{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:38:09Z","timestamp":1780954689344,"version":"3.54.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T00:00:00Z","timestamp":1670544000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Semi-structured environments are difficult for autonomous driving because there are numerous unknown obstacles in drivable area without lanes, and its width and curvature considerably change. In such environments, searching for a path on a real-time is difficult, and localization data are inaccurate, reducing path tracking accuracy. Instead, alternative methods that reactively avoid obstacles in real-time using candidate paths or an artificial potential field have been studied. However, these require heuristics to identify specific parameters for handling various environments and are vulnerable to inaccurate input data. To address these limitations, this study proposes a method in which a vehicle drives toward drivable area using vision and deep learning. The proposed imitation learning method learns the look-ahead point where the vehicle should reach on a vision-based occupancy grid map to obtain a safe policy with a clear state action pattern relationship. Furthermore, using this point, the data aggregation (DAgger) algorithm with weighted loss function is proposed, which imitates expert behavior more accurately, especially in unsafe or near-collision situations. Experimental results in actual semi-structured environments demonstrated the limitations of general model-based methods and the effectiveness of the proposed imitation learning method. Moreover, simulation experiments showed that DAgger with the weight obtains a safer policy than existing DAgger algorithms.<\/jats:p>","DOI":"10.1038\/s41598-022-23546-6","type":"journal-article","created":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T11:04:51Z","timestamp":1670583891000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Autonomous driving using imitation learning with look ahead point for semi structured environments"],"prefix":"10.1038","volume":"12","author":[{"given":"Joonwoo","family":"Ahn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaeheung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,12,9]]},"reference":[{"key":"23546_CR1","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1109\/TITS.2015.2498841","volume":"17","author":"D Gonz\u00e1lez","year":"2015","unstructured":"Gonz\u00e1lez, D., P\u00e9rez, J., Milan\u00e9s, V. & Nashashibi, F. A review of motion planning techniques for automated vehicles. IEEE Trans. Intell. Transp. Syst. 17, 1135\u20131145 (2015).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"23546_CR2","doi-asserted-by":"crossref","unstructured":"Philippe, C., Adouane, L., Thuilot, B., Tsourdos, A. & Shin, H.-S. Safe and online mpc for managing safety and comfort of autonomous vehicles in urban environment. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC), 300\u2013306 (IEEE, 2018).","DOI":"10.1109\/ITSC.2018.8569384"},{"key":"23546_CR3","doi-asserted-by":"crossref","unstructured":"Pek, C. & Althoff, M. Computationally efficient fail-safe trajectory planning for self-driving vehicles using convex optimization. In 2018 21st International Conference on Intelligent Transportation Systems (ITSC), 1447\u20131454 (IEEE, 2018).","DOI":"10.1109\/ITSC.2018.8569425"},{"key":"23546_CR4","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s10846-019-01119-6","volume":"99","author":"L Li","year":"2020","unstructured":"Li, L. et al. Improving autonomous exploration using reduced approximated generalized voronoi graphs. J. Intell. Robot. Syst. 99, 91\u2013113 (2020).","journal-title":"J. Intell. Robot. Syst."},{"key":"23546_CR5","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1017\/S0373463318001005","volume":"72","author":"H Niu","year":"2019","unstructured":"Niu, H., Savvaris, A., Tsourdos, A. & Ji, Z. Voronoi-visibility roadmap-based path planning algorithm for unmanned surface vehicles. J. Navi. 72, 850\u2013874 (2019).","journal-title":"J. Navi."},{"key":"23546_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Fattahi, N. & Li, W. Probabilistic roadmap with self-learning for path planning of a mobile robot in a dynamic and unstructured environment. In 2013 IEEE International Conference on Mechatronics and Automation, 1074\u20131079 (IEEE, 2013).","DOI":"10.1109\/ICMA.2013.6618064"},{"key":"23546_CR7","doi-asserted-by":"crossref","unstructured":"Shin, S., Ahn, J. & Park, J. Desired orientation rrt (do-rrt) for autonomous vehicle in narrow cluttered spaces. In 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), 4736\u20134741 (IEEE, 2016).","DOI":"10.1109\/IROS.2016.7759696"},{"key":"23546_CR8","doi-asserted-by":"crossref","unstructured":"Dolgov, D., Thrun, S., Montemerlo, M. & Diebel, J. Path planning for autonomous driving in unknown environments. In Experimental Robotics, 55\u201364 (Springer, 2009).","DOI":"10.1007\/978-3-642-00196-3_8"},{"key":"23546_CR9","doi-asserted-by":"publisher","first-page":"1613","DOI":"10.1016\/j.artint.2007.11.009","volume":"172","author":"M Likhachev","year":"2008","unstructured":"Likhachev, M., Ferguson, D., Gordon, G., Stentz, A. & Thrun, S. Anytime search in dynamic graphs. Artif. Intell. 172, 1613\u20131643 (2008).","journal-title":"Artif. Intell."