Identify, estimate and bound the uncertainty of reinforcement learning for autonomous driving
Deep reinforcement learning (DRL) has emerged as a promising approach for developing
more intelligent autonomous vehicles (AVs). A typical DRL application on AVs is to train a …
more intelligent autonomous vehicles (AVs). A typical DRL application on AVs is to train a …
Safe reinforcement learning with mixture density network: A case study in autonomous highway driving
A Baheri - arXiv preprint arXiv:2007.01698, 2020 - arxiv.org
This paper presents a safe reinforcement learning system for automated driving that benefits
from multimodal future trajectory predictions. We propose a safety system that consists of two …
from multimodal future trajectory predictions. We propose a safety system that consists of two …
A Real-World Reinforcement Learning Framework for Safe and Human-Like Tactical Decision-Making
Lane-change decision-making for vehicles is a challenging task for many reasons, including
traffic rules, safety, and the stochastic nature of driving. Because of its success in solving …
traffic rules, safety, and the stochastic nature of driving. Because of its success in solving …
An ML-aided reinforcement learning approach for challenging vehicle maneuvers
DC Selvaraj, S Hegde, N Amati… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
The richness of information generated by today's vehicles fosters the development of data-
driven decision-making models, with the additional capability to account for the context in …
driven decision-making models, with the additional capability to account for the context in …
Uncertainty-aware decision-making for autonomous driving at uncontrolled intersections
Reinforcement learning (RL) has been widely used in the decision-making of autonomous
vehicles (AVs) in recent studies. However, existing RL methods generally find the optimal …
vehicles (AVs) in recent studies. However, existing RL methods generally find the optimal …
Addressing inherent uncertainty: Risk-sensitive behavior generation for automated driving using distributional reinforcement learning
J Bernhard, S Pollok, A Knoll - 2019 IEEE Intelligent Vehicles …, 2019 - ieeexplore.ieee.org
For highly automated driving above SAE level 3, behavior generation algorithms must
reliably consider the inherent uncertainties of the traffic environment, eg arising from the …
reliably consider the inherent uncertainties of the traffic environment, eg arising from the …
Safe-state enhancement method for autonomous driving via direct hierarchical reinforcement learning
Reinforcement learning (RL) has shown excellent performance in the sequential decision-
making problem, where safety in the form of state constraints is of great significance in the …
making problem, where safety in the form of state constraints is of great significance in the …
Towards robust decision-making for autonomous driving on highway
Reinforcement learning (RL) methods are commonly regarded as effective solutions for
designing intelligent driving policies. Nonetheless, even if the RL policy is converged after …
designing intelligent driving policies. Nonetheless, even if the RL policy is converged after …
Safe reinforcement learning for autonomous vehicles through parallel constrained policy optimization
Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to
its potential to solve complex classification and control problems. However, existing RL …
its potential to solve complex classification and control problems. However, existing RL …
Emergency Collision Avoidance Decision-making for Autonomous Vehicles: A Model-based Reinforcement Learning Approach
The challenging task of “intelligent vehicles” opens up a new frontier to enhancing traffic
safety. However, how to determine driving behavior timely and effectively is one of the most …
safety. However, how to determine driving behavior timely and effectively is one of the most …