Virtual to Real Reinforcement Learning for Autonomous Driving
Open accessAbstract
Reinforcement learning is considered as a promising direction for driving policy learning. However, training autonomous driving vehicle with reinforcement learning in real environment involves non-affordable trial-and-error. It is more desirable to first train in a virtual environment and then transfer to the real environment. In this paper, we propose a novel realistic translation network to make model trained in virtual environment be workable in real world. The proposed network can convert non-realistic virtual image input into a realistic one with similar scene structure. Given realistic frames as input, driving policy trained by reinforcement learning can nicely adapt to real world driving. Experiments show that our proposed virtual to real (VR) reinforcement learning (RL) works pretty well. To our knowledge, this is the first successful case of driving policy trained by reinforcement learning that can adapt to real world driving data.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 1× · see citing works
“Many of them are based on deep convolutional neural network or fully convolutional neural network [16].”
BackgroundHuman-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 3× · see citing works
“Recent work in deep reinforcement learning has made great progress in learning in a high dimensional space with the power of deep neural networks [13, 15, 17, 18, 24].”
BackgroundMethodImage-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930 · see citing works
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392 · see citing works
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631 · cited 2× · see citing works
“In this paper, we use the SegNet for image segmentation, the structure of the network is revealed in [2], which is composed of two main parts.”
MethodThe Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 2× · see citing works
“We used image segmentation model trained on the cityscape [7] dataset to segment both virtual and real images.”
MethodContinuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782 · cited 4× · see citing works
“Recent work in deep reinforcement learning has made great progress in learning in a high dimensional space with the power of deep neural networks [13, 15, 17, 18, 24].”
BackgroundMethodInfluentialMulti-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738 · cited 1× · see citing works
“al network or fully convolutional neural network [17]. In order to get better quality segmented images, the work of [2] cut down the downsampling layers to avoid resolution reduction, and the work of [32, 5] uses dilated convolution to improve performance. Bi-linear interpolation and deconvolutional methods are also v…”
MethodAsynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 11× · see citing works
“that of [18] where the actor network is a 4-layer convolutional network (shown in figure 3) with ReLU activation functions in-between.”
BackgroundMethodInfluentialTrust region policy optimization
Schulman, J., Levine, S., Moritz, P., Jordan, M. I., & Abbeel, P. (2015) · arXiv · doi:10.48550/arxiv.1502.05477 · Cited by 4,578 · cited 1× · see citing works
“Recent work in deep reinforcement learning has made great progress in learning in a high dimensional space with the power of deep neural networks [13, 15, 17, 18, 24].”
BackgroundEnd to End Learning for Self-Driving Cars
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., et al. (2016) · arXiv · doi:10.48550/arxiv.1604.07316 · Cited by 3,198 · cited 2× · see citing works
“rn the driving policy that automatically outputs control signals for steering wheel, throttle, brake, etc., based on observed surroundings. The straight-forward idea is end-to-end supervised learning [3,4], which trains a neural network model mapping visual input directly to action output, and the training data is lab…”
BackgroundDomain randomization for transferring deep neural networks from simulation to the real world
Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202133 · Cited by 3,124 · cited 2× · see citing works
“These models either first train a model in virtual environment and then fine-tune in the real environment [21], or learn an alignment between virtual image and real image by finding representations that are shared between the two domains [27], or use randomized rendered virtual environments to train and then test in r…”
BackgroundDeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
Chen, C., Seff, A., Kornhauser, A., & Xiao, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.312 · Cited by 1,876 · see citing works
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
Wu, J., Zhang, C., Xue, T., Freeman, W. T., & Tenenbaum, J. B. (2016) · arXiv · doi:10.48550/arxiv.1610.07584 · Cited by 1,393 · cited 1× · see citing works
“To name a few, the work of [29] explored the use of VAE-GAN [14] in generating 3D voxel models, and the work of [28] proposed a cascade GAN to generate natural image by structure and style.”
MethodEnd-to-End Learning of Driving Models from Large-Scale Video Datasets
Xu, H., Gao, Y., Yu, F., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.376 · Cited by 884 · cited 1× · see citing works
“However, supervised approach usually requires large amount of data to train a model [31] that can generalize to different environments.”
BackgroundAutoencoding beyond pixels using a learned similarity metricPreprint
Larsen, A., Sønderby, S. K., Larochelle, H., & Winther, O. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.09300 · Cited by 712 · cited 2× · see citing works
“To name a few, the work of [29] explored the use of VAE-GAN [14] in generating 3D voxel models, and the work of [28] proposed a cascade GAN to generate natural images by structure and style.”
MethodPolicy gradient reinforcement learning for fast quadrupedal locomotion
Kohl, N., & Stone, P. (2004) · IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 · doi:10.1109/robot.2004.1307456 · Cited by 676 · cited 1× · see citing works
“Reinforcement learning has been applied to a wide variety of robotics related tasks, such as computer games [17], robot locomotion [8, 12], and autonomous driving [1, 25].”
BackgroundCAD2RL: Real Single-Image Flight Without a Single Real Image
Sadeghi, F., & Levine, S. (2017) · Robotics: Science and Systems XIII · doi:10.15607/rss.2017.xiii.034 · Cited by 618 · cited 6× · see citing works
“As a more recent work, [22] proposed a new framework for training a reinforcement learning agent with only virtual environment.”
