Now more than ever, automotive manufacturers and OEMs are focused on high performing Advanced Driver Assistance Systems capabilities that translate to safe, accurate and trustworthy technology. The auto industry should pay attention to recent reports including one from NHTSA raising safety concerns around crashes associated with Level 2 ADAS-equipped vehicles, particularly vehicles involved in crashes that use camera-only technology.
Level 2 autonomous vehicle technology allows the ADAS to control steering, accelerating and decelerating. This means that the vehicle’s ADAS must be able to “see” in real time to enable a vehicle to take rapid, proactive action faster than a human ever could. That’s a tall order for camera-only systems.
Cameras should not set the standard. Just because cameras have been popularized through extensive use in early electric vehicles, doesn’t mean they should be the standard.
Cameras, while inexpensive and smaller, don't provide the same level of data, range and resolution that a lidar solution does, failing to deliver on the promise of safety that drivers need and expect. The NHTSA report data illustrates that cameras are simply not enough. Issues that arise from using a camera-only system include: a limited two-dimensional view of a three-dimensional environment; difficulty performing in fog, rain, changing lighting conditions, and at high speeds; and the inability to track moving objects like a vehicle changing lanes or being obscured by another obstacle. In addition, current camera module technology is not suitable for long ranges and wide fields of view and require considerable training on object classification as well as significant computing power.
“Seeing” further, faster and in real time. The key to improving and innovating ADAS is to utilize lidar as part of the solution. A lidar system works by sending out laser pulses and then processing that information to “see” obstacles, pedestrians, other vehicles, and more. This data provides a vehicle’s ADAS with near-instant readings for distance and object measurements - “seeing” further, faster and in real time. Achieving both dynamic range and measurement, lidar systems perform more accurate three-dimensional mapping of a vehicle’s surroundings and process this information quickly and predictably. Lidar works well in different lighting conditions, even in direct sunlight and complete darkness, while also accurately evaluating distance regardless of road composition.
Three-dimensional mapping, dynamic range, and high performance in changing lighting conditions are only a few of the strengths lidar has over camera-only systems. Lidar also has the edge in terms of performance in many of the scenarios in which camera-only systems struggle. Lidar provides readings on the instant velocity of moving objects not only in relation to the vehicle but objects around it. Lidar enables consistently faster response times which makes it ideal for operating at highway speeds. And lidar provides an ultra-high-resolution point cloud showing drivable and non-drivable areas of the road ahead without needing to classify objects.
Safety, reliability and accuracy. Ensuring safety, reliability and accuracy means the most advanced ADAS will be one that utilizes cameras, radar and lidar to enable a dynamic view at high speeds - one that covers short-, medium-, and long-range views to produce an ultra-high-resolution point cloud showing drivable and non-drivable areas of the road ahead. And it’ll be one that enables ADAS systems to respond more quickly and to take action every single time, no matter the lighting, weather conditions or speed.
Staying at the forefront of developing ADAS technology means putting consumer safety at the top of the list. Proving the safety, reliability and accuracy of ADAS now and in automated vehicles in the future will be the key to unlocking the public’s trust and ensuring OEMs are on the right path to choosing the best technology.
Sumit Sharma is CEO of MicroVision, an automotive lidar technology provider.