Knowledge transfer is a promising concept to achieve real-time decision-making for autonomous vehicles. This paper constructs a transfer deep reinforcement learning framework to transform the driving tasks in inter-section environments. The driving missions at the un-signalized intersection are cast into a left turn, right turn, and running straight for automated vehicles. The goal of the autonomous ego vehicle (AEV) is to drive through the intersection situation efficiently and safely. This objective promotes the studied vehicle to increase its speed and avoid crashing other vehicles. The decision-making pol-icy learned from one driving task is transferred and evaluated in another driving mission. Simulation results reveal that the decision-making strategies related to similar tasks are transferable. It indicates that the presented control framework could reduce the time consumption and realize online implementation.
In fact, the Lincoln never enters the intersection. It gradually slows down and yields to the law-breaking vehicle with time to spare. A car is stopped dead in the road around a blind curve, but the Kia Soul that comes up behind it doesn't rear-end it. It gently comes to a stop before its passengers even register the obstacle. Both scenarios are as noteworthy for what didn't happen as they are for what did.
At first glance it seems like any other city, with five lane roads, intersections, buildings and even pedestrians waving as you pass. However, M City, in Ann Arbor, is devoid of one thing - people. Ford has become the first major car maker test autonomous vehicles at Mcity – the full-scale simulated real-world urban environment at the University of Michigan. At first glance it seems like any other city, with five lane roads, intersections, buildings and even pedestrians waving as you pass. However, M City, in Ann Arbor, is devoid of one thing - people.
At first glance it seems like any other city, with five lane roads, intersections, buildings and even pedestrians waving as you pass. However, M City, in Ann Arbor, is missing one thing - people. The entire 32 acre town has been to allow self driving car makers to test their vehicles in conditions as close as possible to the real world. The $6.5 million facility has 40 building facades, angled intersections, a traffic circle, a bridge, a tunnel, gravel roads, and plenty of obstructed views The $6.5 million facility has 40 building facades, angled intersections, a traffic circle, a bridge, a tunnel, gravel roads, and plenty of obstructed views. Occupying 32 acres at the University's North Campus Research Complex, it includes approximately five lane-miles of roads with intersections, traffic signs and signals, sidewalks, benches, simulated buildings, street lights, and obstacles such as construction barriers.
Cooperative Intelligent Transportation Systems (C-ITS) will change the modes of road safety and traffic management, especially at intersections without traffic lights, namely unsignalized intersections. Existing researches focus on vehicle control within a small area around an unsignalized intersection. In this paper, we expand the control domain to a large area with multiple intersections. In particular, we propose a Multi-intersection Vehicular Cooperative Control (MiVeCC) to enable cooperation among vehicles in a large area with multiple unsignalized intersections. Firstly, a vehicular end-edge-cloud computing framework is proposed to facilitate end-edge-cloud vertical cooperation and horizontal cooperation among vehicles. Then, the vehicular cooperative control problems in the cloud and edge layers are formulated as Markov Decision Process (MDP) and solved by two-stage reinforcement learning. Furthermore, to deal with high-density traffic, vehicle selection methods are proposed to reduce the state space and accelerate algorithm convergence without performance degradation. A multi-intersection simulation platform is developed to evaluate the proposed scheme. Simulation results show that the proposed MiVeCC can improve travel efficiency at multiple intersections by up to 4.59 times without collision compared with existing methods.