An FPGA implementation of two-step trajectory planning for automatic parking

Ertuğrul, Halil
The main distinguishing feature of different automatic parking technologies is the method that determines a proper collision-free path. Hereby, the length of the path, the number of halts and the computation time for finding such path are the most relevant performance criteria. In this thesis, a two-step trajectory planning algorithm for automatic parking is considered. The algorithm finds a path that meets all kinematic constraints of the car from its initial position, to the target position while requiring a small number of vehicle halts. It first calculates a collision-free path from the initial position to the target position by maximizing the distance from any obstacle. Since this path usually does not respect the kinematic constraints of the vehicle, a second algorithmic step computes a path that is suitable for the vehicle. In both steps, a set of 48 optimal trajectories is used for the path computations and distance evaluations. Since the trajectory planning algorithm requires complex geometric calculations, it a microprocessor is not suitable for practicable computation times. Hence, an FPGA is chosen for the realization of the trajectory planning algorithm on hardware, enabling parallel processing of the trajectory computations. This thesis describes the hardware design for implementing the trajectory planning algorithm on FPGA. The performed analysis both via simulations and implementation on hardware shows that a speedup in the trajectory computation is obtained. Different from other hardware realizations that are restricted to either only parallel parking or vertical parking, our implementation can handle general parking situations. In addition, our implementation increases the driver comfort by reducing the number of vehicle halts.


An Adaptive Approach for Road Boundary Detection Using 2D LIDAR Sensor
Demir, S. O.; Ertop, T. E.; Koku, Ahmet Buğra; Konukseven, Erhan İlhan (2017-11-18)
Robotic ground vehicles are commonly used in various road conditions for performing special tasks with different levels of autonomy. This requires the robots to possess a certain degree of perception about the road conditions up ahead and make plans accordingly. It is essential for the robots to be able to quickly adapt their perception for various road conditions they operate. In this paper, an adaptive method for road boundary extraction using 2D LIDAR sensor is presented. A three-stage detection algorith...
An FPGA based high performance optical flow hardware design for autonomous mobile robotic platforms
Gültekin, Gökhan Koray; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2010)
Optical flow is used in a number of computer vision applications. However, its use in mobile robotic applications is limited because of the high computational complexity involved and the limited availability of computational resources on such platforms. The lack of a hardware that is capable of computing optical flow vector field in real time is a factor that prevents the mobile robotics community to efficiently utilize some successful techniques presented in computer vision literature. In this thesis work,...
FPGA implementation of license plate detection and recognition
Sarıkavak, Serap; Bulut, Mehmet Mete; Akar, Gözde; Department of Electrical and Electronics Engineering (2013)
In this thesis, license plate detection and recognition system based on Gabor approach is proposed and recognition part of the system is implemented on the FPGA platform. The purpose of this project is to develop a system that extracts license plate region from image, taken from proposed distance, and recognizes the characters on this region. For this project, techniques on the literature are investigated and some of them are implemented. In the localization of the plate region, color space conversion, imag...
Mini autonomous car architecture for urban driving scenarios
Karabulut, Gökhan; Can, Tolga; Department of Computer Engineering (2019)
Autonomous cars capable of driving in city traffic have been long studied in architectures decomposed into perception, planning, and control components. Recent advances in deep learning techniques considerably contributed to the perception component of this approach. These techniques also laid the groundwork for the progress of other approaches such as end-to-end learning of steering commands and driving affordances from camera images. Though these approaches are promising to simplify the overall architectu...
A Bayesian approach to jointly estimate tire radii and vehicle trajectory
Özkan, Emre; Gustafsson, Fredrik (2011-10-05)
High-precision estimation of vehicle tire radii is considered, based on measurements on individual wheel speeds and absolute position from a global navigation satellite system (GNSS). The wheel speed measurements are subject to noise with time-varying covariance that depends mainly on the road surface. The novelty lies in a Bayesian approach to estimate online the time-varying radii and noise parameters using a marginalized particle filter, where no model approximations are needed such as in previously prop...
Citation Formats
H. Ertuğrul, “An FPGA implementation of two-step trajectory planning for automatic parking,” M.S. - Master of Science, Middle East Technical University, 2013.