Related papers: Combining Policy Gradient and Safety-Based Control…
Developing an autonomous vehicle control strategy for signalised intersections (SI) is one of the challenging tasks due to its inherently complex decision-making process. This study proposes a Deep Reinforcement Learning (DRL) based…
In this paper, we develop a safe decision-making method for self-driving cars in a multi-lane, single-agent setting. The proposed approach utilizes deep reinforcement learning (RL) to achieve a high-level policy for safe tactical…
Trajectory planning in dense, interactive traffic scenarios presents significant challenges for autonomous vehicles, primarily due to the uncertainty of human driver behavior and the non-convex nature of collision avoidance constraints.…
Traditional planning and control methods could fail to find a feasible trajectory for an autonomous vehicle to execute amongst dense traffic on roads. This is because the obstacle-free volume in spacetime is very small in these scenarios…
Finding feasible, collision-free paths for multiagent systems can be challenging, particularly in non-communicating scenarios where each agent's intent (e.g. goal) is unobservable to the others. In particular, finding time efficient paths…
Traditional decision and planning frameworks for self-driving vehicles (SDVs) scale poorly in new scenarios, thus they require tedious hand-tuning of rules and parameters to maintain acceptable performance in all foreseeable cases.…
Connected and automated vehicles provide a new opportunity for highly advanced collision avoidance, in which several cars cooperate to reach an optimal overall outcome, that no single car acting in isolation could achieve. For example, one…
Deep reinforcement learning has shown promise in various engineering applications, including vehicular traffic control. The non-stationary nature of traffic, especially in the lane-free environment with more degrees of freedom in vehicle…
Applying reinforcement learning to autonomous driving entails particular challenges, primarily due to dynamically changing traffic flows. To address such challenges, it is necessary to quickly determine response strategies to the changing…
This paper studies a policy optimization problem arising from collaborative multi-agent reinforcement learning in a decentralized setting where agents communicate with their neighbors over an undirected graph to maximize the sum of their…
Direct optimization is an appealing framework that replaces integration with optimization of a random objective for approximating gradients in models with discrete random variables. A$^\star$ sampling is a framework for optimizing such…
To maximize safety and driving comfort, autonomous driving systems can benefit from implementing foresighted action choices that take different potential scenario developments into account. While artificial scene prediction methods are…
Reinforcement learning has received high research interest for developing planning approaches in automated driving. Most prior works consider the end-to-end planning task that yields direct control commands and rarely deploy their algorithm…
Autonomous vehicles (AVs) have the potential to prevent accidents caused by drivers errors and reduce road traffic risks. Due to the nature of heavy vehicles, whose collisions cause more serious crashes, the weights of vehicles need to be…
Autonomous driving has attracted great interest due to its potential capability in full-unsupervised driving. Model-based and learning-based methods are widely used in autonomous driving. Model-based methods rely on pre-defined models of…
The objective of this paper is to develop a sample efficient end-to-end deep learning method for self-driving cars, where we attempt to increase the value of the information extracted from samples, through careful analysis obtained from…
Real-world control systems require policies that are not only high-performing but also interpretable and robust. A promising direction toward this goal is model-based control, which learns system dynamics and cost functions from historical…
Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…
Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…
Reach-Avoid-Stay (RAS) optimal control enables systems such as robots and air taxis to reach their targets, avoid obstacles, and stay near the target. However, current methods for RAS often struggle with handling complex, dynamic…