Smart driving is no doubt in the general direction, but if there is no hardware, software, etc., everything is empty talk. The back-end supply market has also become a hot favorite. At the CCF-GAIR conference on smart driving, these back-end suppliers will tell us what they have done for the future of smart driving.
(From left to right) Pisa Chunlin, Secretary-General of Telematics Industry Application Alliance (TIAA), Qiu Chunxin, CEO of Sagitar Creativity, Liu Guoqing, CEO of Minieye, Tang Jinsong, General Manager of Quanergy China, Yin Shangzhi, Chief Data Scientist of Huayuan Data, and QNX Corporation Greater China General Manager Zhang Renjie.
Pang Chunlin: Introduce your company.
Qiu Chunxin: Sagitar Creativity is a company that specializes in laser radar. In 2014, we introduced the first laser radar product, which is mainly used in the field of static mapping and 3D modeling. At present, our focus is on R&D and providing high-performance, mass-produced unmanned laser radars.
Liu Guoqing: Minieye was established in April 2013. We focus on the perception of automotive technology. We hope to contribute to the automation and unmanned perception of automobiles.
Tang Jinsong: Our company is Quanergy, headquartered in Silicon Valley, USA. Focusing on the development of high-performance laser radar and related software that can be used for mass production in the future, we have in-depth cooperation with many manufacturers. Many of our existing mechanical laser radar M8 are also in use. Our forthcoming breakthrough solid-state laser radar, the S3, will provide the industry with high-performance, high-reliability laser radars with true energy production.
Yin Xiangzhi: We are currently hosting an artificial intelligence contest. During the competition, we will provide 50,000 driving recorders to experience and carry out competitions related to smart driving algorithms.
Zhang Renjie: Our operating system is widely used in various familiar models, including BMW, Volkswagen, etc. We have a lot of contributions in the new generation of automatic driving.
Pang Chunlin: What do you think about Tesla's accidents in China and the United States?
Qiu Chunxin: This reflects the current deficiencies of Tesla's automatic driving, perhaps because laser radar has not yet been used, so the lack of perception of the white body caused misjudgments.
Liu Guoqing: Tesla has a problem with the definition of functional requirements for autonomous driving. You need to clearly define the scene of automatic driving, and continue to experiment to verify these features. Another point is to have a cloud mechanism, through the integration of multiple sensors - not only radar, but also lidar, one problem, the other can be connected.
Tang Jinsong: From the technical point of view, it is because its system is not reliable enough to see strong light and side detection. In the future, the need to ensure the safety and reliability of the technology is to add a laser radar and use sensor fusion. Going to the fourth and fifth level goals, some mechanisms are set on the system to ensure the safety of automatic driving.
Yin Xiangzhi: This accident highlights the biggest obstacle to artificial intelligence at this stage: Machines can only recognize what we teach and cannot understand and judge extra events. So the algorithm needs to move from recognition to understanding and cognition so that accidents can be better avoided.
Zhang Renjie: Now our system security is divided into two types: functional security and systemic security. In terms of functional safety, Tesla's on-board systems are not available at present; while there are no backups for system security, the system is very weak on these two levels.
Pang Chunlin: Will smart vehicles require a black box in the future? What are the devices that determine the trace and source of this signal command?
Qiu Chunxin: Now that accidents can be determined with the help of driving recorders. The role of a black box on a driverless car is also relatively large. When an accident occurs, it can record information from the environment perception, decision-making units, and motion control, and then define responsibility. In the era of unmanned vehicles, laser radar is not only installed in the vehicle, but also installed on the roadside like a street light or a surveillance camera. The road traffic conditions can be clearly presented. This will make it easier to identify accidents.
Liu Guoqing: I think this is necessary. There are two aspects of thinking: One is how to prevent tampering with on-board data? The other is whether this information should be uploaded in the end?
Tang Jinsong: The possible direction for the future is that each sensor will have a record when it is running, and it will be stored in the cloud. On the one hand is the role of the black box, on the other hand is part of big data. Do not rule out the possibility of using black boxes for certain aspects of the record. In this way, the intelligence of the sensing device is very important. Our future solid-state laser radar has very great advantages and potential in this respect.
