{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:48:24Z","timestamp":1768520904711,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":16,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819607945","type":"print"},{"value":"9789819607952","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0795-2_12","type":"book-chapter","created":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T06:46:54Z","timestamp":1737614814000},"page":"154-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Real-Time Obstacle Avoidance and\u00a0Pathfinding for\u00a0Robot Manipulators Based on\u00a0Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3291-222X","authenticated-orcid":false,"given":"Jun","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8979-2646","authenticated-orcid":false,"given":"Jianliang","family":"Mao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8873-2772","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6052-1682","authenticated-orcid":false,"given":"Chuanlin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,24]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","unstructured":"Wang, B., Dong, J.: A visual servo reinforcement learning control of uncalibrated manipulators with multi-channel gain decision. IEEE Trans. Inst. Meas. Control (2024). https:\/\/doi.org\/10.1177\/01423312241239716","DOI":"10.1177\/01423312241239716"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Zhu, T., Mao, J., Han, L., Zhang, C., Yang, J.: Real-time dynamic obstacle avoidance for robot manipulators based on cascaded nonlinear MPC with artificial potential field. IEEE Trans. Ind. Electron. 71, 7424\u20137434 (2024)","DOI":"10.1109\/TIE.2023.3306405"},{"key":"12_CR3","doi-asserted-by":"publisher","first-page":"11104","DOI":"10.1109\/TIE.2023.3331098","volume":"71","author":"L Han","year":"2023","unstructured":"Han, L., Mao, J., Zhang, C., Kay, R.W., Richardson, R.C., Zhou, C.: A systematic trajectory tracking framework for robot manipulators: an observer-based nonsmooth control approach. IEEE Trans. Ind. Electron. 71, 11104\u201311114 (2023)","journal-title":"IEEE Trans. Ind. Electron."},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Pan, Y., Xia, F., Mao, J.: A robot manipulator grasping method based on improved YOLOX. In: 2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT), pp. 1279\u20131283. Shanghai, China (2022)","DOI":"10.1109\/CEECT55960.2022.10030260"},{"key":"12_CR5","doi-asserted-by":"publisher","first-page":"1749","DOI":"10.1109\/TRO.2022.3232542","volume":"39","author":"C Dawson","year":"2023","unstructured":"Dawson, C., Gao, S., Fan, C.: Safe control with learned certificates: a survey of neural lyapunov, barrier, and contraction methods for robotics and control. IEEE Trans. Robot. 39, 1749\u20131767 (2023)","journal-title":"IEEE Trans. Robot."},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Zhao, W., Queralta, J.P., Westerlund, T.: Sim-to-real transfer in deep reinforcement learning for robotics: a survey. In: 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 737\u2013744. IEEE (2020)","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"12_CR7","doi-asserted-by":"publisher","first-page":"2529","DOI":"10.1109\/TRO.2024.3387010","volume":"40","author":"S Safaoui","year":"2024","unstructured":"Safaoui, S., Vinod, A.P., Chakrabarty, A., Quirynen, R., Yoshikawa, N., Di Cairano, S.: Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning. IEEE Trans. Robot. 40, 2529\u20132542 (2024)","journal-title":"IEEE Trans. Robot."},{"key":"12_CR8","unstructured":"Gu, S., Holly, E., Lillicrap, T.P., Levine, S.: Deep reinforcement learning for robotic manipulation. arXiv preprint arXiv:1610.006331, 1 (2016)"},{"key":"12_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2021.102630","volume":"78","author":"A Yang","year":"2021","unstructured":"Yang, A., Chen, Y., Naeem, W., Fei, M., Chen, L.: Humanoid motion planning of robotic arm based on human arm action feature and reinforcement learning. Mechatronics 78, 102630 (2021)","journal-title":"Mechatronics"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Mehta, S.A., Habibian, S., Losey, D.P.: Waypoint-based reinforcement learning for robot manipulation tasks. arXiv preprint arXiv:2403.13281 (2024)","DOI":"10.1109\/IROS58592.2024.10802681"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Schoettler, G., et al.: Deep reinforcement learning for industrial insertion tasks with visual inputs and natural rewards. In: RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5548\u20135555. Las Vegas, USA (2020)","DOI":"10.1109\/IROS45743.2020.9341714"},{"key":"12_CR12","unstructured":"Haarnoja, T., Tang, H., Abbeel, P., Levine, S.: Reinforcement learning with deep energy-based policies. In: International Conference on Machine Learning, pp. 1352\u20131361. Singapore, Singapore (2017)"},{"issue":"2","key":"12_CR13","volume":"2023","author":"M Ataollahi","year":"2023","unstructured":"Ataollahi, M., Farrokhi, M.: Online path planning of cooperative mobile robots in unknown environments using improved q-learning and adaptive artificial potential field. J. Eng. 2023(2), e12231 (2023)","journal-title":"J. Eng."},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Li, J., Shi, H., Hwang, K.S.: Using goal-conditioned reinforcement learning with deep imitation to control robot arm in flexible flat cable assembly task. IEEE Trans. Autom. Sci. Eng. 21, 1\u201312 (2023)","DOI":"10.1109\/TASE.2023.3323307"},{"issue":"2","key":"12_CR15","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1109\/TRO.2022.3226108","volume":"39","author":"Z Hu","year":"2023","unstructured":"Hu, Z., Zheng, Y., Pan, J.: Grasping living objects with adversarial behaviors using inverse reinforcement learning. IEEE Trans. Rob. 39(2), 1151\u20131163 (2023)","journal-title":"IEEE Trans. Rob."},{"key":"12_CR16","unstructured":"Haarnoja, T., et\u00a0al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0795-2_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T06:47:06Z","timestamp":1737614826000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0795-2_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819607945","9789819607952"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0795-2_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xi'an","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icira2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}