Arbe’s 360° Perception relies on data sharing between multiple radars, decreasing latencies while increasing confidence levels and accuracy of the tracking and the free space map. Multiple radars overlap in the fringes, tracking objects of interest smoothly from one radar to the next and validating the location of the same object through two different perception algorithms. The result is reduced false alarms, higher resilience to occlusion scenarios, and the ability to better foresee the quickly evolving vehicle environment.

Object orientation is critical for countless actions, including safe and successful lane changes, navigation in intersections and roundabouts, and maneuvering through parking lots. For example, the sensor system must both see a truck in the lane and understand exactly where that truck is headed at zero/minimal latency within the dynamically changing road scene. Arbe’s Perception achieves a 1° spatial resolution and hundreds of separate detections per object, allowing credible inference for hundreds of objects at zero latency.

Free Space Mapping is the basis for navigation, path planning, and obstacle avoidance paving the way to autonomous decision-making, and driving. These applications require a reliable estimate of the empty vs. occupied space in the vehicle’s environment. Arbe’s Perception satisfies key requirements for free space mapping, high spatial resolution in all dimensions and weather conditions, at long range with high reliability. Its high doppler resolution allows it to distinguish efficiently between stationary and dynamic detections. Together these capabilities make imaging radar a mandatory sensor suite component to map free space in real-time.

An accurate estimate of a vehicle’s own velocity, referred to as ego-velocity, is crucial for truly safe ADAS and, eventually, autonomous driving. While ego-velocity can be estimated using a variety of methods, only Arbe’s Perception provides precision at zero connectivity scenarios. Based on its ability to distinguish between stationary objects and dynamic objects, and by exploiting its high resolution in all dimensions, Arbe’s technology makes highly accurate, per-frame, continuous ego-velocity estimations that overcome problematic scenarios such as bridges, tunnels, traffic jams, and garages.

Object tracking is the ability to determine an object’s location in relation to the vehicle, to classify it, and to understand its speed, size, shape, altitude, and orientation. Sophisticated tracking empowers all advanced safety applications, building a more complete picture of what is happening on and near the road and enabling safer navigation. Thanks to significantly better spatial resolution, Arbe’s radar-based perception complements cameras for object tracking due to its superior long range detection, direct measurement of distance and relative velocity, and recognition of connections between frames.

All of these perception abilities, combined with the highly detailed 4D radar data and the ability to detect stationary objects, enable the radar to provide Simultaneous Localization and Mapping (SLAM). SLAM is the ability to map the vehicle’s surroundings while simultaneously localizing it within that map as it is being continuously generated. Arbe’s independent SLAM solution is designed to work both in conjunction with and independently of other sensors in the vehicle, providing both redundancy and full backup when other sensors fail.