When learning common skills like driving, beginners usually have domain experts standing
by to ensure the safety of the learning process. We formulate such learning scheme under …

Human intervention is an effective way to inject human knowledge into the training loop of
reinforcement learning, which can bring fast learning and ensured training safety. Given the …

In this paper, we present a safe deep reinforcement learning system for automated driving.
The proposed framework leverages merits of both rule-based and learning-based …

Decision making for autonomous driving is a safety-critical control problem. Prior works of
safe reinforcement learning either tackle the problem with reward shaping or with modifying …

The goal of autonomous vehicles is to navigate public roads safely and comfortably. To
enforce safety, traditional planning approaches rely on handcrafted rules to generate …

In this Ph. D. thesis, we study how autonomous vehicles can learn to act safely and avoid
accidents, despite sharing the road with human drivers whose behaviours are uncertain. To …

Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to
its potential to solve complex classification and control problems. However, existing RL …

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while
satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly …

In this paper we present the first safe system for full control of self-driving vehicles trained
from human demonstrations and deployed in challenging, real-world, urban environments …

Despite recent advances in reinforcement learning (RL), its application in safety critical
domains like autonomous vehicles is still challenging. Although penalizing RL agents for …