BackgroundMethodResultInfluentialGenerative Image Modeling Using Style and Structure Adversarial Networks
Wang, X., & Gupta, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46493-0_20 · Cited by 607 · cited 1× · see citing works
“To name a few, the work of [29] explored the use of VAE-GAN [14] in generating 3D voxel models, and the work of [28] proposed a cascade GAN to generate natural image by structure and style.”
MethodAn Application of Reinforcement Learning to Aerobatic Helicopter Flight
Abbeel, P., Coates, A., Quigley, M., & Ng, A. Y. (2007) · The MIT Press eBooks · doi:10.7551/mitpress/7503.003.0006 · Cited by 551 · cited 1× · see citing works
“Reinforcement learning has been applied to a wide variety of robotics related tasks, such as computer games [17], robot locomotion [8, 12], and autonomous driving [1, 25].”
BackgroundSafe, Multi-Agent, Reinforcement Learning for Autonomous Driving
Shalev-Shwartz, S., Shammah, S., & Shashua, A. (2016) · arXiv · doi:10.48550/arxiv.1610.03295 · Cited by 509 · cited 3× · see citing works
“Recently, reinforcement learning has been considered as a promising technique to learn driving policy due to its expertise in action planing [15, 23, 25].”
BackgroundSim-to-Real Robot Learning from Pixels with Progressive Nets
Rusu, A. A., Vecerik, M., Rothörl, T., Heess, N., Pascanu, R., & Hadsell, R. (2016) · arXiv · doi:10.48550/arxiv.1610.04286 · Cited by 385 · cited 3× · see citing works
“These models either first train a model in virtual environment and then fine-tune in the real environment [21], or learn an alignment between virtual image and real image by finding representations that are shared between the two domains [27], or use randomized rendered virtual environments to train and then test in r…”
BackgroundMethodLearning Invariant Feature Spaces to Transfer Skills with Reinforcement LearningPreprint
Gupta, A., Devin, C., Liu, Y., Abbeel, P., & Levine, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.02949 · Cited by 209 · cited 1× · see citing works
“Recent progress of transfer and domain adaptation learning in robotics provides examples of simulation-toreal reinforcement training [10, 21, 26].”
BackgroundLearning CPG-based Biped Locomotion with a Policy Gradient Method: Application to a Humanoid Robot
Endo, G., Morimoto, J., Matsubara, T., Nakanishi, J., & Cheng, G. (2008) · The International Journal of Robotics Research · doi:10.1177/0278364907084980 · Cited by 206 · cited 1× · see citing works
“Reinforcement learning has been applied to a wide variety of robotics related tasks, such as computer games [17], robot locomotion [8, 12], and autonomous driving [1, 25].”
BackgroundTransfer from Simulation to Real World through Learning Deep Inverse Dynamics ModelPreprint
Christiano, P. F., Shah, Z., Mordatch, I., Schneider, J., Blackwell, T., Tobin, J., Abbeel, P., & Zaremba, W. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.03518 · Cited by 159 · cited 1× · see citing works
“Models trained purely on virtual data do not generalize well to real images [6, 27].”
BackgroundEnd-to-End Deep Reinforcement Learning for Lane Keeping AssistPreprint
Sallab, A. E., Abdou, M., Perot, E., & Yogamani, S. K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.04340 · Cited by 146 · cited 1× · see citing works
“Recently, reinforcement learning has been considered as a promising technique to learn driving policy due to its expertise in action planing [15, 23, 25].”
BackgroundAdapting Deep Visuomotor Representations with Weak Pairwise Constraints
Tzeng, E., Devin, C., Hoffman, J., Finn, C., Abbeel, P., Levine, S., Saenko, K., & Darrell, T. (2020) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-43089-4_44 · Cited by 136 · cited 2× · see citing works
“These models either first train a model in virtual environment and then fine-tune in the real environment [21], or learn an alignment between virtual image and real image by finding representations that are shared between the two domains [27], or use randomized rendered virtual environments to train and then test in r…”
BackgroundEvolving large-scale neural networks for vision-based reinforcement learning
Koutník, J., Cuccu, G., Schmidhuber, J., & Gomez, F. (2013) · Proceedings of the 15th annual conference on Genetic and evolutionary computation · doi:10.1145/2463372.2463509 · Cited by 130 · see citing works
Query-Efficient Imitation Learning for End-to-End Autonomous Driving
Zhang, J., & Cho, K. (2016) · arXiv · doi:10.48550/arxiv.1605.06450 · Cited by 118 · see citing works
BMJ Publishing Group Ltd, & Royal College of Psychiatrists and British Psychological Society (2008) · Evidence-Based Mental Health · doi:10.1136/ebmh.11.4.102 · cited 3×
“Reinforcement learning has been applied to a wide variety of robotics related tasks, such as computer games [19], robot locomotion [13, 9], and autonomous driving [1, 26].”
BackgroundMethodInfluential
Flagged first, then by citations
Cited by
Sorted by citations
Deep reinforcement learning for autonomous driving: A survey
Kiran, B. R., Sobh, I., Talpaert, V., Mannion, P., Sallab, A. A. A., Yogamani, S., & Perez, P. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3054625 · Cited by 2,342 · see citing works
Continuous control for robot based on deep reinforcement learning
Zhang, S. (2019) · doi:10.32657/10356/90191 · Cited by 953 · see citing works
“[51] proposed a virtual-toreal DRL framework based on A3C for the autonomous driving.”
