Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386083237> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4386083237 endingPage "14" @default.
- W4386083237 startingPage "1" @default.
- W4386083237 abstract "Reinforcement learning (RL) is a promising way to achieve human- like autonomous driving (HAD) in complex and dynamic traffic, but faces challenges such as low sample efficiency, partial observability, and sim2real transfer. In light of this, a comprehensive solution for RL-driven HAD is established. First, an efficient training scheme called Deep Recurrent Q-learning from demonstration algorithm (DRQfD) is proposed for lane-changing decision-making to address the low sample efficiency in RL and the poor generalization capability in Imitation Learning (IL). The inherent LSTM structure potentially learns to predict future states of surrounding vehicles, helping to address the partially observable problem in autonomous driving (AD). Second, to reduce the sim2real gap, a twin high-fidelity simulator is built based on ROS-Gazebo for simulating LiDAR sensing, model training, and evaluations. Domain randomization is used to improve the robustness and generalization ability, making it easier for the model to be transferred to real-world scenarios. In addition, for the multi-objective optimization and imbalanced data issues in this scenario, a hierarchical decision-making framework is proposed to decompose the complex decision-making problem into several subtasks, making the driving policies easier to converge. To avoid the excessive dependence of the decision-making module on the output of perception module in modular systems, we train each modularized skill in an end-to-end manner. Moreover, we compare our method with a vanilla RL method to show improvement in learning efficiency. Comparisons between RL-based model and IL baseline in terms of safety, travel efficiency, and human-likeness are also given. To further validate the generalization ability of our model, we test the model on real traffic dataset. Finally, we implement the RL model on physical cars to demonstrate the performance of sim2real transfer." @default.
- W4386083237 created "2023-08-23" @default.
- W4386083237 creator A5046644093 @default.
- W4386083237 creator A5071093853 @default.
- W4386083237 creator A5090699231 @default.
- W4386083237 date "2023-01-01" @default.
- W4386083237 modified "2023-09-26" @default.
- W4386083237 title "From Naturalistic Traffic Data to Learning-Based Driving Policy: A Sim-to-Real Study" @default.
- W4386083237 doi "https://doi.org/10.1109/tvt.2023.3307409" @default.
- W4386083237 hasPublicationYear "2023" @default.
- W4386083237 type Work @default.
- W4386083237 citedByCount "0" @default.
- W4386083237 crossrefType "journal-article" @default.
- W4386083237 hasAuthorship W4386083237A5046644093 @default.
- W4386083237 hasAuthorship W4386083237A5071093853 @default.
- W4386083237 hasAuthorship W4386083237A5090699231 @default.
- W4386083237 hasConcept C101468663 @default.
- W4386083237 hasConcept C104317684 @default.
- W4386083237 hasConcept C111919701 @default.
- W4386083237 hasConcept C119857082 @default.
- W4386083237 hasConcept C134306372 @default.
- W4386083237 hasConcept C154945302 @default.
- W4386083237 hasConcept C177148314 @default.
- W4386083237 hasConcept C185592680 @default.
- W4386083237 hasConcept C2776459999 @default.
- W4386083237 hasConcept C28826006 @default.
- W4386083237 hasConcept C33923547 @default.
- W4386083237 hasConcept C36299963 @default.
- W4386083237 hasConcept C41008148 @default.
- W4386083237 hasConcept C55493867 @default.
- W4386083237 hasConcept C63479239 @default.
- W4386083237 hasConcept C76155785 @default.
- W4386083237 hasConcept C97541855 @default.
- W4386083237 hasConceptScore W4386083237C101468663 @default.
- W4386083237 hasConceptScore W4386083237C104317684 @default.
- W4386083237 hasConceptScore W4386083237C111919701 @default.
- W4386083237 hasConceptScore W4386083237C119857082 @default.
- W4386083237 hasConceptScore W4386083237C134306372 @default.
- W4386083237 hasConceptScore W4386083237C154945302 @default.
- W4386083237 hasConceptScore W4386083237C177148314 @default.
- W4386083237 hasConceptScore W4386083237C185592680 @default.
- W4386083237 hasConceptScore W4386083237C2776459999 @default.
- W4386083237 hasConceptScore W4386083237C28826006 @default.
- W4386083237 hasConceptScore W4386083237C33923547 @default.
- W4386083237 hasConceptScore W4386083237C36299963 @default.
- W4386083237 hasConceptScore W4386083237C41008148 @default.
- W4386083237 hasConceptScore W4386083237C55493867 @default.
- W4386083237 hasConceptScore W4386083237C63479239 @default.
- W4386083237 hasConceptScore W4386083237C76155785 @default.
- W4386083237 hasConceptScore W4386083237C97541855 @default.
- W4386083237 hasLocation W43860832371 @default.
- W4386083237 hasOpenAccess W4386083237 @default.
- W4386083237 hasPrimaryLocation W43860832371 @default.
- W4386083237 hasRelatedWork W2045236383 @default.
- W4386083237 hasRelatedWork W2552014313 @default.
- W4386083237 hasRelatedWork W2604873668 @default.
- W4386083237 hasRelatedWork W2977730262 @default.
- W4386083237 hasRelatedWork W2986252512 @default.
- W4386083237 hasRelatedWork W3156449588 @default.
- W4386083237 hasRelatedWork W4200370596 @default.
- W4386083237 hasRelatedWork W4283455536 @default.
- W4386083237 hasRelatedWork W4319083788 @default.
- W4386083237 hasRelatedWork W2121778218 @default.
- W4386083237 isParatext "false" @default.
- W4386083237 isRetracted "false" @default.
- W4386083237 workType "article" @default.