Cameras, lidar, radar, and ultrasonic: different strengths, different blind spots
Cameras provide rich detail, color, and texture, which is essential for reading traffic lights, road signs, and lane markings, but they struggle in low light, glare, heavy rain, or fog, and they don't directly measure distance the way an active sensor does. Lidar sends out pulses of laser light and measures their return time to build a precise 3D point cloud of the surrounding environment, giving accurate range and shape data regardless of lighting, though it can be degraded by heavy precipitation and is historically more expensive than cameras.
Radar uses radio waves and excels at measuring the speed and distance of other vehicles, even in poor visibility like fog or heavy rain, though it produces a much coarser picture than lidar or cameras. Ultrasonic sensors are short-range and used mainly for close-quarters tasks like parking and detecting curbs, not for highway-speed perception.