Interpretable end-to-end urban autonomous driving with latent deep reinforcement learning
… deep neural network policy is like a black box, which is not ideal since autonomous driving
is a safety … Litkouhi, “Intention estimation for ramp merging control in autonomous driving,” in …
is a safety … Litkouhi, “Intention estimation for ramp merging control in autonomous driving,” in …
Hierarchical reinforcement learning for self‐driving decision‐making without reliance on labelled driving data
… demonstrates that it can realise smooth and safe decision making for self-driving cars. …
For example, the driving-in-lane manoeuvre is a combination of many similar behaviours, …
For example, the driving-in-lane manoeuvre is a combination of many similar behaviours, …
Generalization through simulation: Integrating simulated and real data into deep reinforcement learning for vision-based autonomous flight
… the real world can be combined in a hybrid deep reinforcement learning algorithm. Our
method uses real-world data to learn about the dynamics of the system, and simulated data to …
method uses real-world data to learn about the dynamics of the system, and simulated data to …
A review of safe reinforcement learning: Methods, theory and applications
… RL applications in this review, eg, autonomous driving [102… [102] provide a motion planning
method for automated driving based on constrained RL. They combine traditional motion …
method for automated driving based on constrained RL. They combine traditional motion …
A survey of deep learning applications to autonomous vehicle control
… There are several companies researching autonomous driving using machine learning …
control structure which combines reinforcement learning based control with safety based control …
control structure which combines reinforcement learning based control with safety based control …
End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks
… that combines (1) a model-free RL-based controller with (2) model-based controllers utilizing
control barrier … For example, suppose that in an autonomous driving task, the RL controller …
control barrier … For example, suppose that in an autonomous driving task, the RL controller …
Metadrive: Composing diverse driving scenarios for generalizable reinforcement learning
… safe reinforcement learning and multi-agent reinforcement … can be combined, managed, and
actuated to compose new driving … autonomous driving using deep reinforcement learning. In …
actuated to compose new driving … autonomous driving using deep reinforcement learning. In …
Learning to drive in a day
… of deep reinforcement learning to autonomous driving. From … by the vehicle without the safety
driver taking control. We use … haps combining it with elements from other machine learning …
driver taking control. We use … haps combining it with elements from other machine learning …
Autonomous boat driving system using sample‐efficient model predictive control‐based reinforcement learning approach
Y Cui, S Osaki, T Matsubara - Journal of Field Robotics, 2021 - Wiley Online Library
… propose a novel reinforcement learning (RL) approach specialized for autonomous boats:
sample-… From these works, the combination of GP, MPC, and model-based RL is a potentially …
sample-… From these works, the combination of GP, MPC, and model-based RL is a potentially …
A Multi-agent Reinforcement Learning Based Control Method for Connected and Autonomous Vehicles in A Mixed Platoon
Y Xu, Y Shi, X Tong, S Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
… based on control of Connected and Autonomous Vehicles (… approach to improve traffic
efficiency and safety. However, … and automated vehicles at intersections and merging at highway …
efficiency and safety. However, … and automated vehicles at intersections and merging at highway …