Autonomous Vehicle Following can be achieved if the poses of both the follower and leader vehicles are continuously estimated. This can be achieved by using a Bayesian estimation technique together with a virtual trailer link model. The advantage of such a model is that the follower vehicle will trail a virtual trailer, modeled as an attachment to the leader vehicle, instead of the leader vehic...

This paper presents a modified optimal velocity model (MOVM) for vehicle following. It makes use of time to collision (TTC) in order to reduce the reference speed when relative speed against the leading vehicle is negative. Simulation results have shown an anticipation behavior which leads to smoother maneuvers. The driver risk perception of rear-end collision is also enhanced. Copyright c ©200...

This paper describes the development and test in simulation of a coast line following preview controller for the DELFIMx autonomous surface craft (ASC) that takes into account the reference characteristics ahead of the vehicle. The presented solution is based on the definition of an error vector to be driven to zero by the path-following controller. The proposed methodology for controller desig...

While deep reinforcement learning (RL) methods have achieved unprecedented successes in a range of challenging problems, their applicability has been mainly limited to simulation or game domains due to the high sample complexity of the trial-and-error learning process. However, real-world robotic applications often need a data-efficient learning process with safety-critical constraints. In this...

This work is concerned with the design and validation of a vehicle following controller (VFC). The goal of the VFC is to determine appropriate control actions for a highly-actuated electric vehicle such that the longitudinal and lateral motion of a target vehicle is followed. To achieve this goal, a combination of a non-linear guidance law and a model-predictive method is explored. The proposed...

This paper presents a part of research work within the project that aims at developing intelligent, user-friendly and highly safe vehicle. A research framework is proposed that cover the following aspects: control, visual guidance, human-vehicle interaction. Main discussion is focused on the analysis of interaction modes between human and vehicle under various scenarios such as: calling-up vehi...