The impact of 5G technology on the development of autonomous driving
Autonomous driving is the product of the deep integration of the automotive industry with the new generation of information technologies such as artificial intelligence, Internet of Things, and high-performance computing, including Google, Baidu, Ali, Toyota, and Ford. All the world's top Internet and giant manufacturers are planning to develop autonomous driving. , it is the main direction of the development of intelligence and networking in the field of global automobile and transportation, and it has become a strategic commanding height for countries to compete for, and the core technology of autonomous driving has also developed rapidly in recent years.
Cars are an important scenario for 5G applications. The editor of the automotive communication module circuit board has learned that in the 4G era, our understanding of the Internet of Vehicles is the in-vehicle entertainment system, while in the 5G era, the Internet of Vehicles means V2X (Vehicle to X, everything connected to the car). When the vehicle is interconnected with the entire transportation system (including but not limited to other traffic participants, traffic lights, and road information), each vehicle can obtain the speed and steering information of surrounding vehicles in real time, so as to avoid accidents; Real-time traffic information can be obtained, and the traffic management system can adjust traffic signals according to real-time traffic conditions, thereby greatly reducing congestion.
5G technology will bring great help to autonomous driving. The current mainstream autonomous driving technology route completely relies on the vehicle's own perception ability. The vehicle must be equipped with a series of sensors such as lidar worth hundreds of thousands of yuan. However, the detection distance and accuracy still need to be improved. At the same time, the unpredictability of blind spots and other vehicles means the existence of risks.
After getting the help of 5G technology, in many cases, the vehicle no longer needs to actively perceive other vehicles, because the other party's information has already been transmitted to your car through the network, you and your car do not need to see it, you can know it exists. In such a "god's view", the importance of sensors is greatly reduced, but autonomous driving is therefore simpler, cheaper, more reliable, and safer.
identification technology
The recognition technology mainly includes three aspects, road surface, static objects and dynamic objects. For dynamic objects, it is necessary to not only detect but also track their trajectory, and predict the next trajectory (position) of the object according to the tracking results. This is essential in urban areas, especially in urban areas of China. The most typical scene is Wudaokou in Beijing: if you stop when you see pedestrians, you will never be able to pass through Wudaokou. Pedestrians almost never stop walking past the car. The human driver will roughly estimate the next step based on the pedestrian's movement trajectory, and then calculate the safe space (path planning) based on the speed of the vehicle. Bus drivers are best at this path. Driverless cars have to do the same. It should be noted that this is the tracking and prediction of the trajectory of multiple moving objects, which is much more difficult than a single object. This is MODAT (Moving Object Detection and Tracking). It is also the most difficult technology for driverless cars.
V2X technology
Vehicle wireless communication technology (Vehicle to Everything, V2X) is a new generation of information communication technology that connects the vehicle with everything, where V represents the vehicle and X represents any object that interacts with the vehicle. Currently, X mainly includes vehicles, people, Traffic roadside infrastructure and networks. The circuit board factory learned that the information modes of V2X interaction include: Vehicle to Vehicle (V2V), Vehicle to Infrastructure (V2I), Vehicle to Pedestrian (V2P), The interaction between vehicle and network (Vehicle to Network, V2N). V2V technology allows vehicles to prevent accidents by forwarding real-time information about themselves and ahead, thereby reducing driving time and ultimately improving the traffic environment and reducing traffic congestion.
V2I technology helps vehicles and roadside traffic facilities to realize data exchange through wireless means. The main applications include intersection safety management, vehicle speed limit control, electronic toll collection, transportation safety management, and road construction and height limit warning. This technology will promote the intelligence of traffic facilities, including no-entry lights, weather information systems and other traffic facilities can be evolved into intelligent traffic facilities that can identify high-risk situations and automatically take warning measures through various algorithms.
At present, the V2X field is divided into two standard and industry camps, Dsrc and C-V2X. In the domestic market, because it has the world's largest 4G LTE network and mature industry chain, and does not have much accumulation in Dsrc technology, some analysts believe that the development of domestic V2X will be inclined to C-V2X.
Human-computer interaction technology
Human-computer interaction technology, especially voice control, gesture recognition and touch screen technology, will be widely adopted in the global future car market. The ultimate purpose of the large screen design of human-computer interaction for autonomous vehicles is to provide a good user experience and enhance the user's driving pleasure or operating experience during driving. It pays more attention to driving safety, which makes the design of the human-machine interface necessary. There is a balance between a good user experience and security, with security always coming first. The human-machine interface of autonomous vehicles should integrate many functions such as vehicle control, function setting, infotainment, navigation system, car phone, etc., so as to facilitate the driver to quickly query, set, and switch various information of the vehicle system, so that the vehicle can achieve Ideal running and manoeuvring condition. In the future, the in-vehicle information display system and smart phones will be seamlessly connected, and there will be a variety of input methods provided by the human-machine interface. By using different technologies, consumers can freely switch according to different operations and functions.
High-precision map
High-precision maps have accurate vehicle position information and rich road element data information, which can help cars predict complex road information, such as slope, curvature, heading, etc. Compared with the traditional one, it has higher real-time performance. Due to frequent changes in the road surface, such as road refurbishment, wear or repainting of marking lines, changes in traffic signs, etc., these changes must be reflected on the high-precision map in time. The high-definition map will place more emphasis on the three-dimensional model and accuracy of the space, reducing the accuracy from the meter level to the centimeter level, and must display every feature and condition on the road surface very accurately.
decision technology
Decision-making is the core technology that reflects the intelligence of unmanned driving, which is equivalent to the brain of autonomous vehicles. It plans the current vehicle by comprehensively analyzing the information provided by the environmental perception system and the results of routing and addressing from high-precision maps. planning, orientation planning, acceleration planning, etc.) and generate corresponding decisions (follow, change lanes, park, etc.). The PCB factory believes that the planning technology also needs to consider the mechanical characteristics, dynamic characteristics and kinematic characteristics of the vehicle. Commonly used decision-making techniques include expert control, hidden Markov model, Bayesian network, fuzzy logic, etc.
Positioning Technology
In addition to GPS and inertial sensors, we usually use LiDAR point cloud and high-precision map matching, as well as positioning methods such as visual odometry, so that various positioning methods can correct each other to achieve more accurate results. With the development of autonomous driving, positioning technology will also be continuously optimized.
At present, the technology of autonomous driving is basically derived from robots. An autonomous car can be regarded as a wheeled robot plus a comfortable sofa. Positioning and path planning are a problem in robotic systems. Without positioning, the path cannot be planned. Centimeter-level real-time positioning is one of the biggest challenges of autonomous driving at present. For robot systems, positioning mainly depends on the cross-comparison between SLAM and Prior Map.
Communication Security Technology
When autonomous vehicles are connected to the grid through the vehicle network, it also brings information security issues. In the application, the information of each vehicle and its owner will be transmitted to the network anytime and anywhere to be sensed. The information in the network is easy to be stolen, interfered or even modified, which directly affects the security of the intelligent networked vehicle system. Therefore, in the intelligent networked vehicle, we must pay attention to the research of information security and privacy protection technology.