{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:22:50Z","timestamp":1785511370626,"version":"3.56.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T00:00:00Z","timestamp":1737676800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T00:00:00Z","timestamp":1737676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach. Intell. Res."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s11633-024-1512-6","type":"journal-article","created":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T04:21:48Z","timestamp":1737692508000},"page":"79-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Target Search and Navigation in Heterogeneous Robot Systems with Deep Reinforcement Learning"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6572-4105","authenticated-orcid":false,"given":"Yun","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2888-5210","authenticated-orcid":false,"given":"Jiaping","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,24]]},"reference":[{"issue":"2","key":"1512_CR1","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s10846-013-9822-x","volume":"72","author":"Y G Liu","year":"2013","unstructured":"Y. G. Liu, G. Nejat. Robotic urban search and rescue: A survey from the control perspective. Journal of Intelligent & Robotic Systems, vol. 72, no. 2, pp. 147\u2013165, 2013. DOI: https:\/\/doi.org\/10.1007\/s10846-013-9822-x.","journal-title":"Journal of Intelligent & Robotic Systems"},{"issue":"1","key":"1512_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.16182\/j.issn1004731x.joss.23-1297E","volume":"36","author":"Y C Tang","year":"2024","unstructured":"Y. C. Tang, S. J. Qi, L. X. Zhu, X. R. Zhuo, Y. Q. Zhang, F. Meng. Obstacle avoidance motion in mobile robotics. Journal of System Simulation, vol. 36, no. 1, pp. 1\u201326, 2024. DOI: https:\/\/doi.org\/10.16182\/j.issn1004731x.joss.23-1297E.","journal-title":"Journal of System Simulation"},{"key":"1512_CR3","doi-asserted-by":"publisher","unstructured":"J. P. Xiao, J. H. Chee, M. Feroskhan. Real-time multi-drone detection and tracking for pursuit-evasion with parameter search. IEEE Transactions on Intelligent Vehicles, to be published. DOI: https:\/\/doi.org\/10.1109\/TIV.2024.3360433.","DOI":"10.1109\/TIV.2024.3360433"},{"issue":"2","key":"1512_CR4","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/LRA.2019.2891991","volume":"4","author":"F Niroui","year":"2019","unstructured":"F. Niroui, K. C. Zhang, Z. Kashino, G. Nejat. Deep reinforcement learning robot for search and rescue applications: Exploration in unknown cluttered environments. IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 610\u2013617, 2019. DOI: https:\/\/doi.org\/10.1109\/LRA.2019.2891991.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"1512_CR5","doi-asserted-by":"publisher","unstructured":"K. W. Hu, Z. Chen, H. W. Kang, Y. C. Tang. 3D vision technologies for a self-developed structural external crack damage recognition robot. Automation in Construction, vol. 159, Article number 105262, 2024. DOI: https:\/\/doi.org\/10.1016\/j.autcon.2023.105262.","DOI":"10.1016\/j.autcon.2023.105262"},{"key":"1512_CR6","doi-asserted-by":"publisher","unstructured":"C. Liu, J. Zhao, N. Y. Sun. A review of collaborative airground robots research. Journal of Intelligent & Robotic Systems, vol. 106, no. 3, Article number 60, 2022. DOI: https:\/\/doi.org\/10.1007\/s10846-022-01756-4.","DOI":"10.1007\/s10846-022-01756-4"},{"key":"1512_CR7","doi-asserted-by":"publisher","unstructured":"F. Gul, W. Rahiman, S. S. N. Alhady. A comprehensive study for robot navigation techniques. Cogent Engineering, vol. 6, no. 1, Article number 1632046, 2019. DOI: https:\/\/doi.org\/10.1080\/23311916.2019.1632046.","DOI":"10.1080\/23311916.2019.1632046"},{"key":"1512_CR8","doi-asserted-by":"publisher","unstructured":"O. Varlamov, D. Aladin. A new generation of rules-based approach: Mivar-based intelligent planning of robot actions (MIPRA) and brains for autonomous robots. Machine Intelligence Research, vol. 21, no. 5, pp. 919\u2013940. DOI: