Ford Releases Its Autonomous Vehicle Test Data

Ford releases your data


One of the most promised and delayed inventions of recent years is autonomous vehicles. Beyond the promises of the highly touted Elon Musk, and the time and money invested by Google and Uber, among other large companies, the goal seems to be still a long way off.

It is likely that the problem is not hardware but software. There is a lot of information that must be able to process the control unit of each vehicle to ensure both safety of the passengers as of the people who are in the other vehicles and pedestrians

For this massive amounts of data required that can only be obtained by doing countless tests under real conditions. Vehicles equipped with cameras and LiDAR are needed.

To speed up the research process in autonomous vehicles, some manufacturers are sharing the data they have with competitors and academics.

Ford releases its data obtained by multiple vehicles in Detroit

Thus Ford is publishing a comprehensive data set obtained during their own tests to assist academics and researchers in their own projects. This had already been done by other competitors such as Waymo.

As explained by the company

There is no better way to promote research and development than to ensure that the academic community has the data it needs to create effective autonomous vehicle algorithms.

The material shared by Ford was collected in the span of one year, and was generated by multiple self-driving research vehicles. It includes LiDAR sensor and camera data, GPS and trajectory information, as well as 3D point cloud and ground reflectivity maps.

LIDAR, is the acronym in English for Detection and scope of laser images. It is a device that allows to determine the distance from a laser emitter to an object or surface using a beam. The distance to the object is determined by measuring the delay time between the emission of the pulse and its detection through the reflected signal.

Point clouds are sets of vertices in a three-dimensional coordinate system that are commonly identified as X, Y, and Z coordinates and serve to represent the outer surface of an object.

A three-dimensional laser scanner is commonly used to create a point cloud. This laser automatically measures a large number of points on the surface of an object, and generating a data file with a point cloud. The point cloud represents the set of points that the device has measured.

Ford you are sharing your own tools to visualize that data.

The importance of the contribution of the company is not only in the period of time but also in theThe data was collected in a variety of weather conditions, including rain, sun, clouds, and snow.

Since the geographic area chosen is the Detroit metropolitan area, The vehicles had to travel through dense urban areas, highways, tunnels, residential neighborhoods, airports, construction zones and pedestrian activity. That is, a reasonable representation of the various scenarios in which future autonomous vehicles will have to circulate.

Also, this data comes from multiple vehicles, which will allow researchers to analyze the same situation from two points of view. In this way, it will be possible to investigate the possibility of autonomous units sharing information with each other in real time to make better decisions without the need to connect to a central server.

In the last ten years, being data set is available for academic use under la Creative Commons license Attribution-NonCommercial-ShareAlike 4.0 International License. The company promises to publish regular updates.

To use the visualization tools recommend Ubuntu 16.04, the ROS Kinectic robotics framework and a laptop with at least 32 GB.

Ford wanted to launch its first line of self-driving cars in 2021, but, using the COVID-19 excuse, put it off for another year.

In any case, it may take us a long time to see them in our countries. Due to the information that these types of vehicles need to be able to circulate guaranteeing the safety of people, it is likely that a long prior process of recognition of scenarios is needed. Because of the cost, this will require the collaboration of companies and governments. And, I don't think the professional drivers unions will accept it unopposed.


Leave a Comment

Your email address will not be published. Required fields are marked with *

*

*

  1. Responsible for the data: AB Internet Networks 2008 SL
  2. Purpose of the data: Control SPAM, comment management.
  3. Legitimation: Your consent
  4. Communication of the data: The data will not be communicated to third parties except by legal obligation.
  5. Data storage: Database hosted by Occentus Networks (EU)
  6. Rights: At any time you can limit, recover and delete your information.