TY - CHAP A1 - Chaulwar, Amit A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - A Hybrid Machine Learning Approach for Planning Safe Trajectories in Complex Traffic-Scenarios T2 - 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA) UR - https://doi.org/10.1109/ICMLA.2016.0095 KW - Hybrid learning algorithms KW - Trajectory Planning in Road Traffic KW - 3D-ConvNets Y1 - 2016 UR - https://doi.org/10.1109/ICMLA.2016.0095 SN - 978-1-5090-6167-9 SP - 540 EP - 546 PB - IEEE CY - Los Alamitos ER - TY - CHAP A1 - Chaulwar, Amit A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - A machine learning based biased-sampling approach for planning safe trajectories in complex, dynamic traffic-scenarios T2 - 2017 IEEE Intelligent Vehicles Symposium (IV) UR - https://doi.org/10.1109/IVS.2017.7995735 KW - Acceleration KW - Trajectory KW - Heuristic algorithms KW - Vehicle dynamics KW - Planning KW - Prediction algorithms KW - Roads Y1 - 2017 UR - https://doi.org/10.1109/IVS.2017.7995735 SN - 978-1-5090-4804-5 SP - 297 EP - 303 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Chaulwar, Amit A1 - Botsch, Michael A1 - Utschick, Wolfgang ED - Kurková, Vera ED - Manolopoulos, Yannis ED - Hammer, Barbara ED - Iliadis, Lazaros ED - Maglogiannis, Ilias T1 - Generation of Reference Trajectories for Safe Trajectory Planning T2 - Artificial Neural Networks and Machine Learning – ICANN 2018 : 27th International Conference on Artificial Neural Networks,Rhodes, Greece, October 4–7, 2018 : Proceedings, Part I UR - https://doi.org/10.1007/978-3-030-01418-6_42 KW - Safe trajectory planning KW - Hybrid machine learning KW - Variational autoencoder Y1 - 2018 UR - https://doi.org/10.1007/978-3-030-01418-6_42 SN - 978-3-030-01418-6 SN - 978-3-030-01417-9 SP - 423 EP - 434 PB - Springer CY - Cham ER - TY - JOUR A1 - Chaulwar, Amit A1 - Al-Hashimi, Hussein A1 - Botsch, Michael A1 - Utschick, Wolfgang T1 - Sampling Algorithms Combination with Machine Learning for Effcient Safe Trajectory Planning JF - International Journal of Machine Learning and Computing N2 - The planning of safe trajectories in critical traffic scenarios using model-based algorithms is a very computationally intensive task. Recently proposed algorithms, namely Hybrid Augmented CL-RRT, Hybrid Augmented CL-RRT+ and GATE-ARRT+, reduce the computation time for safe trajectory planning drastically using a combination of a deep learning algorithm 3D-ConvNet with a vehicle dynamic model. An efficient embedded implementation of these algorithms is required as the vehicle on-board micro-controller resources are limited. This work proposes methodologies for replacing the computationally intensive modules of these trajectory planning algorithms using different efficient machine learning and analytical methods. The required computational resources are measured by downloading and running the algorithms on various hardware platforms. The results show significant reduction in computational resources and the potential of proposed algorithms to run in real time. Also, alternative architectures for 3D-ConvNet are presented for further reduction of required computational resources. UR - https://doi.org/10.18178/ijmlc.2021.11.1.1007 KW - Safe trajectory planning KW - hybrid machine learning KW - collision avoidance and mitigation Y1 - 2021 UR - https://doi.org/10.18178/ijmlc.2021.11.1.1007 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-14099 SN - 2010-3700 VL - 11 IS - 1 PB - IACSIT Press CY - Singapur ER -