How does an unmanned vehicle "Google"



    The former secret Google project is now literally appearing in public: the company received a license for test trips on public roads in Nevada , and before that , everyone was invited for a test trip in an enclosed area .

    At the moment, the Toyota Prius fleet of robotic cars belonging to the search giant has rewound more than 300 thousand kilometers in urban surroundings, on busy roads and mountain roads with only partial human intervention. The project is still far from entering the market, but unmanned golf cards have been installed on Google’s own campus in Google, which clearly demonstrate how new technology can change the world in the near future.



    Last September, Stanford University professor of computer science Sebastian Tran , who leads the development, and Chris Urmson, a Google engineer, talked about the main ideas of the project at the International Conference of Intelligent Robots and Systems of the Institute of Electrical and Electronics Engineers in San Francisco. They explained how the car worked and showed several videos and road tests, including a small fragment of how the on-board computer “sees” other vehicles, pedestrians, and traffic lights.



    According to Urmson, technical project manager, the core of the system is a 64-beam laser range finder manufactured by Velodine , installed on the roof of the car. The device helps to generate a detailed volumetric map of the surrounding space. The machine then combines laser measurements with high-precision maps of the world and produces various types of data models that allow you to drive while avoiding obstacles and legal problems. Also on board are other sensors, including four radars on the front and rear bumpers, a camera next to the rearview mirror; The sensor of the GMP system, the inertial measurement unit and the wheel sensor, which determine the position of the vehicle and track the movement.



    It is interesting to note some details. Firstly, Google’s development is highly dependent on carefully designed maps of the Earth’s surface, which, according to Urmson, is an essential condition for accurately locating a machine. Using a global navigation system can give an error of several meters.

    Secondly, before sending a car for an unmanned race, Google engineers travel the route on their own one or more times to collect information about the surrounding area. When driving offline, the car compares data with previous conditions, which allows you to separate pedestrians from stationary objects such as mailboxes or poles. In the previous video, the result was noticeable. At one point, the car stopped at an intersection, and after a green traffic light, it gave way to pedestrians before turning left and continuing on.



    Sometimes a drone is forced to be more aggressive. For example, while driving through an intersection, he passes other cars according to the rules of the road, but if other vehicles do not reciprocate, he will lightly rush forward to show his intention. Without programming this behavior in the real world, the robot will not be able to ride.

    Obviously, the Google engineers like working on the project - look at Urmson’s contented face in the 13th minute, when he, sitting in the driver’s seat, watches as the drone drives the company parking lot, creaking tires at every turn. But the project has a serious intention: Tran and many of his colleagues, including the founding fathers of Google, believe that smart cars will make driving safer and more efficient: cars will drive closer to each other, which will increase the amount of free places on the roads. The program reacts faster than a person, which will help to avoid accidents and save thousands of lives.

    Urmson also proposed a scenario in which vehicles become a common resource, a service that people can use if necessary. For the appearance of the car, it will be enough just to choose the appropriate option in the smartphone, and during the trip it will be possible to relax in the driver's seat - you do not need to drive a car. At the conference, a video of the Caddy Beta concept was demonstrated, in the role of common cars - golf cards. They use a simpler filling than for Toyota Prius samples: sensors on vehicles interact with sensors placed in the environment to determine the position and “learn” about the movement of others.



    Tran and Urmson admit that there are still many unsolved problems ahead: improved reliability, legal issues of responsibility, but that does not stop them. As Tran said, transport issues that others consider unprofitable seem promising to them.

    Also popular now: