Due to the increase in traffic, road congestion has gone up. Vehicle platooning is a possible way to increase the capacity of a given road, by decreasing the distance between the vehicles in the platoon. At the moment, the control of vehicle platoons is commonly done using PID controllers. The advantage of this is that it requires little computational resources. With improvements in computing technology in recent years, the possibility of using a more computationally costly method has opened up. But, parallel with that, dealing with inherently unmodeled dynamics and large parameter variations or faults, is a challenging task while
controlling any system. Classical control techniques do not provide satisfactory responses in most of the settings, and often external supervision systems have to be designed to handle the faults. Recent research has shown that active inference, a unifying neuroscientific theory of the brain, bares the potential of intrinsically coping with strong uncertainties in the system, mimicking the adaptability capabilities of humans. However, the current state-of-the-art regarding active inference in vehicle platooning is non-existent.

This thesis presents a novel active inference controller for adaptive cruise control systems and as a general adaptive fault tolerant solution for control of vehicle platoon. First, we demonstrate the applicability of active inference in classical control scheme in order to control a platoon of vehicles. Second, we verify that the proposed active inference framework is computationally efficient and with high performance against a benchmark model. Third, we access the adaptive properties of the designed framework in presence of large parameter variations and actuator faults. This work reveals that not only active inference is applicable in vehicle platooning, but it also outperforms the benchmark model in some characteristics, and it allows to deal efficiently with parameter variations and actuator faults. This thesis represents a first step towards the implementation of the current state-of-the-art of active inference for vehicle platooning, and it lays the foundations for further research in this direction.