Design and implementation of a neuro-fuzzy system for longitudinal control of autonomous vehicles
ABSTRACT The control of nonlinear systems has been putting especial attention in the use of Artificial Intelligent techniques, where fuzzy logic presents one of the best alternatives due to the exploit of human knowledge. However, several fuzzy logic real-world applications use manual tuning (human expertise) to adjust control systems. On the other hand, in the Intelligent Transport Systems (ITS) field, the longitudinal control (throttle and brake management) is an important topic because external perturbations can generate uncomfortable accelerations as well as unnecessary fuel consumption. In this work, we utilize a neuro-fuzzy system to use human driving knowledge to tune and adjust the input-output parameters of a fuzzy if-then system. The neuro-fuzzy system considered in this work is ANFIS (Adaptive-Network-based Fuzzy Inference System). Results show several improvements in the control system adjusted by neuro-fuzzy techniques in comparison to the previous manual tuned controller, mainly in comfort and efficient use of actuators.
- Iet Software/iee Proceedings - Software. 01/1974;
- [show abstract] [hide abstract]
ABSTRACT: This paper presents an active suspension system for passenger cars, using adaptive critic-based neurofuzzy controller. The model is described by a system with seven degrees of freedom. The car is subjected to excitation from a rode surface and wheel unbalance. The main superiority of the proposed controller over previous analogous fuzzy logic controller designed approaches, e.g., genetic fuzzy logic controller, is its online tuning characteristic and remarkable reduced amount of computations used for parameter adaptation, which makes it desirable for real time applications. Considering the simplicity of this controller and its independence from the system model, this control method has the advantage of online learning and control, and can be applied to a large variety of systems. The simulation results show that the proposed controller proves to be very effective in the vibration isolation of the vehicle body.Mechatronics and its Applications, 2009. ISMA '09. 6th International Symposium on; 04/2009
- [show abstract] [hide abstract]
ABSTRACT: Artificial intelligence techniques applied to control processes are particularly useful when the elements to be controlled are complex and can not be described by a linear model. A trade-off between performance and complexity is the main factor in the design of this kind of system. The use of fuzzy logic is specially indicated when trying to emulate such human control actions as driving a car. This paper presents a fuzzy system that cooperatively controls the throttle and brake pedals for automatic speed control up to 50km/h. It is thus appropriate for populated areas where driving involves constant speed changes, but within a range of low speeds because of traffic jams, road signs, traffic lights, etc. The system gets the current and desired speeds for the car and generates outputs to control the two pedals. It has been implemented in a real car, and tested in real road conditions, showing good speed control with smooth actions resulting in accelerations that are comfortable for the car's occupants.Robotica. 01/2010; 28:509-516.