{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T03:10:44Z","timestamp":1778037044537,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T00:00:00Z","timestamp":1766102400000},"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":["Intel Serv Robotics"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s11370-025-00673-3","type":"journal-article","created":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T04:14:10Z","timestamp":1766117650000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reward shaping of deep reinforcement learning algorithm for autonomous navigation in a structured environment"],"prefix":"10.1007","volume":"19","author":[{"given":"Anu","family":"Priya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ritu","family":"Tiwari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pooja","family":"Agrawal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sushant","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,19]]},"reference":[{"key":"673_CR1","doi-asserted-by":"crossref","unstructured":"Sivaranjani S, Nandesh Divya\u00a0A, Gayathri K, Ramanathan R, et\u00a0al (2021) An investigation of bug algorithms for mobile robot navigation and obstacle avoidance in two-dimensional unknown static environments. In: 2021 international conference on communication information and computing technology (ICCICT). IEEE, pp 1\u20136","DOI":"10.1109\/ICCICT50803.2021.9510118"},{"key":"673_CR2","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.ast.2017.05.012","volume":"68","author":"P Agrawal","year":"2017","unstructured":"Agrawal P, Ratnoo A, Ghose D (2017) Inverse optical flow based guidance for UAV navigation through urban canyons. Aerosp Sci Technol 68:163\u2013178","journal-title":"Aerosp Sci Technol"},{"key":"673_CR3","doi-asserted-by":"crossref","unstructured":"K\u00e4stner L, Zhao X, Buiyan T, Li J, Shen Z, Lambrecht J, Marx C (2021) Connecting deep-reinforcement-learning-based obstacle avoidance with conventional global planners using waypoint generators. In: 2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, pp 1213\u20131220","DOI":"10.1109\/IROS51168.2021.9636039"},{"issue":"6","key":"673_CR4","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","volume":"23","author":"B Ravi Kiran","year":"2021","unstructured":"Ravi Kiran B, Sobh I, Talpaert V, Mannion P, Al AA, Sallab SY, P\u00e9rez P (2021) Deep reinforcement learning for autonomous driving: a survey. IEEE Trans Intell Transp Syst 23(6):4909\u20134926","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"673_CR5","unstructured":"Botteghi N, Sirmacek B, Mustafa KA, Poel M, Stramigioli S (2020) On reward shaping for mobile robot navigation: a reinforcement learning and slam based approach. arXiv preprint arXiv:2002.04109"},{"key":"673_CR6","unstructured":"Sutton RS (2018) Reinforcement learning: an introduction. A Bradford Book"},{"key":"673_CR7","unstructured":"Van Seijen H, Fatemi M, Romoff J. et al (2017) Hybrid Reward Architecture for Reinforcement Learning. Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, 4\u20139 December 2017, 5393\u20135403."},{"key":"673_CR8","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.neucom.2020.02.008","volume":"393","author":"Y Dong","year":"2020","unstructured":"Dong Y, Tang X, Yuan Y (2020) Principled reward shaping for reinforcement learning via lyapunov stability theory. Neurocomputing 393:83\u201390","journal-title":"Neurocomputing"},{"key":"673_CR9","unstructured":"Jin C, Krishnamurthy A, Simchowitz M, Yu T (2020) Reward-free exploration for reinforcement learning. In: International conference on machine learning. PMLR, pp 4870\u20134879"},{"key":"673_CR10","doi-asserted-by":"crossref","unstructured":"Marchesini E, Farinelli A (2020) Discrete deep reinforcement learning for mapless navigation. In: 2020 IEEE international conference on robotics and automation (ICRA). IEEE, pp 10688\u201310694","DOI":"10.1109\/ICRA40945.2020.9196739"},{"issue":"28","key":"673_CR11","doi-asserted-by":"publisher","first-page":"70815","DOI":"10.1007\/s11042-024-18152-9","volume":"83","author":"RG Prasuna","year":"2024","unstructured":"Prasuna RG, Potturu SR (2024) Deep reinforcement learning in mobile robotics-a concise review. Multimedia Tools and Applications 83(28):70815\u201370836","journal-title":"Multimedia Tools and Applications"},{"issue":"1","key":"673_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):1\u201348","journal-title":"J Big Data"},{"key":"673_CR13","doi-asserted-by":"crossref","unstructured":"Tobin J, Fong R, Ray A, Schneider