Pushing Perception Boundaries, Providing the Confidence and Redundancy Needed to Achieve True Safety for Hands-Free Driving and Full Autonomy

On the perception level, the race to the giant-leap of L2+ cars, as the first step towards full autonomy, boils down to choosing the most effective sensor-pair. The sensors must be able to provide a real-time, coherent, and robust picture of the driving environment, regardless of the environment conditions. In this talk we will present the 4D imaging radar technology, and show why it is the perfect counterpart to the camera, not offering redundancy or "more of the same", but rather, relying on a different technology, the radar and camera complement each other’s strengths and weaknesses: radars excel in depth, relative radial velocity, and long range sensing, around the clock, while cameras are perfect for contrast based information, accurate tangential velocities, and classification, when light permits. Therefore, to achieve the ultimate goal of true safety for any Level 2+ application, hands free driving, and full autonomy, the fusion of both sensors is required.

4D Imaging Radar Solution offers real time sensing value on its own merit, even before fusion, as it provides ultra-high physical resolution at a long range, in both azimuth and elevation, that supports 10s of thousands of detections per frame with a point cloud density that is unparalleled to any other radar solution on the market. We will show how Arbe’s technology and post-processing the radar's data enable many advanced real-time features, such as accurate inference of the vehicle’s ego-motion and ego turn rate, tracking objects, their bounding boxes, and motion vector in the entire field of view, accurate free space mapping to distinguish drivable from non-drivable environments, and even simultaneous localization and mapping.

4D imaging radar empowers advanced sensing for an array of applications including AGVs, commercial and industrial vehicles, and smart cities, and has effectively repositioned itself to become a mandatory sensor for the future of perception.