MethodMachine Learning Testing: Survey, Landscapes and Horizons
Zhang, J. M., Harman, M., Ma, L., & Liu, Y. (2022) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2019.2962027 · Cited by 897 · see citing works
“Autopilot-TensorFlow [265] Recorded to test the NVIDIA Dave model 45,568 robustness”
MethodZhang, J., & Tao, D. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3039359 · Cited by 774 · see citing works
“DA could be useful for AIoT applications when deploying models to new scenarios or new working modes of machines [128], [203]–[206], e.”
BackgroundInfluentialChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
Bansal, M., Krizhevsky, A., & Ogale, A. S. (2019) · Robotics: Science and Systems · doi:10.15607/rss.2019.xv.031 · Cited by 743 · see citing works
“Pan et al. (2017) also describes achieving transfer of an agent trained in simulation to the real world using a learned intermediate scene labeling representation.”
BackgroundComputer Vision for Autonomous Vehicles
Janai, J., Güney, F., Behl, A., & Geiger, A. (2020) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000079 · Cited by 664 · see citing works
Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles
Aradi, S. (2020) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3024655 · Cited by 664 · see citing works
End-To-End Interpretable Neural Motion Planner
Zeng, W., Luo, W., Suo, S., Sadat, A., Yang, B., Casas, S., & Urtasun, R. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00886 · Cited by 406 · see citing works
“Following the success of Alpha GO [29], RL has been applied to self-driving in [15, 23].”
MethodInfluentialMachine learning, social learning and the governance of self-driving cars
Stilgoe, J. (2018) · Social Studies of Science · doi:10.1177/0306312717741687 · Cited by 375 · see citing works
“Reinforcement learning in simulated environments, including games such as Grand Theft Auto, is seen as one way of accelerating self-driving car training (Filipowicz et al., 2017; Pan et al., 2017).”
MethodLi, G., Yang, Y., Li, S., Qu, X., Lyu, N., & Li, S. E. (2022) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2021.103452 · Cited by 308 · see citing works
Recent Advancements in End-to-End Autonomous Driving Using Deep Learning: A Survey
Chib, P. S., & Singh, P. P. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3318070 · Cited by 326 · see citing works
“Regarding planning and decision disparity, Pan et al. [96] propose learning driving policies in a simulated setting with realistic frames before applying them in the real world.”
BackgroundA Survey of End-to-End Driving: Architectures and Training Methods
Tampuu, A., Matiisen, T., Semikin, M., Fishman, D., & Muhammad, N. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3043505 · Cited by 301 · see citing works
“in [9]), one might also just explicitly punish crashes by assigning a large negative reward, as was done in [26], [61], [66], [69], [70].”
BackgroundInfluentialMa, J. W., Czerniawski, T., & Leite, F. L. (2020) · Automation in Construction · doi:10.1016/j.autcon.2020.103144 · Cited by 229 · see citing works
Risk assessment based collision avoidance decision-making for autonomous vehicles in multi-scenarios
Li, G., Yang, Y., Zhang, T., Qu, X., Cao, D., Cheng, B., & Li, K. (2020) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2020.102820 · Cited by 229 · see citing works
Learning Robust Control Policies for End-to-End Autonomous Driving From Data-Driven Simulation
Amini, A., Gilitschenski, I., Phillips, J., Moseyko, J., Banerjee, R., Karaman, S., & Rus, D. L. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2966414 · Cited by 204 · see citing works
“Performing style transformation, such as adding realistic textures to synthetic images with deep generative models, has been used to deploy learned policies from model-based simulation engines into the real world [9], [24].”
BackgroundTen years of generative adversarial nets (GANs): a survey of the state-of-the-art
Chakraborty, T., S, U. R. K., Naik, S. M., Panja, M., & Manvitha, B. (2024) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ad1f77 · Cited by 198 · see citing works
“A potential method for training autonomous driving models is using GANs to produce synthetic visuals [89].”
MethodChallenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning
Ilahi, I., Usama, M., Qadir, J., Janjua, M. U., Al-Fuqaha, A., Hoang, D. T., & Niyato, D. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3111139 · Cited by 170 · see citing works
“They test their approach on a self-driving environment using the TORCS simulator and show that a risk-averse agent handles the risk better and leads to fewer crashes than a normal agent trained in a similar environment.”
BackgroundInfluentialLiu, H., & Wu, W. (2020) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2020.3041620 · Cited by 167 · see citing works
“In recent years, deep reinforcement learning (DRL) algorithms have demonstrated remarkable performance on multiple controlling tasks such as games [21], [22], autonomous driving [23] and continuous control [24].”
Deep learning in robotics: survey on model structures and training strategies
Karoly, A. I., Galambos, P., Kuti, J., & Rudas, I. J. (2021) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2020.3018325 · Cited by 146 · see citing works
“The other approach to bridge the reality gap is to make the simulation environment as similar to the real world as possible, so the trained DL model can be applied for the real-world problem directly [31], [93], [94].”
