{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T11:48:32Z","timestamp":1782215312659,"version":"3.54.5"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032123848","type":"print"},{"value":"9783032123855","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-12385-5_6","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:11:06Z","timestamp":1767319866000},"page":"85-99","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Rapid Robotic Arm Path Planning Through Deep Reinforcement Learning with Human Demonstration Key Points"],"prefix":"10.1007","author":[{"given":"Lin","family":"Wan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaonan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deyu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwei","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyang","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Liu, W., Niu, H., Mahyuddin, M.N., et al.: A model-free deep reinforcement learning approach for robotic manipulators path planning. In: 2021 21st International Conference on Control, Automation and Systems (ICCAS), pp. 512\u2013517. IEEE (2021)","DOI":"10.23919\/ICCAS52745.2021.9649802"},{"issue":"9","key":"6_CR2","doi-asserted-by":"publisher","first-page":"3826","DOI":"10.1109\/TCYB.2020.2977374","volume":"50","author":"TT Nguyen","year":"2020","unstructured":"Nguyen, T.T., Nguyen, N.D., Nahavandi, S.: Deep reinforcement learning for multiagent systems: a review of challenges, solutions, and applications. IEEE Trans. Cybernet. 50(9), 3826\u20133839 (2020)","journal-title":"IEEE Trans. Cybernet."},{"key":"6_CR3","unstructured":"Schrijver, A.: Combinatorial Optimization: Polyhedra and Efficiency, vol. 24. Springer, Heidelberg (2003)"},{"key":"6_CR4","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1109\/TSSC.1968.300136","volume":"4","author":"PE Hart","year":"1968","unstructured":"Hart, P.E., Nilsson, N.J., Raphael, B.: A formal basis for the heuristic determination of minimum cost paths. IEEE Trans. Syst. Sci. Cybern. 4, 100\u2013107 (1968)","journal-title":"IEEE Trans. Syst. Sci. Cybern."},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Tang, X., Zhou, H., Xu, T.: Obstacle avoidance path planning of 6-DOF robotic arm based on improved A* algorithm and artificial potential field method. Robotica 42(2), 457\u2013481 (2024)","DOI":"10.1017\/S0263574723001546"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, X., Zhou, J., Zhou, Z., Zhao, X., Gao, J., Qiao, T.: An improved RRT-Connect path planning algorithm of robotic arm for automatic sampling of exhaust emission detection in Industry 4.0. J. Ind. Inf. Integr. 33, 100436 (2023)","DOI":"10.1016\/j.jii.2023.100436"},{"key":"6_CR7","unstructured":"\u5468\u76ca\u90a6\uff0c\u7ae0\u5170\u73e0\uff0c\u5f90\u6d77\u94ed.\u57fa\u4e8e\u6539\u8fdb\u53cc\u5411RRT*\u7b97\u6cd5\u7684\u673a\u68b0\u81c2\u8def\u5f84\u89c4\u5212. \u8ba1\u7b97\u673a\u5e94\u7528 42(201), 342\u2013346 (2022)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Zhong, J., Wang, T., Cheng, L.: Collision-free path planning for welding manipulator via hybrid algorithm of deep reinforcement learning and inverse kinematics. Complex Intell. Syst. 8(3), 1899\u20131912 (2022)","DOI":"10.1007\/s40747-021-00366-1"},{"issue":"13","key":"6_CR9","doi-asserted-by":"publisher","first-page":"5974","DOI":"10.3390\/s23135974","volume":"23","author":"S Zhang","year":"2023","unstructured":"Zhang, S., Xia, Q., Chen, M., et al.: Multi-objective optimal trajectory planning for robotic arms using deep reinforcement learning. Sensors 23(13), 5974 (2023)","journal-title":"Sensors"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Zhou, D., Jia, R., Yao, H., et al.: Robotic arm motion planning based on residual reinforcement learning. In: 2021 13th International Conference on Computer and Automation Engineering (ICCAE), pp. 89\u201394. IEEE (2021)","DOI":"10.1109\/ICCAE51876.2021.9426160"},{"key":"6_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2019.105657","volume":"98","author":"YH Wu","year":"2020","unstructured":"Wu, Y.H., Yu, Z.C., Li, C.Y., et al.: Reinforcement learning in dual-arm trajectory planning for a free-floating space robot. Aerosp. Sci. Technol. 98, 105657 (2020)","journal-title":"Aerosp. Sci. Technol."},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Bhuiyan, T., K\u00e4stner, L., Hu, Y., et al.: Deep-reinforcement-learning-based path planning for industrial robots using distance sensors as observation. In: 2023 8th International Conference on Control and Robotics Engineering (ICCRE), pp. 204\u2013210. IEEE (2023)","DOI":"10.1109\/ICCRE57112.2023.10155608"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Liu, W., Niu, H., Mahyuddin, M.N., Herrmann, G., Carrasco, J.: A model-free deep reinforcement learning approach for robotic manipulators path planning. In: 2021 21st International Conference on Control, Automation and Systems (ICCAS), Jeju, Korea, Republic of, pp. 512\u2013517 (2021)","DOI":"10.23919\/ICCAS52745.2021.9649802"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Tang, W., et al.: Dual-arm robot trajectory planning based on deep reinforcement learning under complex environment. Micromachines 13(4), 564 (2022)","DOI":"10.3390\/mi13040564"},{"key":"6_CR15","unstructured":"Wang, Y., Wang, Y.