Follow
Subscribe

An Introduction to Self-Driving Cars

Home > News > Content

【Summary】A self-driving car (driverless, autonomous, robotic car) is a vehicle that is capable of sensing its environment and navigating without human input.

Original Jing Yi    Oct 25, 2016 7:45 PM PT
An Introduction to Self-Driving Cars
Yi Jing

By Yi Jing

What are self-driving cars? This is a seemingly innocuous question about a complex machine.

To begin, a self-driving car (driverless, autonomous, robotic car) is a vehicle that is capable of sensing its environment and navigating without human input. Self-driving cars can detect environments using a variety of techniques such as radarGPS and computer vision.

Advanced control systems interpret sensory information to identify appropriate navigational paths, as well as obstacles and relevant signage. Self-driving cars have control systems that are capable of analyzing sensory data to distinguish between different cars on the road. This is very useful in planning a path to the desired destination.

Let's take a look at one kind of self-driving car in detail the Google self-driving vehicle. Google's self-driving cars all have test drivers at the wheel. They have been developed by Google X as a part of its project to develop technology for electric cars.

The project team has equipped a number of different types of cars with the self-driving equipment; including the Toyota PriusAudi TT, and Lexus RX450h. Google has also developed their own custom vehicle which is assembled by Roush Enterprises and uses equipment from BoschZF LenksystemeLG, and Continental.

Google's robotic cars have about $150,000 in equipment, including a $70,000 LIDAR system. The range finder mounted on the top is a Velodyne 64-beam laser. This laser allows the vehicle to generate a detailed 3D map of its environment. The car then takes these generated maps and combines them with high-resolution maps of the world, producing different types of data models that allow it to drive itself. As of June 2014, the system works with a very high definition inch-precision map of the area the vehicle is expected to use, including how high from the ground the traffic lights are. In addition to on-board systems, some computation is performed on remote computer farms.

Based on Google's own accident reports, their test cars have been involved in 14 collisions. It was not until 2016 that the car's software caused a crash. Additionally, Google maintains monthly reports that include any traffic incidents that their self-driving cars have been involved in.

Google is required by the California DMV to report the number of incidents during testing where the human driver took control. Some of these incidents are not reported by Google when simulations indicate the car should have coped on its own. There is some controversy concerning this distinction between the driver-initiated disengagements Google reports and those it does not report.

Since the cars rely primarily on pre-programmed route data, they do not obey temporary traffic lights. And in some situations, they revert to a slower "extra cautious" mode in complex unmapped intersections. The vehicle has difficulty identifying when objects, such as trash and light debris, are harmless, causing the vehicle to veer unnecessarily. Additionally, the technology cannot spot some potholes or discern when humans, such as a police officer, are signaling the car to stop.

Google wants to design a new prototype of its driverless car. This would be a car that has no steering wheel, no gas or brake pedals and thus is 100% autonomous.

Prev                  Next
Writer's other posts
Comments:
    Related Content