic, D.: From active perception to deep learning. Sci. Robot. 3(23), eaav1778 (2018)
Neftci, E.O., Averbeck, B.B.: Reinforcement learning in artificial and biological systems. Nat. Mach. Intell. 1, 133–143 (2019)
Acknowledgments
Project supported by the Funds for the “13th Five-Year Plan” for scientific and technological research projects of the Education Department of Jilin Province, China (Grant No. JJKH20181139KJ).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, Y., Wang, J. (2021). Probability Programming and Control of Moving Agent Based on MC-POMDP. In: MacIntyre, J., Zhao, J., Ma, X. (eds) The 2020 International Conference on Machine Learning and Big Data Analytics for IoT Security and Privacy. SPIOT 2020. Advances in Intelligent Systems and Computing, vol 1282. Springer, Cham. https://doi.org/10.1007/978-3-030-62743-0_111
Download citation
DOI: https://doi.org/10.1007/978-3-030-62743-0_111
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62742-3
Online ISBN: 978-3-030-62743-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)