{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T02:16:40Z","timestamp":1783995400438,"version":"3.55.0"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"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":["Cluster Comput"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s10586-025-05522-7","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T19:44:45Z","timestamp":1757965485000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A reward shaping approach used for end-to-end mapless navigation using deep reinforcement learning algorithm"],"prefix":"10.1007","volume":"28","author":[{"given":"Anu","family":"Priya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ritu","family":"Tiwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pooja","family":"Agrawal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sushant","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,15]]},"reference":[{"issue":"5","key":"5522_CR1","doi-asserted-by":"publisher","first-page":"674","DOI":"10.26599\/TST.2021.9010012","volume":"26","author":"Kai Zhu","year":"2021","unstructured":"Zhu, Kai, Zhang, Tao: Deep reinforcement learning based mobile robot navigation: A review. Tsinghua Science and Technology 26(5), 674\u2013691 (2021)","journal-title":"Tsinghua Science and Technology"},{"key":"5522_CR2","unstructured":"Zeng, Taiping: Learning continuous control through proximal policy optimization for mobile robot navigation. In 2018 International Conference on Future Technology and Disruptive Innovation, (2018)"},{"key":"5522_CR3","doi-asserted-by":"crossref","unstructured":"Kakoty, Nayan M., Mazumdar, Mridusmita, Sonowal, Durlav: Mobile robot navigation in unknown dynamic environment inspired by human pedestrian behavior. In Progress in Advanced Computing and Intelligent Engineering: Proceedings of ICACIE 2017, Volume 2, pages 441\u2013451. Springer, (2019)","DOI":"10.1007\/978-981-13-0224-4_40"},{"issue":"3","key":"5522_CR4","doi-asserted-by":"publisher","first-page":"172988142092167","DOI":"10.1177\/1729881420921672","volume":"17","author":"Hao Quan","year":"2020","unstructured":"Quan, Hao, Li, Yansheng, Zhang, Yi.: A novel mobile robot navigation method based on deep reinforcement learning. International Journal of Advanced Robotic Systems 17(3), 1729881420921672 (2020)","journal-title":"International Journal of Advanced Robotic Systems"},{"issue":"6","key":"5522_CR5","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1007\/s12065-023-00829-z","volume":"16","author":"Niloofar Rezaei","year":"2023","unstructured":"Rezaei, Niloofar, Darabi, Samira: Mobile robot monocular vision-based obstacle avoidance algorithm using a deep neural network. Evolutionary Intelligence 16(6), 1999\u20132014 (2023)","journal-title":"Evolutionary Intelligence"},{"issue":"1","key":"5522_CR6","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1080\/10095020.2017.1420509","volume":"21","author":"Lu Yuncheng","year":"2018","unstructured":"Yuncheng, Lu., Xue, Zhucun, Xia, Gui-Song., Zhang, Liangpei: A survey on vision-based uav navigation. Geo-spatial information science 21(1), 21\u201332 (2018)","journal-title":"Geo-spatial information science"},{"key":"5522_CR7","doi-asserted-by":"crossref","unstructured":"Cimurs, Reinis, Hwang, Jaepyung, Suh, Il Hong: Bezier curve-based smoothing for path planner with curvature constraint. In 2017 First IEEE International Conference on Robotic Computing (IRC), pages 241\u2013248, (2017)","DOI":"10.1109\/IRC.2017.13"},{"issue":"3","key":"5522_CR8","doi-asserted-by":"publisher","first-page":"3467","DOI":"10.1109\/JSYST.2018.2875789","volume":"13","author":"Radhe Shyam Sharma","year":"2018","unstructured":"Sharma, Radhe Shyam, Nair, Ranjith Ravindranathan, Agrawal, Pooja, Behera, Laxmidhar, Subramanian, Venkatesh K.: Robust hybrid visual servoing using reinforcement learning and finite-time adaptive fosmc. IEEE Systems Journal 13(3), 3467\u20133478 (2018)","journal-title":"IEEE Systems Journal"},{"key":"5522_CR9","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/234747","volume":"5","author":"Mehmet Serdar G\u00fczel","year":"2013","unstructured":"Mehmet Serdar G\u00fczel: Autonomous vehicle navigation using vision and mapless strategies: a survey. Advances in Mechanical Engineering 5, 234747 (2013)","journal-title":"Advances in Mechanical Engineering"},{"key":"5522_CR10","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.ast.2017.05.012","volume":"68","author":"Pooja