"Result-oriented, fact-speaking" is the only law of business survival.
Since Surestar launched its intelligent networked car business, it has set its core goal to develop solid-state lidars that can be pre-installed and mass-produced. No matter how hot the high-line count mechanical type has been, how the OPA concept has been hot, and how the fiber laser is advertised as equivalent to hundreds of lines, Surestar will not be moved.
Surestar insists that mechanical laser radar is not suitable for mass production, OPA cannot go out of the laboratory, and fiber laser is most suitable for surveying and mapping laser radar. Not following the trend or following the capital's preferences, Surestar practiced alone in the field of lidar.
Combining the requirements of vehicle regulations, costs, and scenarios, and relying on 21 years of accumulation in the field of lidar, Surestar has overcome many problems in optical and mechanical structure, laser transceiver, signal processing, manufacturing process, chip, light and small size, etc. , Created a low-cost 256-line front-mounted solid-state lidar based on semiconductor technology.
C-Fans256 main parameters
How C-Fans256 improves perception
Unmanned vehicles will encounter a variety of complex road conditions in the process of driving: vehicles occupying the road illegally, traffic jams at close distances, vehicles driving against traffic regulations, retrograde electric vehicles, ghost probes, unprotected left turn, Bicycles crossing the road, traffic cones or warning signs for temporary construction, tunnels, basements, highways, etc.
Different areas have different road characteristics. Southern cities are rainy and the roads are prone to damp, and there are more motorcycles that do not follow traffic regulations. Beijing’s inner ring road has wide roads, dense vehicles and faster speeds.
The rich and stable perception module is the vanguard of the unmanned driving system. It provides data input for fine decision-making and planning. C-Fans256 has conducted in-depth investigations on various scenarios at the beginning of the design, in order to help solve various corner cases and improve the The perception ability of the human driving system has created a number of secret weapons.
C-Fans256, high resolution (0.1°×0.1°)
In the process of driving on urban highways, pedestrians who do not follow the traffic rules in the distance, and vehicles that accidentally go backwards on the highway, etc., High-resolution lidar can solve various problems encountered by millimeter-wave radar and camera detection, provide stable perceptual input for decision planning system.
The real-time data of lidar below 100 lines is a sparse point cloud, but with its ultra-high resolution of 0.1°×0.1°, the C-Fans256 line can still achieve a grid density of 0.4m×0.4m at 200m. For an ordinary SUV with a width of 1.8m and a height of 1.8m, a 4×4 dot matrix can still be seen at 200m.
C-Fans256 vehicle measured point cloud
C-Fans256 measured point cloud for children (height <1.1m)
C-Fans256 measured point cloud of small obstacles (20cm×20cm×20cm)
The high resolution corresponds to the high grid density, which can realize the detection of farther and smaller obstacles. Under the complex road conditions of the city, the details of the distant changes can be found as early as possible. At high speeds, the actions or abnormalities of distant vehicles can be detected in advance. Such detection capability means higher safety.
C-Fans256, large field of view (150°×30°)
In the scene of unprotected left-turning at intersections and complex intersections in urban areas, large FOV can bring rich perception information to autonomous vehicles, especially when completing U-turn movements, the larger the field of view, the better, provided by C-Fans256 With a 150°×30° FOV, it can provide a wide sensing range when the vehicle turns left or U-turn, and improves the safety of the automatic driving system.
C-Fans256 point cloud
C-Fans256, high frame rate (80Hz)
In scenes such as ghost probes, high-speed merging into the main road, high-speed sudden braking, etc., the precise and rapid direct contour measurement capability of lidar can help autonomous vehicles respond within 100 milliseconds. The key indicator at this time is the frame rate. If a ghost probe or a car that brakes suddenly, the relative speed is 80km/h. If the radar frame rate is 10Hz, the tracking algorithm has completed the calculation in 5 frames, which means the vehicle’s response. The distance is:
From the time of the accident to the beginning of the system's judgment, the relative distance between the two has been shortened by 6.7m, and then the braking distance of the vehicle is included, which obviously means an increase in the risk factor.
Vehicle response distance under different frame rates (80km/h)
This is one of the main reasons why most autonomous vehicles are operating in low-to-medium-speed and low-dynamic scenarios at this stage. In order to improve the perception ability of the autonomous driving system as much as possible, C-Fans256 has increased its frame rate to 80Hz, which is unheard of in the industry, hope to contribute to the realization of unmanned driving in high-speed, high-dynamic and complex environments.
80Hz capture high-speed objects falling in the air (0.3x playback)
Use 80Hz to capture the little girl's dynamic dance (dance name: gossip of the prodigal son)
The 80Hz high frame rate brings smooth and fast dynamic detection. In a real traffic environment, the dynamic detection time of unmanned vehicles can be shortened from the order of hundreds of milliseconds to the order of ten milliseconds, thereby bringing higher safety.
Good grayscale recognition
The L2 scene library must be a subset of the L3 scene library, such as LCC lane centering assist, ALC automatic lane change assist, ACC full-speed adaptive cruise, ATC adaptive curve cruise, LDW lane departure, etc. The use of lidar can enhance automatic driving Robustness of the system at night, tunnel entrances and exits, etc.
These scenes mainly rely on the sensor's accurate detection of lane lines and road shoulders, which puts forward requirements for the gray-scale recognition level of lidar, which requires accurate and precise gray-scale recognition.
C-Fans256 provides 8bit grayscale resolution, which can realize clear lane line recognition all-weather and improve the night perception ability of the unmanned driving system.
Lane line recognition effect at night
Comply with car regulations, self-developed chips, independent and controllable supply chain
Surestar has obtained three major system certifications: IATF 16949, ISO9001, and ISO 14001. And referring to the specific requirements of ISO 16750 and several domestic and foreign auto companies for us, a number of vehicle compliance tests have been carried out in third-party laboratories. At present, the official announcement of the C-Fans256 pre-installation designated project is on the road, please expect.
Vehicle compliance
Lidar is a key technology in the field of autonomous driving sensors. Under the current international situation, Lidar manufacturers that have excellent product performance, stability and reliability, and can make all key components localized are particularly rare. After 21 years of long-term accumulation, Surestar has filled the domestic blank in the laser radar application field many times, and realized the completely domestically-made independent controllability of the measurement laser radar. The price of the measurement lidar has been hit from the tens of millions of imported equipment to the 100,000 level, and as a result, it has repeatedly won the special prize and first prize of provincial and ministerial scientific and technological progress.
With deep accumulation, Surestar has realized the chipization of the core module of the laser radar signal processing. Up to now, it has completed the independent design of 24 chips in 5 categories, and realized the complete independent control of the core components of the laser radar.
High goals and down-to-earth are the principles of Surestar. For more than 20 years, Surestar has been quietly advancing on the road of localization of lidar. This road is sparsely populated, with thorns and long roads. The friends of Surestar continue to innovate, polish products, do not deliberately create topics, and do not pursue short-term flowers and attention. This is probably the essential difference between Surestar and the new lidar company that is chasing the wind.(www.isurestar.net)