January 26, 2020

179 words 1 min read

Linux-based RTOS Experimental Platform for Constructing Self-driving Vehicles

Linux-based RTOS Experimental Platform for Constructing Self-driving Vehicles

A holistic design and cost-efficient platform to construct self-driving systems is presented, with an emphasis on Linux-based software architectures for computer vision, control system, and inter-vehi …
Talk Title Linux-based RTOS Experimental Platform for Constructing Self-driving Vehicles
Speakers Jim Huang (CTO, BiiLabs Co., Ltd.), ShaoHua Wang (Graduate student, National Cheng Kung University)
Conference Open Source Summit + ELC Europe
Conf Tag
Location Edinburgh, UK
Date Oct 21-25, 2018
URL Talk Page
Slides Talk Slides
Video

A holistic design and cost-efficient platform to construct self-driving systems is presented, with an emphasis on Linux-based software architectures for computer vision, control system, and inter-vehicle communication. The software is facilitated through the integration of ROS/OpenCV as well as closed-loop control algorithms and Linux in the run-time system. We built a rapid prototyping based on fundamentally open source technologies and hardware under $100, which allows developers to be explored and evaluated in realistic conditions efficiently. Using lane departure and the corresponding performance speedup, we show that our platform reduces the design time, while improving the verification efforts, with the aid of tweaked real-time executives.

algorithm self-driving open source rtos performance computer vision hardware opencv
comments powered by Disqus
Enabling Zephyr on Your Hardware Platform

Enabling Zephyr on Your Hardware Platform

January 24, 2020

Zephyr is a fast-growing, both in terms of contributions and adoption, open source RTOS that is designed to be small, optimized, scalable and secure for resource constrained devices and applications. …
Lightning Talk: Artificial Intelligence the Next Digital Wave for Telcos

Lightning Talk: Artificial Intelligence the Next Digital Wave for Telcos

January 22, 2020

Since five years Artificial Intelligence has entered a new dimension, thanks to the progress of machine and deep learning algorithms, the availability of high performance GPU and labelled Data. Artif …
TuneIn: How to get your jobs tuned while you are sleeping

TuneIn: How to get your jobs tuned while you are sleeping

January 17, 2020

Have you ever tuned a Spark or MR job? If the answer is yes, you already know how difficult it is to tune more than hundred parameters to optimize the resources used. Manoj Kumar, Pralabh Kumar, and Arpan Agrawal offer an overview of TuneIn, an auto-tuning tool developed to minimize the resource usage of jobs. Experiments have shown up to a 50% reduction in resource usage.
Machine learning for continuous integration

Machine learning for continuous integration

December 28, 2019

Your continuous integration process produces torrents of data. Joseph Gregorio explains how to mine that data to drive improvements in your development process and offers an overview of Skiaan open source 2D graphics library that provides common APIs that work across a variety of hardware and software platforms.
Human in the loop: Bayesian rules enabling explainable AI

Human in the loop: Bayesian rules enabling explainable AI

November 25, 2019

Pramit Choudhary explores the usefulness of a generative approach that applies Bayesian inference to generate human-interpretable decision sets in the form of "if. . .and else" statements. These human interpretable decision lists with high posterior probabilities might be the right way to balance between model interpretability, performance, and computation.
Vectorized query processing using Apache Arrow

Vectorized query processing using Apache Arrow

November 19, 2019

Query processing technology has rapidly evolved since the iconic C-Store paper was published in 2005, with a focus on designing query processing algorithms and data structures that efficiently utilize CPU and leverage the changing trends in hardware to deliver optimal performance. Siddharth Teotia outlines the different types of vectorized query processing in Dremio using Apache Arrow.