Agrawal","year":"2017","unstructured":"Agrawal, Pooja, Ratnoo, Ashwini, Ghose, Debasish: Inverse optical flow based guidance for uav navigation through urban canyons. Aerospace Science and Technology 68, 163\u2013178 (2017)","journal-title":"Aerospace Science and Technology"},{"issue":"2","key":"5522_CR11","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1068\/p080125","volume":"8","author":"Brian Rogers","year":"1979","unstructured":"Rogers, Brian, Graham, Maureen: Motion parallax as an independent cue for depth perception. Perception 8(2), 125\u2013134 (1979)","journal-title":"Perception"},{"key":"5522_CR12","doi-asserted-by":"crossref","unstructured":"Li, Zhenyu, Wang, Xuyang, Liu, Xianming, Jiang, Junjun: Binsformer: Revisiting adaptive bins for monocular depth estimation. IEEE Transactions on Image Processing, (2024)","DOI":"10.1109\/TIP.2024.3416065"},{"key":"5522_CR13","doi-asserted-by":"crossref","unstructured":"Prasuna, Rayadurga Gnana, Potturu, Sudharsana Rao: Deep reinforcement learning in mobile robotics\u2013a concise review. Multimedia Tools and Applications, pages 1\u201322, (2024)","DOI":"10.1007\/s11042-024-18152-9"},{"key":"5522_CR14","doi-asserted-by":"crossref","unstructured":"Hsu, Shih-Hsi, Chan, Shao-Hung, Wu, Ping-Tsang, Xiao, Kun, Fu, Li-Chen: Distributed deep reinforcement learning based indoor visual navigation. In 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2532\u20132537. IEEE, (2018)","DOI":"10.1109\/IROS.2018.8594352"},{"key":"5522_CR15","volume-title":"Reinforcement learning: An introduction","author":"Richard S Sutton","year":"2018","unstructured":"Sutton, Richard S., Barto, Andrew G.: Reinforcement learning: An introduction. MIT press (2018)"},{"issue":"7839","key":"5522_CR16","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"Julian Schrittwieser","year":"2020","unstructured":"Schrittwieser, Julian, Antonoglou, Ioannis, Hubert, Thomas, Simonyan, Karen, Sifre, Laurent, Schmitt, Simon, Guez, Arthur, Lockhart, Edward, Hassabis, Demis, Graepel, Thore, et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"key":"5522_CR17","first-page":"836","volume":"9","author":"Prashant Pandey","year":"2018","unstructured":"Pandey, Prashant, Shukla, Anupam, Tiwari, Ritu: Three-dimensional path planning for unmanned aerial vehicles using glowworm swarm optimization algorithm. International Journal of System Assurance Engineering and Management 9, 836\u2013852 (2018)","journal-title":"International Journal of System Assurance Engineering and Management"},{"key":"5522_CR18","doi-asserted-by":"crossref","unstructured":"Michels, Jeff, Saxena, Ashutosh, Ng, Andrew Y.: High speed obstacle avoidance using monocular vision and reinforcement learning. In Proceedings of the 22nd international conference on Machine learning, pages 593\u2013600, (2005)","DOI":"10.1145\/1102351.1102426"},{"issue":"7540","key":"5522_CR19","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"Volodymyr Mnih","year":"2015","unstructured":"Mnih, Volodymyr, Kavukcuoglu, Koray, Silver, David, Rusu, Andrei A., Veness, Joel, Bellemare, Marc G., Graves, Alex, Riedmiller, Martin, Fidjeland, Andreas K., Ostrovski, Georg, et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"5522_CR20","unstructured":"Mirowski, Piotr, Pascanu, Razvan, Viola, Fabio, Soyer, Hubert, Ballard, Andrew J., Banino, Andrea, Denil, Misha, Goroshin, Ross, Sifre, Laurent, Kavukcuoglu, Koray et al.: Learning to navigate in complex environments. (2016). arXiv preprint arXiv:1611.03673"},{"key":"5522_CR21","doi-asserted-by":"crossref","unstructured":"Tai, Lei, Paolo, Giuseppe, Liu, Ming: Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation. In 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pages 31\u201336. IEEE, (2017)","DOI":"10.1109\/IROS.2017.8202134"},{"key":"5522_CR22","doi-asserted-by":"crossref","unstructured":"Tai, Lei, Liu, Ming: Towards cognitive exploration through deep reinforcement learning for mobile robots. (2016). arXiv preprint arXiv:1610.01733","DOI":"10.1186\/s40638-016-0055-x"},{"key":"5522_CR23","doi-asserted-by":"crossref","unstructured":"Gandhi, Dhiraj, Pinto, Lerrel, Gupta, Abhinav: Learning to fly by crashing. In 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 3948\u20133955. IEEE, (2017)","DOI":"10.1109\/IROS.2017.8206247"},{"issue":"5","key":"5522_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3234150","volume":"51","author":"Samira Pouyanfar","year":"2018","unstructured":"Pouyanfar, Samira, Sadiq, Saad, Yan, Yilin, Tian, Haiman, Tao, Yudong, Reyes, Maria