Toggle light / dark theme

An autonomous vehicle must rapidly and accurately recognize objects that it encounters, from an idling delivery truck parked at the corner to a cyclist whizzing toward an approaching intersection.

To do this, the vehicle might use a powerful computer vision model to categorize every pixel in a high-resolution image of this scene, so it doesn’t lose sight of objects that might be obscured in a lower-quality image. But this task, known as semantic segmentation, is complex and requires a huge amount of computation when the image has high resolution.

Researchers from MIT, the MIT-IBM Watson AI Lab, and elsewhere have developed a more efficient computer vision model that vastly reduces the computational complexity of this task. Their model can perform semantic segmentation accurately in real-time on a device with limited hardware resources, such as the on-board computers that enable an to make split-second decisions.

Needless to say, this could transform the way Tesla builds EVs and contribute decisively to halving production costs, which is a long-time goal of CEO Elon Musk.

The sources said the know-how to achieve that is core to Tesla’s “unboxed” manufacturing strategy unveiled by Elon Musk in March, which is key to his plan to build tens of millions of cheaper EVs over the next ten years, and still turn a profit.

Two of the insiders said Tesla’s new design and manufacturing techniques could allow the company to develop a car from the ground up in 18–24 months, compared to 3–4 years for most rivals.

According to the Organisation for Economic Co-operation and Development estimates, transportation accounts for 27 percent of global carbon emissions. Powered by fossil fuels, road-based transportation contributes 80 percent of these emissions and therefore countries are aggressively pushing for the electrification of vehicles. While major advances have been made for passenger cars and air transport, water transport is still lagging. Yara’s new cargo ship might just lead the way.

Decarbonising Australia’s transport systems will take more than a transition to electric vehicles. Understanding how and when owners like to charge their cars is important. Our researchers are examining how we might persuade the increasing electricity demand to meet the time-dependent renewable energy supply.

How many people do you know who own an electric vehicle? Most Australians still drive petrol-fuelled cars. But the proportion of electric vehicles (EVs) on our roads is set to boom in coming years, particularly if the government’s plans to introduce a fuel efficiency standard prove successful.

Transport researchers at the University of Melbourne Faculty of Engineering and Information Technology have studied the expectations EV owners have for charging – and what they think of policies and technologies that aim to shape EV charging behaviours.

Specializing in extreme fast charging (XFC) battery technology for electric vehicles, StoreDot aims to solve range anxiety, which is a well-known type of anxiety among EV owners. With its “100inX” technology roadmap, the company aims to achieve a mileage of 100 miles per five minutes of charging by 2024, according to a press release.

The company is at the advanced stages of developing groundbreaking semi-solid state technologies and targets mass manufacturing of its fast-charging battery cells, 100in5, which offer 100 miles of travel in five minutes of charging in 2024, then improve its charging abilities by 40 percent to three minutes by 2028 with 100in3, and finally achieving complete charging in two minutes by improving an additional 33 percent by 2032 with 100in2 batteries.

The METL tire is made from a shape memory alloy, making it elastic like rubber yet strong like titanium.

The much-hyped airless tire technology developed by NASA for its rovers, later commercialized for terrestrial use by The SMART Tire Company (STC), is now available for sale.

According to a Kickstarter campaign, the SMART METL tires designed for bikes have minimal rolling resistance (less labor for you), require no air pressure, ride smoothly like pneumatic tires, and last the lifetime of your vehicle. They also look exceptionally stylish as well.

At the recent launch of its new BEV factory, Toyota vowed its next-generation electric vehicles will deliver longer range and faster charging at a lower price. The Japanese automaker now says its new EVs, due out in 2026, will feature nearly 500 miles of range.

At a technical briefing in June, Toyota revealed several new innovations, including advanced battery plans, improvements in aerodynamics, and manufacturing upgrades as it looks to boost EV sales with its next-gen electric models.

The company shared at the launch of its BEV factory, which is not an actual plant but rather “an organization dedicated to battery EVs,” that production of Toyota’s new EVs will begin in 2026.

Self-driving car startup Wayve can now interrogate its vehicles, asking them questions about their driving decisions—and getting answers back. The idea is to use the same tech behind ChatGPT to help train driverless cars.

The company combined its existing self-driving software with a large language model, creating a hybrid model it calls LINGO-1. LINGO-1 synchs up video data and driving data (the actions that the cars take second by second) with natural-language descriptions that capture what the car sees and what it does.