Design of a semi-autonomous parking assist system (original) (raw)

A Rule-based Controller Simulation for an Autonomous Parallel Parking of a Car-like Robot using Laser Sensors

In the last few years, a plenty of tools and methods developed in the Mobile Robotics field have shown a great potencial for the automotive area. Due to this, the interest of researchers for applications in this subject has increased. Therefore, many researches have addressed the problem to embed smart systems in touring vehicles to perform daily tasks, such as urban driving, obstacle avoidance, active cruise control in heavy traffic situation, automatic parallel parking, etc. This work aims to develop a rule-based control system responsible for driver handling assistance, in the special case of reaching a robust control capable of doing a perfect automatic parallel parking. The studies involving the kinematics of the vehicle and the sensors modelling were previously carried out. Then, a simulation environment has been designed in C# language with the Visual C#2008 IDE in order to validate the finite state automaton algorithm. Based on the data of the front and rear laser sensors, the automatic mode of the simulation environment controls the vehicle by generating acceleration and steering commands. The manual mode returns the control of the vehicle to the user. So far, the simulations results have shown that a finite state automaton is capable of parallel parking the car, based on two sensors data.

Automated Car Parking Assist System Based on Video

INTERNATIONAL JOURNAL OF IMAGING SCIENCE AND ENGINEERING (IJISE), 2010

This paper such as the automated parking assist system based on video on model cars and car parks, it indicates that the probability of the utilization of a camera to monitor car parks is feasible. This is seen in the results that indicate the accuracy in determining the presence of a car in a parking bay or the information that can be provided on the location of the available parking bays. The development of the automated parking assist system based on video shows the feasibility of utilizing simple cameras such as video cameras to monitor car parks and provide information about the available parking areas. This consists of the following steps. First, the video is captured using a video camera which is in AVI (Audio Video Interleave) format, then converting it into the MPEG (Moving Picture Experts Group) format using mpeg converter. Second, the parking space is read and extract the features of the reference image and video image. Third, rank correlation method will be used to detect the available parking space depend on the correlation threshold. If the correlation threshold is high (here 1), it indicates there is no vehicle occupied in the parking area. If it is 0.5, it indicates one vehicle occupied in the parking area. This paper shows that the initial work done here has an accuracy that ranges from 97% to 100% for a 2space car park.