BackgroundMethodPhysGAN: Generating Physical-World-Resilient Adversarial Examples for Autonomous Driving
Kong, Z., Guo, J., Li, A., & Liu, C. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01426 · Cited by 151 · see citing works
“…mounted camera of a driving car and the simultaneous steering wheel angle applied by a human driver for each image; (2) DAVE-2 testing dataset [20] 6 , which contains 45,568 images to test the NVIDIA DAVE-2 model; (3) Kitti [9] dataset which contains 14,999 images from six different scenes…”
MethodA Survey on Visual Traffic Simulation: Models, Evaluations, and Applications in Autonomous Driving
Chao, Q., Bi, H., Li, W., Mao, T., Wang, Z., Lin, M. C., & Deng, Z. (2019) · Computer Graphics Forum · doi:10.1111/cgf.13803 · Cited by 135 · see citing works
Self-citationDeep Reinforcement Learning for Soft, Flexible Robots: Brief Review with Impending Challenges
Bhagat, S., Banerjee, H., Tse, Z. T. H., & Ren, H. (2019) · Robotics · doi:10.3390/robotics8010004 · Cited by 134 · see citing works
“[130]) Color/Semantics Autonomous Drivings AI-2 (Kolve et al.”
Hierarchical Reinforcement Learning: A Survey and Open Research Challenges
Hutsebaut-Buysse, M., Mets, K., & Latré, S. (2022) · Machine Learning and Knowledge Extraction · doi:10.3390/make4010009 · Cited by 129 · see citing works
“autonomous vehicles [27,28] smart grids [29], fleet management [30], resource management [31,32] and recommender systems [33].”
BackgroundLikmeta, A., Metelli, A. M., Tirinzoni, A., Giol, R., Restelli, M., & Romano, D. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103568 · Cited by 106 · see citing works
Visual Navigation for Biped Humanoid Robots Using Deep Reinforcement Learning
Lobos-Tsunekawa, K., Leiva, F., & Ruíz-del-Solar, J. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2851148 · Cited by 99 · see citing works
“Training visual policies using segmented images as part of the method has been presented in previous works in the context of autonomous cars, such as [20]”
MethodFederated Transfer Reinforcement Learning for Autonomous Driving
Liang, X., Liu, Y., Chen, T., Liu, M., & Yang, Q. (2022) · Adaptation, learning, and optimization · doi:10.1007/978-3-031-11748-0_15 · Cited by 131 · see citing works
Parallel Learning: Overview and Perspective for Computational Learning Across Syn2Real and Sim2Real
Miao, Q., Lv, Y., Huang, M., Wang, X., & Wang, F. (2023) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2023.123375 · Cited by 80 · see citing works
Ye, F., Zhang, S., Wang, P., & Chan, C. (2021) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv48863.2021.9575880 · Cited by 85 · see citing works
“(2017) [45] A3C Virtual world images A = {Steering,Acc.”
BackgroundMethodInfluentialAmini, A., Wang, T.-H. J., Gilitschenski, I., Schwarting, W., Liu, Z., Han, S., Karaman, S., & Rus, D. L. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812276 · Cited by 80 · see citing works
“Driving Policy Learning: While policy learning for driving using real-world data is largely restricted to IL [31]– [35], learning in simulation allows for greater algorithmic flexibiltiy ranging from IL [5], [36], [37], to RL [1], [4], [38], [39], and GPL [6], [40].”
BackgroundReinforcement Learning-Based Motion Planning for Automatic Parking System
Zhang, J., Chen, H., Song, S., & Hu, F. (2020) · IEEE Access · doi:10.1109/access.2020.3017770 · Cited by 76 · see citing works
A Survey of Deep Learning Applications to Autonomous Vehicle Control
Kuutti, S., Bowden, R., Jin, Y., Barber, P., & Fallah, S. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2962338 · Cited by 96 · see citing works
“ferring driving policies from simulation to the real world easier [143], [144].”
BackgroundMachine learning in fermentative biohydrogen production: Advantages, challenges, and applications
Pandey, A. K., Park, J., Ko, J., Joo, H.-H., Raj, T., Singh, L. K., Singh, N., & Kim, S. (2022) · Bioresource Technology · doi:10.1016/j.biortech.2022.128502 · Cited by 73 · see citing works
Lu, Y., Fu, J., Tucker, G., Pan, X., Bronstein, E., Roelofs, R., Sapp, B., White, B., Faust, A., Whiteson, S., et al. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342038 · Cited by 82 · see citing works
“However, relying on RL alone, e.g., [7], [8], [9], is also problematic because it heavily depends on reward design, which is an open challenge in autonomous driving [10].”
BackgroundSelf-citationVirtual-to-Real: Learning to Control in Visual Semantic Segmentation
Hong, Z.-W., Chen, Y., Yang, H.-K., Su, S.-Y., Shann, T.-Y., Chang, Y.-H., Ho, B. H.-L., Tu, C.-C., Hsiao, T.-C., Hsiao, H.-W., et al. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/682 · Cited by 73 · see citing works
“As the image semantics rendered by the simulators and those generated by the perception module are invariant [You et al., 2017], the control policy learned from the simulators can be transferred to the real world directly.”
BackgroundRisk Averse Robust Adversarial Reinforcement Learning
Pan, X., Seita, D., Gao, Y., & Canny, J. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8794293 · Cited by 69 · see citing works
“Reinforcement learning has demonstrated remarkable performance on a variety of sequential decision making tasks such as Go [36], Atari games [20], autonomous driving [35], [40], and continuous robotic control [17], [9].”
BackgroundSelf-citationSafe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization
Wen, L., Duan, J., Li, S. E., Xu, S., & Peng, H. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294262 · Cited by 78 · see citing works
“(2017) built a new framework on the basis of A3C to train a self-driving vehicle by interacting with a synthesized real environment [7].”
