Luciano Alonso

Ultrasonic Sensors in Urban Traffic Driving-Aid Systems

Currently, vehicles are often equipped with active safety systems to reduce the risk of accidents, most of which occur in urban environments. The most prominent include Antilock Braking Systems (ABS), Traction Control and Stability Control. All these systems use different kinds of sensors to constantly monitor the conditions of the vehicle, and act in an emergency. In this paper the use of ultrasonic sensors in active safety systems for urban traffic is proposed, and the advantages and disadvantages when compared to other sensors are discussed. Adaptive Cruise Control (ACC) for urban traffic based on ultrasounds is presented as an application example. The proposed system has been implemented in a fully-automated prototype vehicle and has been tested under real traffic conditions. The results confirm the good performance of ultrasonic sensors in these systems.

Genetically tuned controller of an adaptive cruise control for urban traffic based on ultrasounds

Currently, Adaptive Cruise Controls on the market can only run at high speeds and distances. This makes them useless in urban traffic, where most traffic accidents occur. In the present work, a controller for an adaptive cruise control (ACC) system for urban traffic based on ultrasonic sensors is optimized using Genetic Algorithms. The use of ultrasonic sensors limits their operating range to distances and speeds typical of urban traffic. The proposed system uses the distance between vehicles as measured by the ultrasonic sensor to estimate the relative velocity and acceleration, thus requiring no interaction with the electronics of the car, except for the actuation on acceleration and braking systems. The system is capable of acting on the acceleration and braking systems throughout all its operating range, thereby constituting an additional emergency braking system. With this system both comfort and safety are improved.

Genetic Optimization of Fuzzy Adaptive Cruise Control for Urban Traffic

The greatest concern in the automotive market is possibly the safety of the occupants of vehicles, pedestrians and other highway users. Cars are increasingly incorporating intelligent systems to improve safety, comfort and energy efficiency.

Compensation of environmental parameters for driving-aid ultrasonic systems in foggy conditions

The use of driving-aid ultrasonic systems in low visibility conditions due to fog, makes it necessary to study the influence of environmental parameters such as temperature, humidity or air velocity on the ultrasonic propagation. The present work tries to construct simple empirical models for velocity and echo amplitude that includes temperature and relative humidity as inputs. We present the results obtained in the modelling of the ultrasonic propagation in environments with variable conditions of humidity and temperature, including foggy conditions

Linear quadratic regulator based Takagi-Sugeno model for multivariable nonlinear processes

In this work, a fuzzy based linear quadratic regulator (FLC-LQR) is developed. The main aim is to obtain an improved performance of non-linear multivariable systems. In this work, the well known weighting parameters approach is applied to optimize local and global approximation and modelling capability of Takagi-Sugeno (T-S) fuzzy model. A multi-input multi-output (MIMO) thermal mixing process system is chosen to evaluate the robustness, effectiveness, accuracy and remarkable performance of estimation approach and the proposed controller. The results obtained show a robust, smooth and well damped response using the proposed FLC-LQR of the system under study.

Optimal Control Using Feedback Linearization for a Generalized T-S Model

In this paper, a fuzzy feedback linearization is used to control nonlinear systems described by Takagi-Suengo (T-S) fuzzy systems. In this work, an optimal controller is designed using the linear quadratic regulator (LQR). The well known weighting parameters approach is applied to optimize local and global approximation and modelling capability of T-S fuzzy model to improve the choice of the performance index and minimize it. The approach used here can be considered as a generalized version of T-S method. Simulation results indicate the potential, simplicity and generality of the estimation method and the robustness of the proposed optimal LQR algorithm.

Self-tuning PID controller for autonomous car tracking in urban traffic

In this paper an on line self-tuned PID controller is proposed for the control of a car whose goal is to follow another one, at distances and speeds typical in urban traffic. The best-known tuning mechanism is perhaps the MIT rule, due to its ease of implementation. However, as it is well known, this method does not guarantee the stability of the system, providing good results only for constant or slowly varying reference signals and in the absence of noise, which are unrealistic conditions. When the reference input varies with an appreciable rate or in presence of noise, eventually it could result in system instability. In this paper an alternative method is proposed that significantly improves the robustness of the system for varying inputs or in the presence of noise, as demonstrated by simulation.

Genetically optimized controller for urban traffic emergency braking system based on ultrasonic sensors

In this work, an original controller for an emergency braking system for urban traffic based on ultrasonic sensors is presented, which is optimized by means of a Genetic Algorithm. The main advantage over similar controllers available in the market today, is that in order to maintain a safe distance to the preceding vehicle, it is not necessary to know the speed of either the controlled vehicle or the vehicle ahead. The only information used by the proposed controller is the distance between vehicles, which is measured by an ultrasonic system. In this way, the interaction with the electronics of the vehicle is avoided, except for the action on the braking system. Moreover, the use of ultrasonic sensors also makes possible the detection of pedestrians on the road, resulting in the avoidance of accidents, or at least lessening their consequences.

Car Crash Prevention Expert System in Urban Traffic Based on Ultrasounds

Abstract Abstract The system presented is an expert system capable of taking decisions to avoid collisions in urban traffic or to minimize the damages, due to a lack of attention or some other unexpected situation. It is based on the use of simple and inexpensive ultrasonic transducers as sensing elements for the driver support. The rule-based expert system is able to detect a potentially dangerous situation and act accordingly on the brake. Simulations demonstrates the validity of the system to improve the active safety of vehicles.