https:\/\/doi.org\/10.1007\/s11633-023-1473-1.","DOI":"10.1007\/s11633-023-1473-1"},{"issue":"2","key":"1512_CR9","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1109\/TVT.2018.2890416","volume":"68","author":"H L Qin","year":"2019","unstructured":"H. L. Qin, Z. H. Meng, W. Meng, X. D. Chen, H. Sun, F. Lin, M. H. Ang. Autonomous exploration and mapping system using heterogeneous UAVs and UGVS in GPS-denied environments. IEEE Transactions on Vehicular Technology, vol. 68, no. 2, pp. 1339\u20131350, 2019. DOI: https:\/\/doi.org\/10.1109\/TVT.2018.2890416.","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"1512_CR10","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"D Yarats","year":"2021","unstructured":"D. Yarats, I. Kostrikov, R. Fergus. Image augmentation is all you need: Regularizing deep reinforcement learning from pixels. In Proceedings of the 9th International Conference on Learning Representations, 2021."},{"issue":"2","key":"1512_CR11","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1109\/LRA.2021.3056373","volume":"6","author":"B Liu","year":"2021","unstructured":"B. Liu, X. S. Xiao, P. Stone. A lifelong learning approach to mobile robot navigation. IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 1090\u20131096, 2021. DOI: https:\/\/doi.org\/10.1109\/LRA.2021.3056373.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"1512_CR12","doi-asserted-by":"publisher","unstructured":"J. P. Xiao, M. Feroskhan. Learning multi-pursuit evasion for safe targeted navigation of drones. IEEE Transactions on Artificial Intelligence, to be published. DOI: https:\/\/doi.org\/10.1109\/TAI.2024.3366871.","DOI":"10.1109\/TAI.2024.3366871"},{"issue":"1","key":"1512_CR13","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1109\/LRA.2020.3036597","volume":"6","author":"Q Y Wu","year":"2021","unstructured":"Q. Y. Wu, X. X. Gong, K. Xu, D. Manocha, J. X. Dong, J. Wang. Towards target-driven visual navigation in indoor scenes via generative imitation learning. IEEE Robotics and Automation Letters, vol. 6, no. 1, pp. 175\u2013182, 2021. DOI: https:\/\/doi.org\/10.1109\/LRA.2020.3036597.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"1512_CR14","doi-asserted-by":"publisher","unstructured":"J. P. Xiao, P. Pisutsin, M. Feroskhan. Collaborative target search with a visual drone swarm: An adaptive curriculum embedded multistage reinforcement learning approach. IEEE Transactions on Neural Networks and Learning Systems, to be published. DOI: https:\/\/doi.org\/10.1109\/TNNLS.2023.3331370.","DOI":"10.1109\/TNNLS.2023.3331370"},{"issue":"9","key":"1512_CR15","doi-asserted-by":"publisher","first-page":"3826","DOI":"10.1109\/TCYB.2020.2977374","volume":"50","author":"T T Nguyen","year":"2020","unstructured":"T. T. Nguyen, N. D. Nguyen, S. Nahavandi. Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications. IEEE Transactions on Cybernetics, vol. 50, no. 9, pp. 3826\u20133839, 2020. DOI: https:\/\/doi.org\/10.1109\/TCYB.2020.2977374.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"1512_CR16","doi-asserted-by":"publisher","unstructured":"Y. L. Song, A. Romero, M. M\u00fcller, V. Koltun, D. Scaramuzza. Reaching the limit in autonomous racing: Optimal control versus reinforcement learning. Science Robotics, vol. 8, no. 82, Article number eadg1462, 2023. DOI: https:\/\/doi.org\/10.1126\/scirobotics.adg1462.","DOI":"10.1126\/scirobotics.adg1462"},{"key":"1512_CR17","doi-asserted-by":"publisher","unstructured":"M. O\u2019Connell, G. Y. Shi, X. C. Shi, K. Azizzadenesheli, A. Anandkumar, Y. S. Yue, S. J. Chung. Neural-fly enables rapid learning for agile flight in strong winds. Science Robotics, vol. 7, no. 66, Article number eabm6597, 2022. DOI: https:\/\/doi.org\/10.1126\/scirobotics.abm6597.","DOI":"10.1126\/scirobotics.abm6597"},{"key":"1512_CR18","volume-title":"Proximal policy optimization algorithms","author":"J Schulman","year":"2017","unstructured":"J. Schulman, F. Wolski, P. Dhariwal, A. Radford, O. Klimov. Proximal policy optimization algorithms, [Online], Available: https:\/\/arxiv.org\/abs\/1707.06347, 2017."