BackgroundHoel, C.-J., Wolff, K., & Laine, L. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3251376 · Cited by 69 · see citing works
“The desired speed of the cars is uniformly distributed in the range [vmin, vmax] = [10, 15] m/s, and the longitudinal speed is controlled by the standard SUMO speed controller (which is a type of adaptive cruise controller, based”
BackgroundGeneralizing semi-supervised generative adversarial networks to regression using feature contrasting
Olmschenk, G., Zhu, Z., & Hao Tang, A. (2019) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2019.06.004 · Cited by 68 · see citing works
“Such an approach allows for basic partial self-driving/auto-pilot capabilities using a single image (Pan et al., 2017).”
BackgroundA Review of End-to-End Autonomous Driving in Urban Environments
Coelho, D., & de Oliveira, M. A. R. (2022) · IEEE Access · doi:10.1109/access.2022.3192019 · Cited by 66 · see citing works
Reinforcement Learning in Game Industry—Review, Prospects and Challenges
Souchleris, K., Sidiropoulos, G. K., & Papakostas, G. A. (2023) · Applied Sciences · doi:10.3390/app13042443 · Cited by 78 · see citing works
Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
Cao, Z., Bıyık, E., Wang, W. Z., Raventos, A., Gaidon, A., Rosman, G., & Sadigh, D. (2020) · Robotics: Science and Systems · doi:10.15607/rss.2020.xvi.039 · Cited by 65 · see citing works
“Reinforcement learning (RL) [12, 13, 14] and imitation learning (IL) [1, 2, 3, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24] are two promising learning-based approaches for autonomous driving.”
BackgroundLearning to Drive Like Human Beings: A Method Based on Deep Reinforcement Learning
Tian, Y., Cao, X., Huang, K., Fei, C., Zheng, Z., & Ji, X. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3055899 · Cited by 62 · see citing works
Reinforcement learning for electric vehicle charging scheduling: A systematic review
Zhao, Z., Lee, C. K. M., Yan, X., & Wang, H. (2024) · Transportation Research Part E Logistics and Transportation Review · doi:10.1016/j.tre.2024.103698 · Cited by 81 · see citing works
Towards Multi-Modal Perception-Based Navigation: A Deep Reinforcement Learning Method
Huang, X., Deng, H., Zhang, W., Song, R., & Li, Y. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3064461 · Cited by 65 · see citing works
“However, the gap between simulated and real-world environments in terms of their appearance is inevitable in vision-based navigation task [12].”
BackgroundJarosiński, M., Beekman, F., Bada, G., & Cloetingh, S. A. P. L. (2006) · Geophysical Journal International · doi:10.1111/j.1365-246x.2006.02979.x · Cited by 56 · see citing works
Tactical Decision-Making in Autonomous Driving by Reinforcement Learning with Uncertainty Estimation
Hoel, C.-J., Wolff, K., & Laine, L. (2020) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv47402.2020.9304614 · Cited by 58 · see citing works
“A few studies have also trained decision-making agents in a simulated environment and then deployed them in a real vehicle [19], [20], or for a limited case, trained an agent directly in a real vehicle [21].”
BackgroundNie, H., Chen, Y., Xia, Y., Huang, S., & Liu, B. (2020) · IEEE Access · doi:10.1109/access.2020.3018142 · Cited by 54 · see citing works
“With model-free algorithm and empirical learning, DRL solves many of the tough problems of the past, such as robot control [17], autonomous driving [18] and many kinds of games”
MethodLearning Driving Models From Parallel End-to-End Driving Data Set
Chen, L. F., Wang, Q., Lu, X., Cao, D., & Wang, F. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2952735 · Cited by 52 · see citing works
“Some recent works [8]–[11] have studied the sim2real problems at the algorithmic level.”
BackgroundMethodInfluentialA Systematic Review on Reinforcement Learning-Based Robotics Within the Last Decade
Khan, M. A.-M., Khan, M. R. J., Tooshil, A., Sikder, N., Mahmud, M. A. P., Kouzani, A. Z., & Nahid, A.-A. (2020) · IEEE Access · doi:10.1109/access.2020.3027152 · Cited by 51 · see citing works
“From then, RL methods have been broadly applied to various robotics control task from manipulation [9], [10] to navigation [11], [12], industrial manufacturing, production [13], [14] and autonomous vehicle control [15], [16].”
MethodCharacterizing Attacks on Deep Reinforcement LearningPreprint
Pan, X., Xiao, C., He, W., Yang, S., Peng, J., Sun, M.-J., Yi, J.-F., Yang, Z.-J., Liu, M.-Y., Li, B., et al. (2019) · Adaptive Agents and Multi-Agent Systems · doi:10.48550/arxiv.1907.09470 · Cited by 83 · see citing works
“TORCS, including baseline attacks: obs-fgsm-wb , and obs-fgsm-bb , and finite difference based methods ( obs-fd-bb , obs-s[n]fd-bb ) on It shows that obs-fd-bb could achieve similar obs-fgsm-wb obs-fgsm-bb Moreover, for obs-s[ 𝑖 ]fd-bb , it shows the effectiveness and with that when 𝑛 = 40, it could achieve comparable…”
BackgroundMethodInfluentialSelf-citationA survey of visual navigation: From geometry to embodied AI
Zhang, T., Hu, X., Xiao, J., & Zhang, G. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105036 · Cited by 51 · see citing works
Deductive Reinforcement Learning for Visual Autonomous Urban Driving Navigation
Huang, C., Zhang, R., Ouyang, M., Wei, P., Lin, J., Su, J., & Lin, L. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3109284 · Cited by 50 · see citing works
Tian, W., Liao, Z., Zhang, Z., Wu, H., & Xin, K. (2022) · Water Resources Research · doi:10.1029/2021wr030939 · Cited by 50 · see citing works
“It has emerged as a state-of-the-art methodology for the autonomous driving (Pan et al., 2017), robotic control (Kober & Peters, 2012), and game artificial intelligence (Shao et al., 2018; Silver et al., 2017).”
