Active Stereo Vision for Precise Autonomous Vehicle Control

2020 ◽  
Vol 2020 (16) ◽  
pp. 258-1-258-6
Author(s):  
Michael Feller ◽  
Jae-Sang Hyun ◽  
Song Zhang

This paper describes the development of a low-cost, lowpower, accurate sensor designed for precise, feedback control of an autonomous vehicle to a hitch. The solution that has been developed uses an active stereo vision system, combining classical stereo vision with a low cost, low power laser speckle projection system, which solves the correspondence problem experienced by classic stereo vision sensors. A third camera is added to the sensor for texture mapping. A model test of the hitching problem was developed using an RC car and a target to represent a hitch. A control system is implemented to precisely control the vehicle to the hitch. The system can successfully control the vehicle from within 35° of perpendicular to the hitch, to a final position with an overall standard deviation of 3.0 m m of lateral error and 1.5° of angular error.

2012 ◽  
Vol 36 (4) ◽  
pp. 281-288 ◽  
Author(s):  
Paolo Zicari ◽  
Stefania Perri ◽  
Pasquale Corsonello ◽  
Giuseppe Cocorullo

2009 ◽  
Vol 2009 (0) ◽  
pp. _1P1-C15_1-_1P1-C15_3
Author(s):  
Shota SHIRAYAMA ◽  
Ryusuke UEKI ◽  
Mitsuharu KOJIMA ◽  
Yoshinao SODEYAMA ◽  
Kei OKADA ◽  
...  

2009 ◽  
Vol 2009 (0) ◽  
pp. _1P1-C14_1-_1P1-C14_4
Author(s):  
Shota SHIRAYAMA ◽  
Ryusuke UEKI ◽  
Mitsuharu KOJIMA ◽  
Yoshinao SODEYAMA ◽  
Kei OKADA ◽  
...  

2021 ◽  
Author(s):  
Jamin Islam

For the purpose of autonomous satellite grasping, a high-speed, low-cost stereo vision system is required with high accuracy. This type of system must be able to detect an object and estimate its range. Hardware solutions are often chosen over software solutions, which tend to be too slow for high frame-rate applications. Designs utilizing field programmable gate arrays (FPGAs) provide flexibility and are cost effective versus solutions that provide similar performance (i.e., Application Specific Integrated Circuits). This thesis presents the architecture and implementation of a high frame-rate stereo vision system based on an FPGA platform. The system acquires stereo images, performs stereo rectification and generates disparity estimates at frame-rates close to 100 fpSi and on a large-enough FPGA, it can process 200 fps. The implementation presents novelties in performance and in the choice of the algorithm implemented. It achieves superior performance to existing systems that estimate scene depth. Furthermore, it demonstrates equivalent accuracy to software implementations of the dynamic programming maximum likelihood stereo correspondence algorithm.


Sign in / Sign up

Export Citation Format

Share Document