Search

In this paper, we present an autonomous vehicles (AV) research testbed with photo-realistic visualisation and simulation capability. Compared to Oak Ridge National Labs CAVE system, Microsoft's AirSim, and MATLAB's Vehicle Dynamics Blockset approach, the key difference is a decoupled and modular system architecture which allows developers to focus on only one aspect of the whole system and be productive with minimal training. Basically, the proposed system has a game engine, an external hardware accelerator for vehicle dynamical models, and a GPU equipped computer to run the AI algorithms. Our vision is to have all vehicle dynamical models to be built in MATLAB/Simulink and run on a hardware accelerator like Speedgoat, which is a leading software and hardware framework for scientific system modelling and hardware in the loop simulation. The proposed photo realistic visualization environment is Unreal Engine based, and all AI models are keras based. This decoupled system architecture allows all vehicle dynamical models and AI decision making to be implemented outside the Unreal Engine, while the game engine doing all collision detections and reporting. Similarly, all traffic and pedestrian movement stochastic models can be implemented outside the game engine, allowing a framework agnostic approach to be used throughout the whole system. [ABSTRACT FROM AUTHOR]

In this paper, we consider modelling of a hybrid vehicle for autonomous vehicles (AV) algorithm development, simulation, and verification. Our research platform is a Ford Fusion plugin hybrid vehicle with drive-by-wire conversion done by Dataspeed Inc. The vehicle is equipped with steering, throttle, break, wheel speed and several other sensors and actuators all connected to the vehicle CAN network. Furthermore, we have lidar, radar and multiple camera sensors, and a vibration resistant GPU desktop. We will drive the research vehicle both on the campus and on local highways and generate a rich dataset for various modelling studies. Our preliminary test results show that existing hardware is capable of recording all relevant CAN network activity without any data packet loss. We have explored linear differential equation-based models including the air friction but planning to explore both nonlinear and AI based more complex models. All of these vehicle models are planned to be executed on an external hardware accelerator, Speedgoat Performance Real-Time Target Unit, with full MATLAB/Simulink integration. In the full version of the paper, we will present both experimental results and provide a detailed comparison between different modelling alternatives, computational demand, and modelling accuracy. [ABSTRACT FROM AUTHOR]