BackgroundYes, we GAN: Applying adversarial techniques for autonomous driving
Uřičář, M., Křížek, P., Hurych, D., Sobh, I., Yogamani, S. K., & Denny, P. E. (2019) · Electronic Imaging · doi:10.2352/issn.2470-1173.2019.15.avm-048 · Cited by 54 · see citing works
“Reinforcement Learning for Autonomous Driving model trained in virtual environment is shown to perform well in real environment [39].”
BackgroundMethodVirtual to Real-World Transfer Learning: A Systematic Review
Ranaweera, M., & Mahmoud, Q. H. (2021) · Electronics · doi:10.3390/electronics10121491 · Cited by 48 · see citing works
Rupprecht, T., & Wang, Y. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.05.013 · Cited by 48 · see citing works
Zhang, K., Chang, C., Zhong, W., Li, S., Li, Z., & Li, L. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3170329 · Cited by 49 · see citing works
Virtual-to-Real Knowledge Transfer for Driving Behavior Recognition: Framework and a Case Study
Lu, C., Hu, F., Cao, D., et al. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2917025 · Cited by 45 · see citing works
Self-citationEnd-to-End Autonomous Driving: An Angle Branched Network Approach
Wang, Q., Chen, L. F., Tian, B., Tian, W., Li, L., & Cao, D. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2921918 · Cited by 44 · see citing works
Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving
Bronstein, E., Palatucci, M., Notz, D., White, B., Kuefler, A., Lu, Y., Paul, S., Nikdel, P., Mougin, P., Chen, H., et al. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981695 · Cited by 46 · see citing works
“Closed-loop simulation continues to advance, both for the purposes of evaluating driving performance through realistic world models [9], [40]–[44], and to train driving policies that could transfer to the real world [45], [46].”
BackgroundA Safe Hierarchical Planning Framework for Complex Driving Scenarios based on Reinforcement Learning
Li, J., Sun, L., Chen, J., Tomizuka, M., & Zhan, W. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561195 · Cited by 46 · see citing works
Domain Adaptation In Reinforcement Learning Via Latent Unified State Representation
Xing, J., Nagata, T., Chen, K., Zou, X., Neftci, E., & Krichmar, J. L. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17251 · Cited by 47 · see citing works
“In this work, we use Ray RLlib (Liang et al. 2018) and RLCodebase (Xing 2020) for the PPO implementation.”
MethodThe Societal Implications of Deep Reinforcement Learning
Whittlestone, J., Arulkumaran, K., & Crosby, M. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12360 · Cited by 43 · see citing works
“However, good simulations require enormous amounts of data and often still do not result in policies that transfer well to the real world (Pan et al., 2017).”
BackgroundMachine Learning, Social Learning and the Governance of Self-Driving Cars
Stilgoe, J. (2017) · doi:10.2139/ssrn.2937316 · Cited by 376 · see citing works
Wang, G., Wei, F., Jiang, Y. L., et al. (2022) · Sensors · doi:10.3390/s22218562 · Cited by 38 · see citing works
Reinforcement Learning with Uncertainty Estimation for Tactical Decision-Making in Intersections
Hoel, C.-J., Tram, T., & Sjoberg, J. S. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294407 · Cited by 33 · see citing works
“Some studies have trained an RL agent in a simulated environment and then deployed the agent in a real vehicle [8], [9], and for a limited case, trained the agent directly in a real vehicle [10].”
BackgroundWu, M., Yu, F. R., & Liu, P. X. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3165172 · Cited by 37 · see citing works
“vironment abstracted, [13] and [14] employ DRL-based driving policy while [15] employs end-to-end learning-based driving policy.”
MethodTian, W., Liao, Z., Zhi, G., Zhang, Z., & Wang, X. (2022) · Water Resources Research · doi:10.1029/2021wr030703 · Cited by 39 · see citing works
“It has emerged as a state-of-theart methodology for autonomous driving (Pan et al., 2017), stock trading (Tan et al.”
BackgroundDeep Reinforcement Learning in Agent Based Financial Market Simulation
Maeda, I., deGraw, D., Kitano, M., Matsushima, H., Sakaji, H., Izumi, K., & Kato, A. (2020) · Journal of risk and financial management · doi:10.3390/jrfm13040071 · Cited by 38 · see citing works
“DRL is applied to various tasks such as table games (Silver et al. 2016, 2017) video games (Lample and Chaplot 2017; Mnih et al. 2013), autonomous driving (Pan et al. 2017; Sallab et al. 2017), and robotic manipulation (Gu et al. 2017; Kalashnikov et al. 2018).”
