Tesla will start shipping non-radar Model Y and Model 3 vehicles to customers in Europe and the Middle East, a continuation of the company’s plans and CEO Elon Musk’s desire to use machine learning only to support its advanced driver assistance system and others. cameras connected. Active safety features.
Tesla began production of Model 3 and Model Y vehicles without radar in May 2021. These cars were specifically for the North American market. In an update on its website, the company said it will start deliveries of its camera-equipped Model Y and Model 3 vehicles to Europe and the Middle East this month.
Vehicles may have a number of features that are temporarily disabled or inactive, the company says, including a feature that keeps them within their lane. The feature, called Autosteer, is limited to a top speed of 80 mph and a long minimum short distance. Tesla will gradually restore features through a series of over-the-air software updates in the coming weeks. All other available Tesla Autopilot and Full Autonomous Driving features are activated upon delivery, depending on order configuration.
Tesla’s decision to stop using the sensor is a departure from the industry standard. Vehicle manufacturers typically use a combination of radar and cameras to provide the detection needed to provide advanced driver assistance features such as adaptive cruise control that tracks vehicle speed based on the speed of surrounding traffic, as well as lane keeping and automatic transmission. to lane change. Some automakers, such as Mercedes-Benz and Volvo, have also added a third sensor called a lidar, or light and distance detection sensor, to provide redundancy to the ADAS system.
More, not less. Moving towards sensors is what most automakers are heading towards. Tesla and his CEO are opposed to Musk.
Musk has long been touting the potential of his proprietary “Tesla Vision” system, which uses nothing but cameras and so-called neural network processing to detect and understand what’s going on in the car’s environment and then react accordingly.
Neural networks are a form of machine learning that works in the same way that humans learn. It is an advanced form of an artificial intelligence algorithm that allows computers to learn by using a series of connected networks to discover patterns in data.
Many companies developing autonomous vehicle technology for robotic axles or self-driving trucks use deep neural networks to solve specific problems. But they are shutting down deep networks and using rule-based algorithms to join the wider system. These AV developers are also using a combination of camera, radar and lidar to make the system redundant.