Safe Adaptive Deep Reinforcement Learning for Autonomous Driving in Urban Environments. Additional Filter? How and Where?

This paper set out to revise and improve existing autonomous driving models using reinforcement learning, thus proposing a reinforced autonomous driving prediction model. The paper conducted training for a reinforcement learning model using DQN, a reinforcement learning algorithm. The main aim of this paper was to reduce the time spent on training and improve self-driving performance. Rewards for reinforcement learning agents were developed to mimic human driving behavior as much as possible. High rewards were given for greater distance travelled within lanes and higher speed. Negative rewards were given when a vehicle crossed into other lanes or had a collision. Performance evaluation was carried out in urban environments without pedestrians. The performance test results show that the model with the collision prevention model exhibited faster performance improvement within the same time compared to when the model was not applied. However, vulnerabilities to factors such as pedestrians and vehicles approaching from the side were not addressed, and the lack of stability in the definition of compensation functions and limitations with respect to the excessive use of memory were shown.

Download Full-text

Tactical Decision-Making in Autonomous Driving by Reinforcement Learning with Uncertainty Estimation

2020 IEEE Intelligent Vehicles Symposium (IV) ◽

10.1109/iv47402.2020.9304614 ◽

2020 ◽

Author(s):

Carl-Johan Hoel ◽

Krister Wolff ◽

Leo Laine

Keyword(s):

Decision Making ◽

Reinforcement Learning ◽

Autonomous Driving ◽

Uncertainty Estimation ◽

Tactical Decision

Download Full-text

A Reinforcement Learning Approach for Enacting Cautious Behaviours in Autonomous Driving System: Safe Speed Choice in the Interaction With Distracted Pedestrians

IEEE Transactions on Intelligent Transportation Systems ◽

10.1109/tits.2021.3086397 ◽

2021 ◽

pp. 1-18

Author(s):

Gastone Pietro Rosati Papini ◽

Alice Plebe ◽

Mauro Da Lio ◽

Riccardo Dona

Keyword(s):

Reinforcement Learning ◽

Autonomous Driving ◽

Learning Approach ◽

Driving System ◽

Autonomous Driving System

Download Full-text

Transfer Reinforcement Learning for Autonomous Driving

ACM Transactions on Modeling and Computer Simulation ◽

10.1145/3449356 ◽

2021 ◽

Vol 31 (3) ◽

pp. 1-26

Author(s):

Aravind Balakrishnan ◽

Jaeyoung Lee ◽

Ashish Gaurav ◽

Krzysztof Czarnecki ◽

Sean Sedwards

Keyword(s):

Decision Making ◽

Reinforcement Learning ◽

Transfer Problem ◽

Autonomous Driving ◽

High Fidelity ◽

Rule Based ◽

High Level ◽

Real Vehicle

Reinforcement learning (RL) is an attractive way to implement high-level decision-making policies for autonomous driving, but learning directly from a real vehicle or a high-fidelity simulator is variously infeasible. We therefore consider the problem of transfer reinforcement learning and study how a policy learned in a simple environment using WiseMove can be transferred to our high-fidelity simulator, W ise M ove . WiseMove is a framework to study safety and other aspects of RL for autonomous driving. W ise M ove accurately reproduces the dynamics and software stack of our real vehicle. We find that the accurately modelled perception errors in W ise M ove contribute the most to the transfer problem. These errors, when even naively modelled in WiseMove , provide an RL policy that performs better in W ise M ove than a hand-crafted rule-based policy. Applying domain randomization to the environment in WiseMove yields an even better policy. The final RL policy reduces the failures due to perception errors from 10% to 2.75%. We also observe that the RL policy has significantly less reliance on velocity compared to the rule-based policy, having learned that its measurement is unreliable.

Download Full-text