Jung, C., & Shim, D. H. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3059628 · Cited by 36 · see citing works
A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving
Abouelazm, A., Michel, J., & Zöllner, J. M. (2024) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55156.2024.10588385 · Cited by 40 · see citing works
“In order to provide a dense reward, progress is often proxied by the distance traveled [30], [35], [48], [49], [52] or the velocity [21], [28], [34], [36]–[38], [43], [51] in the current time step.”
BackgroundXu, X., Aggarwal, D., & Shankar, K. (2022) · Nanomaterials · doi:10.3390/nano12040633 · Cited by 34 · see citing works
“RL has become known to the general public for its application in AlphaGo [73], logical decision making, and self-driving [74].”
BackgroundEnd to End Vehicle Lateral Control Using a Single Fisheye Camera
Toromanoff, M., Wirbel, É., Wilhelm, F., Vejarano, C., Perrotton, X., & Moutarde, F. (2018) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8594090 · Cited by 32 · see citing works
“[2] tried to go one step closer to real test by first training a Generative Adversarial Network [3] to generate real-looking images from the synthetic images of the simulation and then give these generated images as input to the RL algorithm.”
Predicting drag on rough surfaces by transfer learning of empirical correlations
Lee, S.-S., Yang, J., Forooghi, P., et al. (2021) · Journal of Fluid Mechanics · doi:10.1017/jfm.2021.1041 · Cited by 31 · see citing works
“The method has been used, for example, for self-driving cars, which can be pre-trained with data from virtual car simulators (Pan et al. 2017; Martinez et al. 2017; Akhauri et al. 2020).”
MethodAI Wings: An AIoT Drone System for Commanding ArduPilot UAVs
Lai, K.-T., Chung, Y.-T., Su, J.-J., Lai, C.-H., & Huang, Y.-H. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3189011 · Cited by 32 · see citing works
“This technique is called virtual-to-real learning [29].”
New challenges in reinforcement learning: a survey of security and privacy
Lei, Y., Ye, D., Shen, S., Sui, Y., Zhu, T., & Zhou, W. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10348-5 · Cited by 32 · see citing works
“Reinforcement learning’s strong performance has led to its implementation and deployment across a broad range of fields in recent years, such as the Internet of things (IoT) [7], recommend systems [8], healthcare [9], robotics [10], finance [11], self-driving cars [12], and smart grids [13], and so on.”
BackgroundHu, H., Lu, Z., Wang, Q., & Zheng, C. (2020) · Sensors · doi:10.3390/s20185443 · Cited by 29 · see citing works
“used a twostage automatic encoder–decoder for image translation, and then used the real image synthesized by the virtual image as the input to train a deep reinforcement learning agent [25].”
MethodSocial Signal-Driven Knowledge Automation: A Focus on Social Transportation
Lü, H., Zhu, Y., Yuan, Y., Gong, W., Li, J., Shi, K., Lv, Y., Niu, Z., & Wang, F. (2021) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2021.3057332 · Cited by 30 · see citing works
Safe Reinforcement Learning in Autonomous Driving With Epistemic Uncertainty Estimation
Zhang, Z., Liu, Q., Li, Y., Lin, K., & Li, L. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3397700 · Cited by 32 · see citing works
“Pan et al. [14] proposed the first autonomous driving policy adaptive to real-world driving data to address the gap between simulation and reality.”
BackgroundZhao, H., Wang, B., Liu, H., Sun, H., Pan, Z., & Guo, Q. (2021) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2021.3107439 · Cited by 27 · see citing works
Driving policies of V2X autonomous vehicles based on reinforcement learning methods
Wu, Z., Qiu, K., & Gao, H. (2020) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2019.0457 · Cited by 27 · see citing works
“Xinlei et al. proposed a novel realistic translation network to make model trained in virtual environment be workable in real world [22].”
BackgroundVisual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective
Tai, L., Yun, P., Chen, Y., Liu, C., Ye, H.-Y., & Liu, M. (2019) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros40897.2019.8968307 · Cited by 28 · see citing works
“One probable solution is the so-called sim-to-real, where synthetic images are translated to the realistic domain [18].”
BackgroundLearning robotic navigation from experience: principles, methods and recent results
Levine, S., & Shah, D. (2022) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2021.0447 · Cited by 28 · see citing works
Self-Optimizing Path Tracking Controller for Intelligent Vehicles Based on Reinforcement Learning
Ma, J., Xie, H., Song, K., & Liu, H. (2021) · Symmetry · doi:10.3390/sym14010031 · Cited by 28 · see citing works
“The full name of sim-to-real is simulation to reality, which is a branch of reinforcement learning and a kind of transfer learning [52].”
BackgroundAutomated Dataset Generation with Blender for Deep Learning-based Object Segmentation
Karoly, A. I., & Galambos, P. (2022) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami54271.2022.9780790 · Cited by 27 · see citing works
Improving the Performance of Autonomous Driving through Deep Reinforcement Learning
Tammewar, A., Chaudhari, N., Saini, B., Venkatesh, D., Dharahas, G., Vora, D. R., Patil, S., Kotecha, K. V., & Alfarhood, S. (2023) · Sustainability · doi:10.3390/su151813799 · Cited by 26 · see citing works
An Overview of Robust Reinforcement Learning
Chen, S., & Li, Y. (2020) · IEEE International Conference on Networking, Sensing and Control (ICNSC) · doi:10.1109/icnsc48988.2020.9238129 · Cited by 26 · see citing works
A Reinforcement Learning Approach for Continuum Robot Control
Kargin, T. C., & Kołota, J. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-02003-0 · Cited by 27 · see citing works
A review on pavement data acquisition and analytics tools using autonomous vehicles
Abdollahi, C., Mollajafari, M., Golroo, A., Moridpour, S., & Wang, H. (2023) · Road Materials and Pavement Design · doi:10.1080/14680629.2023.2237601 · Cited by 24 · see citing works
“Improving the so-called virtual images (simulated data) currently is state-of-the-art (You et al., 2017).”