Presa, Shyu, Mei-Ling., Chen, Shu-Ching., Iyengar, Sundaraja S.: A survey on deep learning: Algorithms, techniques, and applications. ACM computing surveys (CSUR) 51(5), 1\u201336 (2018)","journal-title":"ACM computing surveys (CSUR)"},{"key":"5522_CR25","doi-asserted-by":"crossref","unstructured":"He, Kaiming, Zhang, Xiangyu, Ren, Shaoqing, Sun, Jian: Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770\u2013778, (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5522_CR26","unstructured":"Simonyan, Karen, Zisserman, Andrew: Very deep convolutional networks for large-scale image recognition. (2014). arXiv preprint arXiv:1409.1556"},{"key":"5522_CR27","doi-asserted-by":"crossref","unstructured":"Huang, Gao, Liu, Zhuang, Van Der Maaten, Laurens, Weinberger, Kilian Q.: Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700\u20134708, (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"5522_CR28","unstructured":"Xie, Linhai, Wang, Sen, Markham, Andrew, Trigoni, Niki: Towards monocular vision based obstacle avoidance through deep reinforcement learning. (2017). arXiv preprint arXiv:1706.09829"},{"key":"5522_CR29","doi-asserted-by":"crossref","unstructured":"Chaffre, Thomas, Moras, Julien, Chan-Hon-Tong, Adrien, Marzat Julien: Sim-to-real transfer with incremental environment complexity for reinforcement learning of depth-based robot navigation. (2020). arXiv preprint arXiv:2004.14684","DOI":"10.5220\/0009821603140323"},{"issue":"5","key":"5522_CR30","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/s11370-021-00398-z","volume":"14","author":"Eduardo F Morales","year":"2021","unstructured":"Morales, Eduardo F., Murrieta-Cid, Rafael, Becerra, Israel, Esquivel-Basaldua, Marco A.: A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning. Intelligent Service Robotics 14(5), 773\u2013805 (2021)","journal-title":"Intelligent Service Robotics"},{"key":"5522_CR31","doi-asserted-by":"crossref","unstructured":"Marchesini, Enrico, Farinelli, Alessandro: Discrete deep reinforcement learning for mapless navigation. In 2020 IEEE International Conference on Robotics and Automation (ICRA), pages 10688\u201310694. IEEE, (2020)","DOI":"10.1109\/ICRA40945.2020.9196739"},{"key":"5522_CR32","unstructured":"Laud, Adam, DeJong, Gerald: The influence of reward on the speed of reinforcement learning: An analysis of shaping. In Proceedings of the 20th International Conference on Machine Learning (ICML-03), pages 440\u2013447, (2003)"},{"key":"5522_CR33","doi-asserted-by":"crossref","unstructured":"Pathak, Deepak, Agrawal, Pulkit, Efros, Alexei A., Darrell, Trevor: Curiosity-driven exploration by self-supervised prediction. In International conference on machine learning, pages 2778\u20132787. PMLR, (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"issue":"2","key":"5522_CR34","first-page":"249","volume":"13","author":"Wu Keyu","year":"2019","unstructured":"Keyu, Wu., Wang, Han, Esfahani, Mahdi Abolfazli, Yuan, Shenghai: Bnd*-ddqn: Learn to steer autonomously through deep reinforcement learning. IEEE Transactions on Cognitive and Developmental Systems 13(2), 249\u2013261 (2019)","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"5522_CR35","unstructured":"Botteghi, Nicol\u00f2, Sirmacek, Beril, Mustafa, Khaled A.A., Poel, Mannes, Stramigioli, Stefano: On reward shaping for mobile robot navigation: A reinforcement learning and slam based approach. (2020). arXiv preprint arXiv:2002.04109"},{"key":"5522_CR36","unstructured":"Van Seijen, Harm, Fatemi, Mehdi, Romoff, Joshua, Laroche, Romain, Barnes, Tavian, Tsang, Jeffrey: Hybrid reward architecture for reinforcement learning. Advances in Neural Information Processing Systems, 30, (2017)"},{"key":"5522_CR37","doi-asserted-by":"crossref","unstructured":"Ibrahim, Sinan, Mostafa, Mostafa, Jnadi, Ali, Salloum, Hadi, Osinenko, Pavel: Comprehensive overview of reward engineering and shaping in advancing reinforcement learning applications. IEEE Access, (2024)","DOI":"10.1109\/ACCESS.2024.3504735"},{"key":"5522_CR38","doi-asserted-by":"crossref","unstructured":"Laina, Iro, Rupprecht, Christian, Belagiannis, Vasileios, Tombari, Federico, Navab, Nassir: Deeper depth prediction with fully convolutional residual networks. In 2016 Fourth international conference on 3D vision (3DV), pages 239\u2013248. IEEE, (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"5522_CR39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s42452-020-03978-3","volume":"3","author":"Xu