J, Zaremba W, Abbeel P (2017) 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). IEEE, pp 23\u201330","DOI":"10.1109\/IROS.2017.8202133"},{"key":"673_CR14","doi-asserted-by":"crossref","unstructured":"Peng XB, Andrychowicz M, Zaremba W, Abbeel P (2018) Sim-to-real transfer of robotic control with dynamics randomization. In: 2018 IEEE international conference on robotics and automation (ICRA). IEEE, pp 3803\u20133810","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"673_CR15","first-page":"7968","volume":"33","author":"K Wang","year":"2020","unstructured":"Wang K, Kang B, Shao J, Feng J (2020) Improving generalization in reinforcement learning with mixture regularization. Adv Neural Inf Process Syst 33:7968\u20137978","journal-title":"Adv Neural Inf Process Syst"},{"issue":"5","key":"673_CR16","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1007\/s11370-021-00398-z","volume":"14","author":"EF Morales","year":"2021","unstructured":"Morales EF, Murrieta-Cid R, Becerra I, Esquivel-Basaldua MA (2021) A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning. Intel Serv Robot 14(5):773\u2013805","journal-title":"Intel Serv Robot"},{"key":"673_CR17","unstructured":"Mnih V (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602"},{"issue":"6","key":"673_CR18","doi-asserted-by":"publisher","first-page":"1999","DOI":"10.1007\/s12065-023-00829-z","volume":"16","author":"N Rezaei","year":"2023","unstructured":"Rezaei N, Darabi S (2023) Mobile robot monocular vision-based obstacle avoidance algorithm using a deep neural network. Evol Intel 16(6):1999\u20132014","journal-title":"Evol Intel"},{"key":"673_CR19","doi-asserted-by":"crossref","unstructured":"Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI conference on artificial intelligence, vol\u00a030","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"673_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111503","volume":"158","author":"M G\u00f6k","year":"2024","unstructured":"G\u00f6k M (2024) Dynamic path planning via dueling double deep q-network (d3qn) with prioritized experience replay. Appl Soft Comput 158:111503","journal-title":"Appl Soft Comput"},{"issue":"8","key":"673_CR21","doi-asserted-by":"publisher","first-page":"10623","DOI":"10.1007\/s13369-022-06673-0","volume":"47","author":"V Garg","year":"2022","unstructured":"Garg V, Tiwari R, Shukla A, Dhar J (2022) A distributed cooperative approach for dynamic target search using particle swarm optimization with limited intercommunication. Arab J Sci Eng 47(8):10623\u201310637","journal-title":"Arab J Sci Eng"},{"issue":"3\u20134","key":"673_CR22","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1561\/2200000071","volume":"11","author":"V Fran\u00e7ois-Lavet","year":"2018","unstructured":"Fran\u00e7ois-Lavet V, Henderson P, Islam R, Bellemare MG, Pineau J et al (2018) An introduction to deep reinforcement learning. Found Trends\u00ae Mach Learn 11(3\u20134):219\u2013354","journal-title":"Found Trends\u00ae Mach Learn"},{"issue":"7839","key":"673_CR23","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser J, Antonoglou I, Hubert T, Simonyan K, Sifre L, Schmitt S, Guez A, Lockhart E, Hassabis D, Graepel T et al (2020) Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839):604\u2013609","journal-title":"Nature"},{"key":"673_CR24","doi-asserted-by":"crossref","unstructured":"Pathak D, Agrawal P, Efros AA, Darrell T (2017) Curiosity-driven exploration by self-supervised prediction. In: International conference on machine learning. PMLR, pp 2778\u20132787","DOI":"10.1109\/CVPRW.2017.70"},{"issue":"2","key":"673_CR25","first-page":"249","volume":"13","author":"W Keyu","year":"2019","unstructured":"Keyu W, Wang H, Esfahani MA, Yuan S (2019) Bnd*-ddqn: learn to steer autonomously through deep reinforcement learning. IEEE Trans Cogn Dev Syst 13(2):249\u2013261","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"673_CR26","unstructured":"Laud A, DeJong G (2003) 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), pp 440\u2013447"},{"key":"673_CR27","doi-asserted-by":"crossref","unstructured":"Grzes M, Kudenko D (2009) Theoretical and empirical analysis of reward shaping in reinforcement learning. In: 2009 international conference on machine learning and applications. IEEE, pp. 337\u2013344","DOI":"10.1109\/ICMLA.2009.33"},{"key":"673_CR28","doi-asserted-by":"crossref","unstructured":"Matignon L, Laurent GJ, Le Fort-Piat N (2006) Reward function and initial values: Better choices for accelerated goal-directed reinforcement learning. In: