Self-driving vehicle startup Optimus Ride has announced it is using the Nvidia Drive AGX Xavier platform for its autonomous shuttles. The vehicles have Level 4 autonomy, to be used in geofenced deployments.

Nvidia Drive AGX Xavier is a computing platform designed for AVs and as such promises to combine a high level of processing power (30 trillion operations per second) with a low power consumption of 30W. It also uses six different processor types for redundancy and a diverse deep learning environment. Nvidia is an investor in the Optimus Ride program.

“Building on Nvidia Drive ensures our vehicles are equipped with the highest performance and most efficient processing power available,” said Optimus Ride CEO and co-founder Ryan Chin.

Continue reading Optimus Ride AV shuttles to use Nvidia Drive AGX at ADAS & Autonomous Vehicle International.

Autonomous driving is fast becoming a reality. Increasing driving assistance and safety features such as adaptive cruise control and lane departure warnings are already becoming commonplace. Predictive ride technology is being introduced whereby the car senses the state of the road ahead and adjusts the ride settings to maximize comfort and reduce travel sickness when driving over uneven surfaces.

McKinsey projects that by 2030 up to 15% of vehicles sold will be fully autonomous. For passengers, that is likely to mean a smooth and comfortable driverless experience – but this pushes the need to achieve all the external connectivity to meet lifestyle and/or workplace requirements.

Continue reading Connectivity challenges for next-generation autonomous cars at ADAS & Autonomous Vehicle International.

Testing lies at the root of any innovation. In the case of autonomous vehicles, it’s crucial not only for safety, but also for ironing out kinks in development and ultimately persuading people that cars without drivers are a good idea.

However, as has already been seen, when AVs, or rather the people responsible for them, get it wrong in real-world scenarios, the effects can sometimes be devastating.

Unsurprisingly, those involved in developing AVs spend a good deal of time testing in virtual worlds. Thanks to advances in computing power and software, it’s now possible to create any kind of urban environment in which to test, plus being able to layer on a wealth of everyday scenarios involving virtual people means that nobody gets hurt.

Continue reading Sim cities: How virtual worlds for testing AVs are built at ADAS & Autonomous Vehicle International.

Driverless cars are set to become smoother and more intuitive after scientists and Hyundai have developed technology to make them behave like humans.

One of the stumbling blocks with autonomous cars has been their inability to interpret visual cues from pedestrians, making them overly cautious. So when a person begins to cross the street but changes their mind, a driverless car might just stop and wait.

But engineers at Perceptive Automata have developed artificial intelligence software that enables driverless vehicles to understand people’s state-of-mind, including that of pedestrians, cyclists and other motorists.

With the software installed, autonomous vehicles can anticipate what pedestrians, cyclists and motorists might do next.

Continue reading Hyundai invests in AI that enables AVs to understand human behavior at ADAS & Autonomous Vehicle International.

Hyundai Mobis is utilizing high-definition software originally developed for 3D game development to conduct a series of autonomous driving tests for various scenarios, to enhance the performance of its autonomous driving sensor (camera).

As a result, the biggest automotive supplier in Korea expects to greatly improve the object recognition accuracy of the cameras it is proprietarily developing for autonomous vehicles.

“As it is possible to create the desired environment for testing without being limited by numerous constraints in real life, the performance of the cameras can be enhanced,” explained a company spokesperson.

The company’s technical centre in India recently entered into a contract with Tata Elxsi, an Indian software company that provides solutions optimised for ICT sectors, such as artificial intelligence, Internet of Things, big data and autonomous driving.

Continue reading Hyundai Mobis introduces autonomous driving test using 3D game technology at ADAS & Autonomous Vehicle International.

The American Center for Mobility (ACM), a testing, education and product development facility for future mobility in Michigan, has extended its cooperation with Siemens PLM. The new agreement means that Siemens will supply US$1m in ITS infrastructure software, and engineering support to ACM.

“This expanded partnership with Siemens enables ACM to be outfitted with the best infrastructure and applications to benefit our testers,” said Soraya Kim, chief innovation officer of the American Center for Mobility.

“Our goal is to provide our testers the means for exhaustive validation methodologies and comprehensive regulations for the safe deployment of connected vehicle technologies – something I am confident this extended partnership accomplishes.”

“Michigan has done an incredible job of ensuring its position as a leading technology hub for future transportation solutions, and the American Center for Mobility is an important cornerstone of that effort,” explained Marcus Welz, CEO of Siemens Intelligent Traffic Systems.

Continue reading Siemens PLM supplies ITS technology for CAV research at American Center for Mobility at ADAS & Autonomous Vehicle International.

Tier 1 automotive suppliers Denso, Aisin, ADVICS and JTEKT have reached a basic agreement to establish a joint venture that will develop AV software for integrated ECUs.

The four companies will have stakes in the joint venture of 65%, 25%, 5% and 5%, respectively. Details still have to be finalized, but the aim is for the company to launch in March 2019.

The joint venture aims to develop software for integrated ECUs, which manage numerous functions, thus replacing multiple separate ECUs for sensors, brakes, steering and other components, thus improving the way these elements of the vehicle can work together.

Continue reading Denso, Aisin, ADVICS and JTEKT to collaborate on AV ECU software at ADAS & Autonomous Vehicle International.

Figure Eight, a machine learning platform, has launched a machine learning-assisted video object tracking solution for AV navigation, among other applications.

The software can track objects across a number of video frames and incorporates AI to improve its predictions based on corrections by humans reviewing the machine predictions.

“Training data is the bottleneck to making AI work at scale in the real world today. Unfortunately, human-only annotation solutions cannot meet the market demands of training data volume and quality,” said Robert Munro, CTO of Figure Eight.

“The only viable solution to creating high-quality training data at scale is to combine the best of machine learning and human intelligence.

Continue reading Figure Eight launches object tracking solution at ADAS & Autonomous Vehicle International.

RideOS, a technology platform for the roll-out of next-generation fleets, has raised US$25m in series B funding, with a major part coming from Siemens’s venture arm Next47, meaning that RideOS will also be able to benefit from the company’s AV expertise.

In addition, RideOS is receiving funding from existing investor Sequoia Capital and a new investor, Singapore-based ST Engineering Ventures, bringing its total funding to US$34m.

Next47 will also be integral to RideOS’s mission to accelerate the safe, global roll-out of AVs through its presence in major cities. Next47 will be able to provide RideOS with global support and expertise in industrial and infrastructure technology to help it complete the self-driving car stack.

Continue reading US$25m series B investment for RideOS at ADAS & Autonomous Vehicle International.

Continental has signed a membership agreement with the University of California, Berkeley’s AI research group DeepDrive.

Together, they will continue research into artificial intelligence (AI) in road vehicles, an important part of AVs.

“We are joining forces with the world’s leading AI researchers,” said Demetrio Aiello, head of Continental’s corporate AI and robotics lab.

“Building on the momentum of our strategic partnerships with the University of Oxford, DFKI (German Research Center for Artificial Intelligence) and other AI thought leaders, we have signed a five-year agreement to be members of the UC Berkeley DeepDrive (BDD) centre.”

The research focuses on optimising the speed of neural networks, protecting AI systems in safety-critical applications and improving machine vision and learning.

Continue reading Continental strengthens involvement with UC Berkeley DeepDrive project at ADAS & Autonomous Vehicle International.