Huihui","year":"2021","unstructured":"Huihui, Xu., Liu, Nan: Detail-preserving depth estimation from a single image based on modified fully convolutional residual network and gradient network. SN Applied Sciences 3, 1\u201315 (2021)","journal-title":"SN Applied Sciences"},{"key":"5522_CR40","unstructured":"Mnih, Volodymyr, Kavukcuoglu, Koray, Silver, David, Graves, Alex, Antonoglou, Ioannis, Wierstra, Daan, Riedmiller, Martin: Playing atari with deep reinforcement learning. (2013). arXiv preprint arXiv:1312.5602"},{"key":"5522_CR41","doi-asserted-by":"crossref","unstructured":"Van Hasselt, Hado, Guez, Arthur, Silver, David: Deep reinforcement learning with double q-learning. In Proceedings of the AAAI conference on artificial intelligence, volume 30, (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"5522_CR42","unstructured":"Wang, Ziyu, Schaul, Tom, Hessel, Matteo, Hasselt, Hado, Lanctot, Marc, Freitas, Nando: Dueling network architectures for deep reinforcement learning. In International conference on machine learning, pages 1995\u20132003. PMLR, (2016)"},{"key":"5522_CR43","unstructured":"Xiao, Baicen: Reward Shaping in Single and Multi-Agent Deep Reinforcement Learning. University of Washington, (2021)"},{"key":"5522_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Daniel, Bailey, Colleen P.: Obstacle avoidance and navigation utilizing reinforcement learning with reward shaping. In Artificial intelligence and machine learning for multi-domain operations applications II, volume 11413, pages 500\u2013506. SPIE, (2020)","DOI":"10.1117\/12.2558212"},{"key":"5522_CR45","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s11370-017-0244-7","volume":"11","author":"Abdul Qadir Faridi","year":"2018","unstructured":"Faridi, Abdul Qadir, Sharma, Sanjeev, Shukla, Anupam, Tiwari, Ritu, Dhar, Joydip: Multi-robot multi-target dynamic path planning using artificial bee colony and evolutionary programming in unknown environment. Intelligent Service Robotics 11, 171\u2013186 (2018)","journal-title":"Intelligent Service Robotics"},{"key":"5522_CR46","doi-asserted-by":"crossref","unstructured":"Sharma, Sanjeev, Yadav, Mahendra Pratap: A collective approach to reach known and unknown target in multi agent environment using nature inspired algorithms. Cluster Computing, pages 1\u201324, (2024)","DOI":"10.1007\/s10586-024-04523-2"},{"key":"5522_CR47","doi-asserted-by":"publisher","first-page":"6973","DOI":"10.1109\/ACCESS.2023.3237025","volume":"11","author":"Peeyush Singhal","year":"2023","unstructured":"Singhal, Peeyush, Walambe, Rahee, Ramanna, Sheela, Kotecha, Ketan: Domain adaptation: challenges, methods, datasets, and applications. IEEE access 11, 6973\u20137020 (2023)","journal-title":"IEEE access"},{"key":"5522_CR48","doi-asserted-by":"crossref","unstructured":"Tobin, Josh, Fong, Rachel, Ray, Alex, Schneider, Jonas, Zaremba, Wojciech, Abbeel, Pieter: Domain randomization for transferring deep neural networks from simulation to the real world. In 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pages 23\u201330. IEEE, (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"issue":"10","key":"5522_CR49","doi-asserted-by":"publisher","first-page":"7978","DOI":"10.1109\/TNNLS.2022.3148435","volume":"34","author":"Zizhen Zhang","year":"2022","unstructured":"Zhang, Zizhen, Zhiyuan, Wu., Zhang, Hang, Wang, Jiahai: Meta-learning-based deep reinforcement learning for multiobjective optimization problems. IEEE Transactions on Neural Networks and Learning Systems 34(10), 7978\u20137991 (2022)","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05522-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-025-05522-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-025-05522-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T15:36:23Z","timestamp":1761924983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-025-05522-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":49,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["5522"],"URL":"https:\/\/doi.org\/10.1007\/s10586-025-05522-7","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,15]]},"assertion":[{"value":"19 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that no conflicts of interest are concerned.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"The authors declare that no animals or humans are harmed during this research.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}}],"article-number":"803"}}