},{"issue":"1","key":"1512_CR19","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s11768-019-8148-z","volume":"17","author":"Y L Ding","year":"2019","unstructured":"Y. L. Ding, B. Xin, J. Chen. Precedence-constrained path planning of messenger uav for air-ground coordination. Control Theory and Technology, vol. 17, no. 1, pp. 13\u201323, 2019. DOI: https:\/\/doi.org\/10.1007\/s11768-019-8148-z.","journal-title":"Control Theory and Technology"},{"key":"1512_CR20","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1109\/CYBER.2018.8688331","volume-title":"Proceedings of the 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems","author":"S Y Zhang","year":"2018","unstructured":"S. Y. Zhang, H. P. Wang, S. B. He, C. Zhang, J. T. Liu. An autonomous air-ground cooperative field surveillance system with quadrotor UAV and unmanned ATV robots. In Proceedings of the 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, Tianjin, China, pp. 1527\u20131532, 2018. DOI: https:\/\/doi.org\/10.1109\/CYBER.2018.8688331."},{"key":"1512_CR21","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/SSRR.2017.8088168","volume-title":"Proceedings of the IEEE International Symposium on Safety, Security and Rescue Robotics","author":"C S Shen","year":"2017","unstructured":"C. S. Shen, Y. Z. Zhang, Z. M. Li, F. Gao, S. J. Shen. Collaborative air-ground target searching in complex environments. In Proceedings of the IEEE International Symposium on Safety, Security and Rescue Robotics, Shanghai, China, pp. 230\u2013237, 2017. DOI: https:\/\/doi.org\/10.1109\/SSRR.2017.8088168."},{"key":"1512_CR22","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2014.7017662","volume-title":"Proceedings of the International Symposium on Safety, Security, and Rescue Robotics","author":"E Mueggler","year":"2014","unstructured":"E. Mueggler, M. Faessler, F. Fontana, D. Scaramuzza. Aerial-guided navigation of a ground robot among movable obstacles. In Proceedings of the International Symposium on Safety, Security, and Rescue Robotics, Hokkaido, Japan, 2014. DOI: https:\/\/doi.org\/10.1109\/SSRR.2014.7017662."},{"key":"1512_CR23","volume-title":"Vision-based learning for drones: A survey","author":"J P Xiao","year":"2023","unstructured":"J. P. Xiao, R. Y. Zhang, Y. H. Zhang, M. Feroskhan. Vision-based learning for drones: A survey, [Online], Available: https:\/\/arxiv.org\/abs\/2312.05019, 2023."},{"key":"1512_CR24","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/CAI54212.2023.00012","volume-title":"Proceedings of the Conference on Artificial Intelligence","author":"J P Xiao","year":"2023","unstructured":"J. P. Xiao, Y. X. M. Tan, X. L. Zhou, M. Feroskhan. Learning collaborative multi-target search for a visual drone swarm. In Proceedings of the Conference on Artificial Intelligence, Santa Clara, USA, pp. 5\u20137, 2023. DOI: https:\/\/doi.org\/10.1109\/CAI54212.2023.00012."},{"key":"1512_CR25","doi-asserted-by":"publisher","first-page":"14124","DOI":"10.1109\/ACCESS.2018.2889304","volume":"7","author":"M G Li","year":"2019","unstructured":"M. G. Li, H. Zhu, S. Z. You, L. Wang, C. Q. Tang. Efficient laser-based 3D SLAM for coal mine rescue robots. IEEE Access, vol. 7, pp. 14124\u201314138, 2019. DOI: https:\/\/doi.org\/10.1109\/ACCESS.2018.2889304.","journal-title":"IEEE Access"},{"issue":"5","key":"1512_CR26","doi-asserted-by":"publisher","first-page":"2101","DOI":"10.1109\/TITS.2014.2308977","volume":"15","author":"A Cherubini","year":"2014","unstructured":"A. Cherubini, F. Spindler, F. Chaumette. Autonomous visual navigation and laser-based moving obstacle avoidance. IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 5, pp. 2101\u20132110, 2014. DOI: https:\/\/doi.org\/10.1109\/TITS.2014.2308977.