BackgroundMethodZhang, Y., Gong, G., Yang, H., et al. (2022) · Journal of Zhejiang University. Science A · doi:10.1631/jzus.a2100325 · Cited by 24 · see citing works
“The recent successes in autonomous driving are fueled by DRL techniques (Shalev-Shwartz et al., 2016; Yu et al., 2016; El Sallab et al., 2017; Pan et al., 2017).”
BackgroundLai, K.-T., Lin, C.-C., Kang, C.-Y., Liao, M.-E., & Chen⋆, M.-S. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3243653 · Cited by 23 · see citing works
“Many methods have been proposed to transfer the knowledge learned in 3D virtual environment to real world [9, 16, 18].”
BackgroundMethodEfficient Hybrid-Supervised Deep Reinforcement Learning for Person Following Robot
Pang, L., Zhang, Y., Coleman, S., & Cao, H. (2019) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-019-01030-0 · Cited by 23 · see citing works
Few-Shot Structured Domain Adaptation for Virtual-to-Real Scene Parsing
Zhang, J., Chen, Z., Huang, J., Lin, L., & Zhang, D. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00008 · Cited by 22 · see citing works
“Among these visual structure prediction tasks, scene parsing attracts an increasing amount of attention due to its application potential in autonomous driving [26, 34].”
BackgroundEnd-to-End Automated Guided Modular Vehicle
Curiel-Ramirez, L. A., Ramírez-Mendoza, R. A., Bautista-Montesano, R., Bustamante-Bello, R., González-Hernández, H. G., Reyes-Avendaño, J. A., & Cortes-Gallardo, E. (2020) · Applied Sciences · doi:10.3390/app10124400 · Cited by 21 · see citing works
“Acronym Definition Acronym Definition AD AGV Autonomous Driving Automated Guided Vehicles ADAS AI Advanced Driving Assistance System Artificial Intelligence ARM Advanced RISC Machines AV Autonomous Vehicle BC Behavioral Cloning CAN Controller Area Network CNN Convolutional Neural Network CPU Central Processing Unit DL…”
MethodInfluentialReinforcement learning for patient-specific optimal stenting of intracranial aneurysms
Hachem, E., Méliga, P., Goetz, A., Rico, P. J., Viquerat, J., Larcher, A., Valette, R., Fava-Sanches, A., Lannelongue, V., Ghraieb, H., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-34007-z · Cited by 21 · see citing works
Fernandez-Chaves, D., Ruiz-Sarmiento, J.-R., Jaenal, A., Petkov, N., & González-Jiménez, J. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.117970 · Cited by 21 · see citing works
Doan, Y. T.-T., Ho, M.-T., Nguyen, H.-K., & Han, H.-D. (2021) · Journal of Applied Phycology · doi:10.1007/s10811-021-02488-y · Cited by 20 · see citing works
“…reinforcement learning has been successfully applied in many aspects of human life, such as robotics (Kormushev et al. 2013), self-driving cars (Pan et al. 2017; Liang et al. 2018), natural language processing (Choi et al. 2017; Paulus et al. 2017), healthcare (Schaefer et al. 2005), and…”
Zhang, Z.-L., Han, S., Wang, J., & Miao, F. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10161216 · Cited by 21 · see citing works
“Learning methods can give a high-level decision, such as “go straight”, “go left” [10], or whether or not to yield to another vehicle [11].”
MethodLearning Interactive Driving Policies via Data-driven Simulation
Wang, T.-H. J., Amini, A., Schwarting, W., Gilitschenski, I., Karaman, S., & Rus, D. L. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812407 · Cited by 20 · see citing works
“However, synthetically generated images are typically still insufficient to enable zero shot transfer of learned policies and require techniques such as domain-randomization [19], [20] or style transfer [10] to enable real-world deployment of learned policies.”
BackgroundMa, J., Xie, H., Song, K., & Liu, H. (2021) · Sensors · doi:10.3390/s21020331 · Cited by 18 · see citing works
- Authors
- Pan, X., You, Y., Wang, Z., & Lu, C.
- Venue
- Procedings of the British Machine Vision Conference 2017
- Publisher
- British Machine Vision Association
- Published
- 2017
- OpenAlex
- W2962977206
- Cited by
- 326
- References
- 30
- Citations by year
- 2026: 4 · 2025: 26 · 2024: 29 · 2023: 36 · 2022: 49 · 2021: 64 · 2020: 54 · 2019: 43 · 2018: 16 · 2017: 3 · 2016: 1
- FWCI
- 14.47
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- British Machine Vision Conference (BMVC) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- autonomous driving, reinforcement learning, sim-to-real transfer, driving policy learning, virtual environment training, domain adaptation, realistic image synthesis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