International conference on artificial neural networks. Springer, pp 840\u2013849","DOI":"10.1007\/11840817_87"},{"issue":"1","key":"673_CR29","doi-asserted-by":"publisher","first-page":"7619483","DOI":"10.1155\/2019\/7619483","volume":"2019","author":"H Zijian","year":"2019","unstructured":"Zijian H, Wan K, Gao X, Zhai Y (2019) A dynamic adjusting reward function method for deep reinforcement learning with adjustable parameters. Math Probl Eng 2019(1):7619483","journal-title":"Math Probl Eng"},{"issue":"13","key":"673_CR30","doi-asserted-by":"publisher","first-page":"3664","DOI":"10.3390\/s20133664","volume":"20","author":"Q Zhang","year":"2020","unstructured":"Zhang Q, Zhu M, Zou L, Li M, Zhang Y (2020) Learning reward function with matching network for mapless navigation. Sensors 20(13):3664","journal-title":"Sensors"},{"key":"673_CR31","doi-asserted-by":"publisher","first-page":"175473","DOI":"10.1109\/ACCESS.2024.3504735","volume":"12","author":"S Ibrahim","year":"2024","unstructured":"Ibrahim S, Mostafa M, Jnadi A, Salloum H, Osinenko P (2024) Comprehensive overview of reward engineering and shaping in advancing reinforcement learning applications. IEEE Access 12:175473\u2013175500","journal-title":"IEEE Access"},{"key":"673_CR32","doi-asserted-by":"publisher","first-page":"6973","DOI":"10.1109\/ACCESS.2023.3237025","volume":"11","author":"P Singhal","year":"2023","unstructured":"Singhal P, Walambe R, Ramanna S, Kotecha K (2023) Domain adaptation: challenges, methods, datasets, and applications. IEEE Access 11:6973\u20137020","journal-title":"IEEE Access"},{"key":"673_CR33","unstructured":"Zhang CB, Hong ZW, Pacchiano A, Agrawal P (2024) Orso: Accelerating reward design via online reward selection and policy optimization. arXiv preprint arXiv:2410.13837"},{"key":"673_CR34","unstructured":"Li W, Huang W, Sun C (2025) Shaping sparse rewards in reinforcement learning: a semi-supervised approach. arXiv preprint arXiv:2501.19128"},{"key":"673_CR35","unstructured":"Wang Z, Schaul T, Hessel M, Hasselt H, Lanctot M, Freitas N (2016) Dueling network architectures for deep reinforcement learning. In: International conference on machine learning. PMLR, pp. 1995\u20132003"},{"issue":"32","key":"673_CR36","doi-asserted-by":"publisher","first-page":"20011","DOI":"10.1007\/s00521-024-10208-z","volume":"36","author":"Y Akkem","year":"2024","unstructured":"Akkem Y, Biswas SK, Varanasi A (2024) Streamlit-based enhancing crop recommendation systems with advanced explainable artificial intelligence for smart farming. Neural Comput Appl 36(32):20011\u201320025","journal-title":"Neural Comput Appl"},{"issue":"5","key":"673_CR37","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1109\/TAI.2024.3508654","volume":"6","author":"Y Akkem","year":"2025","unstructured":"Akkem Y, Biswas SK (2025) Analysis of an intellectual mechanism of a novel crop recommendation system using improved heuristic algorithm-based attention and cascaded deep learning network. IEEE Transactions on Artificial Intelligence 6(5):1100\u20131113","journal-title":"IEEE Transactions on Artificial Intelligence"},{"issue":"2","key":"673_CR38","doi-asserted-by":"publisher","DOI":"10.1088\/2631-8695\/ade19d","volume":"7","author":"Y Akkem","year":"2025","unstructured":"Akkem Y, Biswas SK, Varanasi A (2025) Ai-driven smart farming portal: overcoming language barriers and enhancing agricultural productivity through machine learning. Eng Res Express 7(2):025288","journal-title":"Eng Res Express"}],"container-title":["Intelligent Service Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-025-00673-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11370-025-00673-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11370-025-00673-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T02:15:54Z","timestamp":1778033754000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11370-025-00673-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,19]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["673"],"URL":"https:\/\/doi.org\/10.1007\/s11370-025-00673-3","relation":{},"ISSN":["1861-2776","1861-2784"],"issn-type":[{"value":"1861-2776","type":"print"},{"value":"1861-2784","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,19]]},"assertion":[{"value":"23 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2025","order":3,"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 Conflict of interest are concerned.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict 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":"8"}}