-H., Yin, Z.-Z., Wan, P.: Path planning of manipulator based on deep reinforcement learning and screw method. Kongzhi Lilun Yu Yingyong\/Control Theory Appl. 40(3), 516\u2013524 (2023)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Prianto, E., Park, J.-H., Bae, J.-H., Kim, J.-S.: Deep reinforcement learning-based path planning for multi-arm manipulators with periodically moving obstacles. Appl. Sci. 11(2587), 2587 (2021)","DOI":"10.3390\/app11062587"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Park, K.-W., Kim, M., Kim, J.-S., Park, J.-H.: Path planning for multi-arm manipulators using soft actor-critic algorithm with position prediction of moving obstacles via LSTM. Appl. Sci. 12(9837), 9837 (2022)","DOI":"10.3390\/app12199837"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Chen, P., Pei, J., Lu, W., Li, M.: A deep reinforcement learning based method for real-time path planning and dynamic obstacle avoidance. Neurocomputing 497, 64\u201375(2022)","DOI":"10.1016\/j.neucom.2022.05.006"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Q., Jiang, Z., Liu, H.: Robot learning from demonstration for path planning: a review. Sci. China (Technol. Sci.) 63, 1325\u20131334 (2020)","DOI":"10.1007\/s11431-020-1648-4"},{"key":"6_CR20","unstructured":"Vecerik, M., Hester, T., Scholz, J., et al.: Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards. arXiv preprint arXiv:1707.08817 (2017)"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Hester, T., Vecerik, M., Pietquin, O., et al.: Deep q-learning from demonstrations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Nair, A., McGrew, B., Andrychowicz, M., et al.: Overcoming exploration in reinforcement learning with demonstrations. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6292\u20136299. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"6_CR23","unstructured":"\u5b8b\u7d2b\u9633\uff0c\u674e\u519b\u6000\uff0c\u738b\u6000\u519b\uff0c\u82cf\u946b\uff0c\u4e8e\u857e.\u57fa\u4e8e\u8def\u5f84\u6a21\u4eff\u548cSAC\u5f3a\u5316\u5b66\u4e60\u7684\u673a\u68b0\u81c2\u8def\u5f84\u89c4\u5212\u7b97\u6cd5. \u8ba1\u7b97\u673a\u5e94\u7528 44(2), 439\u2013444 (2024)"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Zang, Y., Wang, P., Zha, F., Guo, W., Li, C., Sun, L.: Human skill knowledge guided global trajectory policy reinforcement learning method. Front. Neurorobot. 18, 1368243 (2024)","DOI":"10.3389\/fnbot.2024.1368243"},{"key":"6_CR25","doi-asserted-by":"publisher","unstructured":"\u5218\u884c,\u9ec4\u5ead\u5b89,\u8463\u4e91\u9f99,\u7b49.\u57fa\u4e8e\u793a\u6559\u878d\u5408\u7684\u6df1\u5ea6\u5f3a\u5316\u5b66\u4e60\u673a\u5668\u4eba\u5316\u9f7f\u8f6e\u88c5\u914d\u7b97\u6cd5. \u63a7\u5236\u5de5\u7a0b 30(07), 1308\u20131316 (2023). https:\/\/doi.org\/10.14107\/j.cnki.kzgc.20220894","DOI":"10.14107\/j.cnki.kzgc.20220894"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Lu, W., Chen, L., Wang, Y., et al.: Demonstration data-driven parameter adjustment for trajectory planning in highly constrained environments. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3495454"},{"issue":"4","key":"6_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530103","volume":"41","author":"X Wei","year":"2022","unstructured":"Wei, X., Liu, M., Ling, Z., et al.: Approximate convex decomposition for 3D meshes with collision-aware concavity and tree search. ACM Trans. Graph. (TOG) 41(4), 1\u201318 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"6_CR28","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)"},{"key":"6_CR29","unstructured":"Sola, J.: Quaternion kinematics for the error-state Kalman filter. arXiv preprint arXiv:1711.02508 (2017)"},{"key":"6_CR30","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., et al.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"}],"container-title":["Lecture Notes in Computer Science","HCI International 2025 \u2013 Late Breaking Papers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-12385-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T10:58:06Z","timestamp":1782212286000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-12385-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032123848","9783032123855"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-12385-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gothenburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}