},{"key":"23546_CR10","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1017\/S0263574714000289","volume":"33","author":"M Hoy","year":"2015","unstructured":"Hoy, M., Matveev, A. S. & Savkin, A. V. Algorithms for collision-free navigation of mobile robots in complex cluttered environments: a survey. Robotica 33, 463\u2013497 (2015).","journal-title":"Robotica"},{"key":"23546_CR11","doi-asserted-by":"crossref","unstructured":"Missura, M. & Bennewitz, M. Predictive collision avoidance for the dynamic window approach. In 2019 International Conference on Robotics and Automation (ICRA), 8620\u20138626 (IEEE, 2019).","DOI":"10.1109\/ICRA.2019.8794386"},{"key":"23546_CR12","doi-asserted-by":"crossref","unstructured":"L\u00f3pez, J. et\u00a0al. A new approach to local navigation for autonomous driving vehicles based on the curvature velocity method. In 2019 International Conference on Robotics and Automation (ICRA), 1751\u20131757 (IEEE, 2019).","DOI":"10.1109\/ICRA.2019.8794380"},{"key":"23546_CR13","doi-asserted-by":"publisher","first-page":"3485","DOI":"10.1109\/TITS.2019.2930035","volume":"21","author":"H Mouhagir","year":"2019","unstructured":"Mouhagir, H., Talj, R., Cherfaoui, V., Aioun, F. & Guillemard, F. Evidential-based approach for trajectory planning with tentacles, for autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 21, 3485\u20133496 (2019).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"23546_CR14","first-page":"204","volume":"31","author":"V Olunloyo","year":"2009","unstructured":"Olunloyo, V. & Ayomoh, M. Autonomous mobile robot navigation using hybrid virtual force field concept. Eur. J. Sci. Res. 31, 204\u2013228 (2009).","journal-title":"Eur. J. Sci. Res."},{"key":"23546_CR15","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1109\/70.880813","volume":"16","author":"SS Ge","year":"2000","unstructured":"Ge, S. S. & Cui, Y. J. New potential functions for mobile robot path planning. IEEE Trans. Robot. Autom. 16, 615\u2013620 (2000).","journal-title":"IEEE Trans. Robot. Autom."},{"key":"23546_CR16","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TITS.2015.2401837","volume":"16","author":"J Wang","year":"2015","unstructured":"Wang, J., Wu, J. & Li, Y. The driving safety field based on driver-vehicle-road interactions. IEEE Trans. Intell. Transp. Syst. 16, 2203\u20132214 (2015).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"23546_CR17","doi-asserted-by":"crossref","unstructured":"Varma, G., Subramanian, A., Namboodiri, A., Chandraker, M. & Jawahar, C. Idd: A dataset for exploring problems of autonomous navigation in unconstrained environments. In 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), 1743\u20131751 (IEEE, 2019).","DOI":"10.1109\/WACV.2019.00190"},{"key":"23546_CR18","unstructured":"Hadfield-Menell, D., Milli, S., Abbeel, P., Russell, S.\u00a0J. & Dragan, A. Inverse reward design. In Advances in neural information processing systems, 6765\u20136774 (2017)."},{"key":"23546_CR19","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s12239-021-0013-7","volume":"22","author":"J Ahn","year":"2021","unstructured":"Ahn, J., Shin, S., Kim, M. & Park, J. Accurate path tracking by adjusting look-ahead point in pure pursuit method. Int. J. Automot. Technol. 22, 119\u2013129 (2021).","journal-title":"Int. J. Automot. Technol."},{"key":"23546_CR20","unstructured":"Ross, S., Gordon, G. & Bagnell, D. A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 627\u2013635 (2011)."},{"key":"23546_CR21","doi-asserted-by":"crossref","unstructured":"Ahn, J., Lee, Y., Kim, M. & Park, J. Vision-based branch road detection for intersection navigation in unstructured environment using multi-task network. J. Adv. Transp.2022 (2022).","DOI":"10.1155\/2022\/9328398"},{"key":"23546_CR22","doi-asserted-by":"crossref","unstructured":"Teichmann, M., Weber, M., Zoellner, M., Cipolla, R. & Urtasun, R. Multinet: Real-time joint semantic reasoning for autonomous driving. In 2018 IEEE Intelligent Vehicles Symposium (IV), 1013\u20131020 (IEEE, 2018).","DOI":"10.1109\/IVS.2018.8500504"},{"key":"23546_CR23","unstructured":"Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprintarXiv:1409.1556 (2014)."},{"key":"23546_CR24","unstructured":"Lee, J. et\u00a0al. Deep neural networks as gaussian processes. arXiv preprintarXiv:1711.00165 (2017)."},{"key":"23546_CR25","doi-asserted-by":"crossref","unstructured":"Menda, K., Driggs-Campbell, K. & Kochenderfer, M.\u00a0J. Ensembledagger: A bayesian approach to safe imitation learning. In 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS 2019, 5041\u20135048 (Institute of Electrical and Electronics Engineers Inc., 2019).","DOI":"10.1109\/IROS40897.2019.8968287"},{"key":"23546_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, J. & Cho, K. Query-efficient imitation learning for end-to-end simulated driving. In Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a031 (2017).","DOI":"10.1609\/aaai.v31i1.10857"},{"key":"23546_CR27","doi-asserted-by":"crossref","unstructured":"Kelly, M., Sidrane, C., Driggs-Campbell, K. & Kochenderfer, M.\u00a0J. Hg-dagger: Interactive imitation learning with human experts. In 2019 International Conference on Robotics and Automation (ICRA), 8077\u20138083 (IEEE, 2019).","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"23546_CR28","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62\u201366 (1979).","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"23546_CR29","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A. & Koltun, V. Carla: An open urban driving simulator. arXiv preprintarXiv:1711.03938 (2017)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-23546-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-23546-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-23546-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,9]],"date-time":"2022-12-09T11:06:15Z","timestamp":1670583975000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-23546-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,9]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["23546"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-23546-6","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,9]]},"assertion":[{"value":"16 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"21285"}}