Abstract
With continuous deterioration of the natural environment and the corresponding significant increase in the occurrence of disasters, forest fire accidents have frequently occurred in recent decades. Therefore, it is important to perform extensive effective fire drills to increase evacuation experience and emergency reaction capacity. In comparison to traditional fire drills, which are subject to many latent uncertainties and incur high costs, fire exercises based on virtual scenarios offer many advantages, such as low cost and high safety. Accordingly, the planning and design of effective evacuation paths that sufficiently match real conditions have become an imperative focus of related research. In this paper, we propose a novel framework for path planning in virtual emergency scenarios, which consists of three parts. (a) Configuration of the virtual environment: for convenience in handling, the virtual emergency scenario is discretized into many individual grid cells. (b) Policy generation: a dual deep Q-learning network approach is employed to obtain an effective policy that can allow agents to intelligently find effective paths. (c) Grouping strategy: a strategy is proposed to support multiple agents in achieving collective evacuation based on a given policy. Finally, extensive experiments are presented to validate the superiority of the proposed framework. The results show that by comparison with the existing related state-of-the-art methods, our proposed framework is superior and feasible.
Similar content being viewed by others
References
Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with Double Q-learning[C]. Proceedings of the AAAI Conference on Artificial Intelligence 30(1)
Haznedar B, Arslan MT, Kalinli A (2021) Optimizing ANFIS using simulated annealing algorithm for classification of microarray gene expression cancer data[J]. Medical & Biological Engineering & Computing 59(3):497–509
Wang B, Xie Y, Zhou S et al (2017) Reversible Data Hiding Based on DNA Computing[J]. Computational Intelligenceand Neuroscience 1-9
Adleman L (1994) Molecular computation of solutions to combinatorial problems[J]. Science 266(5187):1021–1024
Zhong G, Li T, Jiao W et al (2020) DNA computing inspired deep networks design[J]. Neurocomputing 3(24):140–147
Hussien HH (2019) DNA computing for RGB image encryption with genetic algorithm[C]. In 2019 14th international conference on computer engineering and systems (ICCES). IEEE, 169-173
Sun L, Kong X, Xu J et al (2019) A hybrid gene selection method based on ReliefF and ant colony optimization algorithm for tumor classification[J]. Sci Rep 9(1):1–14
Mondal M, Ray KS (2020) Prediction of visibility under radiation fog by DNA computing[J]. New Mathematics and Natural Computation 16(2):231–254
Jafarzadeh N, Iranmanesh A (2016) A new graph theoretical method for analyzing DNA sequences based on genetic codes[J]. MATCH-Commun Math Comput Chem 75(3):731–742
Liu R, Wang Y (2019) Research on TSP Solution Based on Genetic Algorithm[C]. In 2019 IEEE/ACIS 18th International Conference on Computer and Information Science (ICIS). IEEE
Yang R, Zhang C, Gao R (2017) A new bionic method inspired by DNA computation to solve the hamiltonian path problem[C]. 2017 IEEE International Conference on Information and Automation (ICIA). IEEE 219-225
Elsayed WM, Elmogy M, El-Desouky BS (2021) DNA sequence reconstruction based on innovated hybridization technique of probabilistic cellular automata and particle swarm optimization. Inf Sci 1(547):828–840
Li X, Wang B, Lv H et al (2020) Constraining DNA sequences with a triplet-bases unpaired. IEEE Trans Nanobiosci 19(2):299–303
Shi K, Huang L, Jiang D, Sun Y, Tong X, Xie Y, Fang Z (2022) Path planning optimization of intelligent vehicle based on improved genetic and ant colony hybrid algorithm[J]. Frontiers in Bioengineering and Biotechnology 10:905–983
Liu Y, Jiang D, Xu C et al (2022) Deep learning based 3D target detection for indoor scenes[J]. Applied Intelligence 1-14
Yun J, Jiang D, Sun Y, Huang L, Tao B, Jiang G, Kong J, Weng Y, Li G, Fang Z (2022) Grasping pose detection for loose stacked object based on convolutional neural network with multiple self-powered sensors information[J]. IEEE Sensors Journal
Liu H, Xu B, Lu D et al (2018) A path planning approach for crowd evacuation in buildings based on improved artificial bee colony algorithm[J]. Appl Soft Comput 68:360–376
Da Silva FL, Costa AHR (2019) A survey on transfer learning for multiagent reinforcement learning systems[J]. Journal of Artificial Intelligence Research 64:645–703
Gronauer S, Diepold K (2022) Multi-agent deep reinforcement learning: A survey[J]. Artif Intell Rev 55(2):895–943
Wang X, Wang S, Liang X et al (2022) Deep reinforcement learning: a survey[J]. IEEE Transactions on Neural Networks and Learning Systems 1-15
Oroojlooy A, Hajinezhad D (2022) A review of cooperative multi-agent deep reinforcement learning[J]. Applied Intelligence 1-46
Yin Z, Yang J, Zhang Q et al (2021) DNA computing model for satisfiability problem based on hybridization chain reaction[J]. Int J Pattern Recognit Artif Intell 35(03):2159–2170
Qiu C, Hu Y, Chen Y et al (2019) Deep deterministic policy gradient (DDPG)-based energy harvesting wireless communications[J]. IEEE Internet Things J 6(5):8577–8588
Prasad PC, Jaiswal A, Shakya S et al (2021) Portfolio Optimization: A Study of Nepal Stock Exchange[C]. Proceedings of International Conference on Sustainable Expert Systems. Springer, Singapore 659-672
Li J, Chen Y, Zhao XN et al (2022) An improved DQN path planning algorithm[J]. J Supercomput 78(1):616–639
Zuo G, Du T, Lu J (2017) Double DQN method for object detection[C]. 2017 Chinese Automation Congress (CAC). IEEE 6727-6732
Min K, Kim H, Huh K. (2018) Deep Q Learning based high level driving policy determination[C]. IEEE Intelligent Vehicles Symposium (IV). IEEE 226-231
Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning[J]. Nature 518(7540):529–533
Duan Y, Chen X, Houthooft R, Schulman J, Abbeel P (2016) Benchmarking deep reinforcement learning for continuous control[C]. In International conference on machine learning (PMLR) 1329-1338
Zhou W, Jiang W, Jie B et al (2022) Multiagent evacuation framework for a virtual fire emergency scenario based on generative adversarial imitation learning[J]. Computer Animation and Virtual Worlds 33(1):e2035
Li J, Chen Y, Zhao XN et al (2022) An improved DQN path planning algorithm[J]. J Supercomput 78(1):616–639
Acknowledgements
The authors appreciate the comments and suggestions from all the anonymous reviewers, which have helped to significantly improve this paper. In addition, this work was supported in part by the National Natural Science Foundation of China (NSFC) (grant no. 61902003) and the Doctoral Scientific Research Foundation of Anhui Normal University.
Funding
Partial financial support was received from the National Natural Science Foundation of China (NSFC) (grant no. 61902003).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, W., Zhang, C. & Chen, S. Dual deep Q-learning network guiding a multiagent path planning approach for virtual fire emergency scenarios. Appl Intell 53, 21858–21874 (2023). https://doi.org/10.1007/s10489-023-04601-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04601-9