Transferring autonomous driving knowledge on simulated and real intersections
We view intersection handling on autonomous vehicles as a reinforcement learning
problem, and study its behavior in a transfer learning setting. We show that a network trained …
problem, and study its behavior in a transfer learning setting. We show that a network trained …
State dropout-based curriculum reinforcement learning for self-driving at unsignalized intersections
Traversing intersections is a challenging problem for autonomous vehicles, especially when
the intersections do not have traffic control. Recently deep reinforcement learning has …
the intersections do not have traffic control. Recently deep reinforcement learning has …
A reinforcement learning benchmark for autonomous driving in intersection scenarios
In recent years, control under urban intersection scenarios has become an emerging
research topic. In such scenarios, the autonomous vehicle confronts complicated situations …
research topic. In such scenarios, the autonomous vehicle confronts complicated situations …
Federated transfer reinforcement learning for autonomous driving
Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL
models typically involves in a multi-step process: pre-training RL models on simulators …
models typically involves in a multi-step process: pre-training RL models on simulators …
End-to-end intersection handling using multi-agent deep reinforcement learning
AP Capasso, P Maramotti, A Dell'Eva… - 2021 IEEE Intelligent …, 2021 - ieeexplore.ieee.org
Navigating through intersections is one of the main challenging tasks for an autonomous
vehicle. However, for the majority of intersections regulated by traffic lights, the problem …
vehicle. However, for the majority of intersections regulated by traffic lights, the problem …
Overtaking maneuvers in simulated highway driving using deep reinforcement learning
Most methods that attempt to tackle the problem of Autonomous Driving and overtaking
usually try to either directly minimize an objective function or iteratively in a Reinforcement …
usually try to either directly minimize an objective function or iteratively in a Reinforcement …
A multi-task reinforcement learning approach for navigating unsignalized intersections
S Kai, B Wang, D Chen, J Hao… - 2020 IEEE Intelligent …, 2020 - ieeexplore.ieee.org
Navigating through unsignalized intersections is one of the most challenging problems in
urban environments for autonomous vehicles. Existing methods need to train specific policy …
urban environments for autonomous vehicles. Existing methods need to train specific policy …
Navigating occluded intersections with autonomous vehicles using deep reinforcement learning
Providing an efficient strategy to navigate safely through unsignaled intersections is a
difficult task that requires determining the intent of other drivers. We explore the …
difficult task that requires determining the intent of other drivers. We explore the …
Learning to drive at unsignalized intersections using attention-based deep reinforcement learning
H Seong, C Jung, S Lee… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Driving at an unsignalized intersection is a complex traffic scenario that requires both traffic
safety and efficiency. At the unsignalized intersection, the driving policy does not simply …
safety and efficiency. At the unsignalized intersection, the driving policy does not simply …
Efficient reinforcement learning for autonomous driving with parameterized skills and priors
When autonomous vehicles are deployed on public roads, they will encounter countless and
diverse driving situations. Many manually designed driving policies are difficult to scale to …
diverse driving situations. Many manually designed driving policies are difficult to scale to …