Zhang Renjie: I think that the black box is a way to make things up and it cannot change the fragile nature of the system. From the perspective of security, autopilot systems are divided into security domains and insecure domains. How to isolate the two domains is a very important issue, and security risks must be resolved at the source. There is the problem of power consumption, black box itself will have power consumption, and when to record, when not recorded, or SD failure ... ... full of uncertainty. Now that more popular software-defined cars are used, the role of software in the system is getting bigger and bigger. We can realize the functions of many original independent hardware through software.
Pang Chunlin: In the current automatic driving car, do you think the sensor should be connected to an interface or multiple interfaces?
Qiu Chunxin: The external sensor data is directly input to the car. The amount is very large. In the process, I feel that the front-end camera and laser radar have certain data processing capabilities and provide the necessary information for the car itself to make decisions. These simplified and valid data information can be input through an interface.
Liu Guoqing: I think they can share one channel, but not necessarily all information is packaged together. In terms of the splicing of information, I think it is necessary to think, because the data is really important for unmanned driving, whether it is development or testing. When we have a clear definition of requirements, we need to carry out a large number of tests. It is necessary to have feedback of information to help us form a closed loop to iterate and gradually improve the function.
Tang Jinsong: This is related to the future computing platform. What we can do is to be effective, safe, and reduce the burden of computing. It is hard to say what the middle structure is. It may take a lot of participation to find the best platform, including GPU vendors.
Yin Xiangzhi: There are many professional sensors and complex algorithms in the entire device. It is very difficult to solve it through a platform. Because there are different algorithms for various occasions, if it is really done, it is not very encouraging for innovative models. I think that after processing the data, it will be passed to the central system through a standard API. However, to define the surrounding areas requires the relevant manufacturers to participate in the development of standards. As for the accuracy of transmission, it depends on the performance of various vendors.
Zhang Renjie: I personally support the trend of integration because the future car is a very powerful computing platform. I/O line cards are available for various sensors, cameras, laser radars, etc. I/O line card, the entire system will become very simple. In addition to using such an architecture can easily enhance its computing power. For example, if the processor fails, it can be upgraded. If there is no redundant backup, I can back up the GPU part... I can use several I/O line cards with similar functions to solve the problem part, and continue to improve.
Pang Chunlin: How to look at the future development trend of automotive sensors and systems? The second is what good advice for real issues can promote this?
Qiu Chunxin: At the beginning of autopilot, the heart rate was more to reduce the accident rate. This point is unchanged. Sagitar created a laser radar and now I can answer your questions very well. At present, the main reason for your price is still not enough. The next major issue is how to meet the requirements of the depot, how to make the equipment more stable, and the rest behind it. Sensorless sensorless sensors, which are currently more expensive than radar, are of great concern to everyone. I believe that prices will soon drop.
Liu Guoqing: The main deciding factor in the price of sensors is its output. The cost reduction is only a matter of time. In terms of promotion, I recommend using a camera. There are several advantages: one is that the cost is lower and more friendly; the other is that in addition to having a large market for new cars, it is not bad in the stock market, but it can also improve. Existing traffic safety conditions.
Tang Jinsong: Lidars need to look at 30 to 200 meters when they drive automatically. The data volume is millions of point cloud data per second. It is a very complicated technology. The cost of development and research is very huge. The traditional laser radar is a rotating one, which is a combination. Each factory is to be debugged, and the cost is harder to lower. In the future, our solid-state laser radar has no mechanical parts and is entirely realized by semiconductor materials and software. Through such technological breakthroughs and repercussions, prices can be reduced under the premise of future mass production.
Yin Xiangzhi: I think business is an effective way. Commercial buyouts and even subsidies can be more effective.
Zhang Renjie: Do we really need 16-line laser radar? The single-line camera +4 line laser radar must be very cheap, better than a single-line camera, why do we not do some low-end attempts? We always think theoretically very well. In fact, we go too fast. It may be better to choose a relatively low-end configuration when the current price of Lidar is relatively high. For China, the current mainstream economic models are basically selling at a price of around 200,000 yuan. No one chooses a higher price, but for a commercial vehicle, adding a $8,000 laser radar to a 1.5 million vehicle is no problem. So you can take the lead in commercial vehicles. When the market reaches a certain amount, the price naturally goes down. Finally, the civilian models can also be popularized.
Gfci Outlet,Gfci Socket,Gfci Plugs,Outdoor Gfci Outlet Box
Lishui Trimone Electrical Technology Co., Ltd , https://www.3gracegfci.com