At the 2021 Shanghai International Auto Show, Huawei publicly released high-resolution imaging radar products and solutions for the first time. For high-end autonomous driving, Huawei’s high-resolution 4D imaging radar was officially released.
It is understood that compared to lidar and cameras,
millimeter-wave radar has excellent speed measurement capabilities, excellent weather and light robustness (not affected by light and rain and snow), and unique detection of non-line-of-sight obscured targets ability.
While the high-resolution 4D imaging radar inherits these advantages,
it greatly improves the resolution, target detection confidence and detection range (such as distance and FOV). At the same time, it has evolved a high-density point cloud like lidar, which can bring richness. Perception enhancement applications , such as environment characterization, radar composition, positioning, etc., can also be integrated with point cloud level of multiple radars to better realize 360° detection of the car’s circumference.
Full target, full coverage, full working conditions and all weather are the targets of ideal autonomous driving sensors.
Huawei believes that the next evolution of millimeter wave is high-resolution 4D imaging radar.
4D refers to the four dimensions of the detection target, including its speed, distance, horizontal angle and vertical angle. Traditional radars have insufficient horizontal resolution and do not support vertical resolution. Leading to invisible and inaccurate.
In recent years, insufficient perception is one of the important reasons for autonomous driving accidents, such as failure to effectively identify stationary vehicles or accident vehicles, and inaccurate judgments of isolation piles or guardrails, leading to serious accidents.
The 4D imaging radar greatly improves the horizontal and vertical angle measurement capabilities,
meets the sensing requirements of full target, full coverage and multiple working conditions, and gradually approaches the ideal sensor target, which will form effective fusion and redundancy with the camera and lidar.
The first is the high resolution of the large array.
Huawei’s high-resolution 4D imaging radar uses 12 transmitting channels and 24 receiving channels, which is 24 times higher than the conventional millimeter wave 3 transmitter and 4 receiver antenna configuration, and 50% more receiver channels than the industry’s typical imaging radar. This is also the largest antenna configuration imaging radar that can be mass-produced in the short term.
The second is the large field of view without blur . The horizontal field of view is increased from 90° to 120°, the vertical field of view is increased from 18° to 30°, and the longitudinal detection range is increased from 200 meters to more than 300 meters.
The third is a 4D high-density point cloud
The 4D point cloud of imaging radar, including speed, distance, horizontal angle and vertical angle, has one more speed dimension than lidar point cloud, and can interpret the target object in more dimensions.
It is reported that Chinese when high-resolution imaging radar 4D may be implemented in front of clogging, 130km / h at comfort brake to stop; cone tub detection range of 110 meters, the fence may also be implemented to distinguish the stationary vehicle .
In addition, the perception of occluded or partially occluded targets is a unique ability of millimeter waves.
The 4D imaging radar can see the car ahead, the car ahead, and the car ahead. You can even see the general chassis outline of the vehicle ahead. Through the perception of the vehicle ahead, such as a sudden deceleration, you can predict the movement of the vehicle ahead in advance and reduce the risk of chain rear-end collisions.
In Huawei’s view, 4D imaging radar will inevitably bring revolutionary changes and become the next necessary weapon for high-end autonomous driving.