To date, some of the hottest players in the autonomous arena have put their energy into driving endless miles in order to fine-tune their AI-based technology. It's time consuming and expensive, and most approved test driving sites have been in parts of the world with sunny skies and dry roads, hardly indicative of common driving conditions. With this mile-by-mile method, it's hard to imagine self-driving could become commonplace anytime soon. However, there is another approach to training and tuning AI for optimized self-driving - cutting-edge simulators that enhance deep learning and offer any number of driving scenarios to train the AI, helping to bring autonomous vehicles (AVs) to market in a more reasonable timeline. The newest approaches to self-driving recognize that by relying on a simulated testing environment, development gets an enormous boost in terms of cost, time, and safety.
This week I'm going to focus on how deep learning is used in self-driving cars. There are plenty of machine learning applications within that field, but I'm going to zoom in on one very cool technology: virtual testing. Let me cut to the chase: below's a video of my fully-autonomous car driving around in a virtual testing environment. Granted, while it does looks like a 1990s retro (pretty dull) driving game, the car is being controlled by a deep convolutional neural net (CNN) based on a modification a deep learning algorithm made by Nvidia. Let's dive in and take a look at what's going on here.
Autonomous cars have been recently hitting the headlines and dominating tech-talks. They are seen as a post-Uber disruption to public commute and transportation of goods. Surely they are no figment of imagination in the age of artificial intelligence (AI), which is being used to complement driverless cars. Companies such as Waymo and Tesla are heavily invested in driverless cars. Currently, Waymo has begun testing of driverless cars again after stopping in 2017.
Nissan Motor Co. on Monday unveiled new autonomous driving technology designed to prevent accidents by detecting successive sudden moves by cars and pedestrians. Nissan will work to improve the technology further with the aim of installing it to new vehicles from the mid-2020s and to almost all vehicles by 2030. Using the LiDAR sensor system, a car with the technology can, for example, change lanes quickly to prevent a collision with a vehicle abruptly coming in front of the car and soon after that apply the brake to avoid hitting a pedestrian jumping into the road, according to Nissan. Current autonomous driving technologies can avoid accident risks one by one, but cannot deal with successive risk situations, Nissan officials said. Nissan substantially improved the performance of the LiDAR system to enable it to figure out the shapes of objects near the vehicle and measure the distances to the items and their movements accurately and instantly.
Self-driving vehicles are no longer a thing of the future, as autonomous buses, taxis and cars are beginning to hit the road. And despite some hesitancy, there are signs that the public may be opening up to autonomous vehicles--as we recently reported, 62% of people surveyed believe autonomous vehicles are the way of the future, according to a consumer Mobility Report. COVID-19 has had a positive impact, as city planning and safety in public spaces haves forced many to reimagine the role of autonomous vehicles in our lives. Still, putting actual trust in these vehicles is still a major obstacle. While 52% of those surveyed say they are excited by the concept of autonomous vehicles, and 72% predict that most people will use them by 2041, they're not ready to get into one--yet.