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"5","key":"1512_CR27","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/s11633-021-1304-1","volume":"18","author":"X Y Shao","year":"2021","unstructured":"X. Y. Shao, G. H. Tian, Y. Zhang. A 2D mapping method based on virtual laser scans for indoor robots. International Journal of Automation and Computing, vol. 18, no. 5, pp. 747\u2013765, 2021. DOI: https:\/\/doi.org\/10.1007\/s11633-021-1304-1.","journal-title":"International Journal of Automation and Computing"},{"key":"1512_CR28","doi-asserted-by":"publisher","first-page":"3357","DOI":"10.1109\/ICRA.2017.7989381","volume-title":"Proceedings of the International Conference on Robotics and Automation","author":"Y K Zhu","year":"2017","unstructured":"Y. K. Zhu, R. Mottaghi, E. Kolve, J. J. Lim, A. Gupta, L. Fei-Fei, A. Farhadi. Target-driven visual navigation in indoor scenes using deep reinforcement learning. In Proceedings of the International Conference on Robotics and Automation, Singapore, pp. 3357\u20133364, 2017. DOI: https:\/\/doi.org\/10.1109\/ICRA.2017.7989381."},{"key":"1512_CR29","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/IROS.2017.8202134","volume-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"L Tai","year":"2017","unstructured":"L. Tai, G. Paolo, M. Liu. Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation. In Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, Vancouver, Canada, pp. 31\u201336, 2017. DOI: https:\/\/doi.org\/10.1109\/IROS.2017.8202134."},{"key":"1512_CR30","doi-asserted-by":"publisher","first-page":"10688","DOI":"10.1109\/ICRA40945.2020.9196739","volume-title":"Proceedings of the International Conference on Robotics and Automation","author":"E Marchesini","year":"2020","unstructured":"E. Marchesini, A. Farinelli. Discrete deep reinforcement learning for mapless navigation. In Proceedings of the International Conference on Robotics and Automation, Paris, France, pp. 10688\u201310694, 2020. DOI: https:\/\/doi.org\/10.1109\/ICRA40945.2020.9196739."},{"key":"1512_CR31","volume-title":"Unity: A general platform for intelligent agents","author":"A Juliani","year":"2020","unstructured":"A. Juliani, V. P. Berges, E. Teng, A. Cohen, J. Harper, C. Elion, C. Goy, Y. Gao, H. Henry, M. Mattar, D. Lange. Unity: A general platform for intelligent agents, [Online], Available: https:\/\/arxiv.org\/abs\/1809.02627, 2020."},{"key":"1512_CR32","first-page":"1008","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"V R Konda","year":"1999","unstructured":"V. R. Konda, J. N. Tsitsiklis. Actor-critic algorithms. In Proceedings of the Advances in Neural Information Processing Systems, Denver, USA, pp. 1008\u20131014, 1999."},{"issue":"5","key":"1512_CR33","doi-asserted-by":"publisher","first-page":"674","DOI":"10.26599\/TST.2021.9010012","volume":"26","author":"K Zhu","year":"2021","unstructured":"K. Zhu, T. Zhang. Deep reinforcement learning based mobile robot navigation: A review. Tsinghua Science and Technology, vol. 26, no. 5, pp. 674\u2013691, 2021. DOI: https:\/\/doi.org\/10.26599\/TST.2021.9010012.","journal-title":"Tsinghua Science and Technology"},{"key":"1512_CR34","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Y Burda","year":"2019","unstructured":"Y. Burda, H. Edwards, D. Pathak, A. J. Storkey, T. Darrell, A. A. Efros. Large-scale study of curiosity-driven learning. In Proceedings of the 7th International Conference on Learning Representations, New Orleans, USA, 2019."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-024-1512-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-024-1512-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-024-1512-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T04:21:53Z","timestamp":1737692513000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-024-1512-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,24]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["1512"],"URL":"https:\/\/doi.org\/10.1007\/s11633-024-1512-6","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,24]]},"assertion":[{"value":"3 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declared that they have no conflicts of interest to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations of conflict of interest"}}]}}