A Low-Cost Hardware-in-the-Loop Agent-Based Simulation Testbed for Autonomous Vehicles

We have developed a flexible and low-cost hardware testbed for autonomous vehicle research and education. The testbed provides the ability to autonomously control multiple small vehicles within a 1200×900 mm environment and is entirely open source with regard to both hardware and software, making it easily reproducible. An agent-based approach is used for vehicle control, meaning that different agent models can be applied to each vehicle as desired for simulation. GPS-like position information is provided to the controller in real-time using a global computer vision system. Using our figure-of-eight test environment, we have demonstrated that our system can support six cars driving smoothly around the track whilst avoiding collisions with each other.