Awesome Self Driving Cars: Awesome

A curated list of awesome self driving cars resources, inspired by many including awesome-autonomous-vehicles.

Table of Contents

Bascis

Developing self driving cars requires many skill which mostly revolves around mobile robotics (percption, localization, path planning, controls, simulations) but can be very different, like end-to-end Deep Learning. I also sometimes requires knowledge of vehicle design, safety ...

Basic Software Library

  1. ROS - Platform for easy development, visulization, logging and lots of community code in this platform
  2. OpenCV - Computer Vision
  3. PCL - 3D point cloud processing

Datasets

  • KITTI Vision Benchmark Suite - 6 hours of traffic scenarios at 10-100 Hz using a variety of sensor modalities such as highresolution
  • Udacity - Udacity driving datasets released for Udacity Challenges. Contains ROSBAG training data. .
  • Oxford's Robotic Car - over 100 repetitions of a consistent route through Oxford, UK, captured over a period of over a year. The dataset captures many different combinations of weather, traffic and pedestrians, along with longer term changes such as construction and roadworks.
  • Caltech Pedestrians - approximately 10 hours of 640x480 30Hz video taken from a vehicle driving through regular traffic in an urban environmen

Dataset Collection

Open Source Software

Platforms/Framework

Calibration

Camera

Lidar and Camera

Visualization

Mobile Apps (Android)

Mapping/Localizing/Odometry

Perception

Using Deep Learning

Obejct Detection

Related Links