Musk doesn't have a timetable for when this radar upgrade could happen, but he believes that it would produce at least "moderate" improvements in Autopilot (if not major ones) without requiring brand new hardware. Tesla has a strong financial motivation to pursue this strategy, as you might guess. It'd have to spend a lot to add lidar to cars, not the least of which might be significant redesigns to accommodate the sensor tech. If this goes forward, though, it could be a big deal. It still wouldn't make Autopilot foolproof, but it might mitigate (or even eliminate) a key weak point and make the hands-off system that much more trustworthy.
Last year, Microsoft, IBM, and Amazon were called out for using facial recognition technology that was biased against people with dark skin. Well, it looks like self-driving cars could have the same problem. An analysis from Georgia Tech researchers found that systems used by self-driving cars to detect pedestrians had trouble picking out people with darker skin tones. Looking at footage from the Berkeley Driving Dataset, with video from New York, Berkeley, San Francisco, and San Jose, researchers were able to study how systems would react to different types of pedestrians. They took eight image recognition systems commonly used in autonomous vehicles and evaluated how each picked up skin tone, as measured on the Fitzpatrick skin type scale.
BMW just announced it's going with a solid-state LiDAR system for the company's self-driving vehicles, which it plans to put into production by 2021. The technology will be supplied by Israeli startup Innoviz Technologies in partnership with automotive supplier Magna. Innoviz, which only launched in 2016, has raced to market with its solid-state LiDAR sensors and accompanying computer vision technology. Solid-state LiDAR is distinct from the mechanical spinning LiDAR that adorns many autonomous vehicles, including Waymo's cars. The spinning mechanism casts lasers in a circular pattern, giving self-guided systems 360 degrees of coverage.
Tesla's progress with artificial intelligence and neural nets has propelled its Autopilot and Full Self Driving solutions to the front of the pack. This is the result of the brilliant work of a large team of Autopilot directors and staff, including Tesla's Senior Director of AI, Andrej Karpathy. Karpathy presented Tesla's methods for training its AI at the Scaled ML Conference in February. Along the way, he shared specific insights into Tesla's methods for achieving the accuracy of traditional laser-based lidar with just a handful of cameras. The secret sauce in Tesla's ever-evolving solution is not the cameras themselves, but rather the advanced processing and neural nets they have built to make sense of the wide range and quality of inputs.
Recently we've seen a series of startups arise hoping to make robocars with just computer vision, along with radar. That includes recently unstealthed AutoX, the off-again, on again efforts of comma.ai Their optimism is based on the huge progress being made in the use of machine learning, most notably convolutional neural networks, at solving the problems of computer vision. Milestones are dropping quickly in AI and particularly pattern matching and computer vision. There are reasons pushing some teams this way.