Autonomous & Self-Driving News: Bosch, Mercedes-Benz, Molex, Weka, Aeva, DRiV, Plus.ai, Quanergy & Nuro

In autonomous and self-driving vehicle news were Bosch, Mercedes-Benz, Molex, Weka, Aeva, DRiV, Plus.ai, Quanergy and Nuro.

Bosch and Mercedes-Benz Know the Way to Autonomous San Jose

In autonomous and self-driving news
Bosch and Mercedes-Benz’s joint project to develop urban automated driving has now entered a new stage. Their pilot project for an app-based ride-hailing service using automated Mercedes-Benz S-Class vehicles has now been launched in the Silicon Valley city of San José. Monitored by a safety driver, the self-driving cars shuttle between West San José and downtown, along the San Carlos Street and Stevens Creek Boulevard thoroughfares. The service will initially be available to a select group of users. They will use an app developed by Daimler Mobility AG to book a journey by the automated S-Class vehicles from a defined pick-up point to their destination. Mercedes-Benz and Bosch hope this trial will provide valuable insights into the further development of their SAE Level 4/5 automated driving system. The partners also expect to gain further insights into how self-driving cars can be integrated into an intermodal mobility system that also includes public transportation and car-sharing.

The project of Mercedes and Bosch ties in with San José’s extensive ‘smart city’ objectives. It will also help us develop guidelines for dealing with new technologies and prepare for the traffic system of the future,” says Dolan Beckel, Director of Civic Innovation and Digital Strategy. “If automated driving is to become everyday reality, the technology has to work reliably and safely. And this is where we need tests such as our pilot project in San José,” says Dr. Michael Fausten, head of engineering for urban automated driving at Robert Bosch GmbH. “It’s not just the automated vehicles that have to prove their mettle. We also need proof that they can fit in as a piece of the urban mobility puzzle. We can test both these things in San José,” says Dr. Uwe Keller, head of autonomous driving at Mercedes-Benz AG.

Bosch and Mercedes-Benz have taken a further partner on board: Daimler Mobility AG is developing and testing a fleet platform to accompany the pilot operation phase. This allows potential ride-hailing partners to seamlessly integrate self-driving (Mercedes-Benz) vehicles into their service portfolio. The platform manages both self-driving and conventional vehicles, including operation and maintenance. An app-based mobility service for conventionally driven Mercedes-Benz vehicles went into operation in the Bay Area in the fall of 2019. The service is also available in the German capital Aptiv Open Sources NuScenes

Aptiv announced the next big step for Aptiv’s open-source data initiative. In the first half of 2020 the team will release two major updates to nuScenes: nuScenes-lidarseg and nuScenes-images. Commercial licensing will be available for both datasets

In the original nuScenes release, cuboids (also known as bounding boxes) are used to represent 3D object detection. While this is a useful representation in many cases, cuboids lack the ability to capture fine shape details of articulated objects. As self-driving technology continues to advance, vehicles need to pick up on as much detailed information of the outside world as possible. For example, if a pedestrian or cyclist is using arm signals to communicate with other road users, the vehicle needs to recognize this and respond correctly.

To achieve such levels of granularity, Aptiv released nuScenes-lidarseg. This dataset contains annotations for every single lidar point in the 40,000 keyframes of the nuScenes dataset with a semantic label — an astonishing 1,400,000,000 lidar points annotated with one of 38 labels.

This is a major step forward for nuScenes, Aptiv, and the industry’s open-source initiative, as it allows researchers to study and quantify novel problems such as lidar point cloud segmentation, foreground extraction and sensor calibration using .

StradVision, an innovator in vision processing technology for autonomous vehicles and ADAS systems, was awarded 2020 AVT ACES Award by BNP Media’s Autonomous Vehicle Technology for its SVNet software. The awards recognize the most innovative technologies, products and services of the year from companies in the areas of vehicle autonomy, connectivity, electrification and mobility services (ACES).

Molex Wins Too

Molex is a winner of the ACES Award from Autonomous Vehicle Technology (AVT) magazine, for the second year in a row. Molex is recognized in the category of Connectivity for its next-gen solution that fuses a telematic control unit (TCU) to an antenna in a sleek, hidden design.

WekaIO & Innoviz

WekaIO™ (Weka), the innovation leader in high-performance, scalable file storage for data-intensive applications, today announced that Innoviz, a leading manufacturer of high-performance, solid-state Light Detection and Ranging (LiDAR) sensors and Perception Software that enables the mass-production of autonomous vehicles, has selected the Weka File System (WekaFS™) to accelerate its Artificial Intelligence (AI) and deep learning workflows. WekaFS has been chosen by Innoviz to improve application performance at scale and deliver high bandwidth I/O to its GPU cluster.

Innoviz’s solid-state LiDAR sensors are key to the future of autonomous cars. The sensors and Perception Software, which identifies, classifies, segments, and tracks objects to give autonomous vehicles a better understanding of the 3D driving scene, rely heavily on AI.

Aeva’s Aeries

Aeva, the company building next-generation sensing for autonomous vehicles, announces the achievement of a critical milestone for the autonomous vehicles industry: Aeries, Aeva’s next generation Frequency Modulated Continuous Wave (FMCW) LiDAR system that integrates all the key elements of a LiDAR sensor into a miniaturized photonics chip. Aeva’s 4D LiDAR-on-chip significantly reduces the size and power of the device by orders of magnitude while achieving full range performance of over 300m for low reflective objects and the ability to measure instant velocity for every point– a first for the autonomous vehicle industry. Aeva’s LiDAR-on-chip will cost less than $500 at scale, in contrast to the several tens of thousands of dollars for today’s LiDAR sensors.

Unlike other LiDAR technologies, Aeva’s 4D LiDAR-on-chip measures the instant velocity of every point on objects beyond 300m. Aeva’s LiDAR is also free from interference from other sensors or sunlight and it operates at only fractions of the optical power typically required to achieve such long range performance, increasing the factor of safety and scalability for autonomous driving.

Aeva also differs from other FMCW approaches in its unique ability to provide multiple millions of points per second for each beam, resulting in ultra high fidelity data that has been unprecedented until today.

DRiV Awarded Grant

DRiV, a Tenneco Inc. business and leading global aftermarket and OE ride performance supplier, and several research partners have received a European Union Marie Sklodowska-Curie Actions mobility grant for development and evaluation of advanced wheel-corner concepts for autonomous vehicles. DRiV will collaborate with Arrival ltd, a London based technology company designing and manufacturing Generation 2.0 electric vehicles, and several leading universities and industrial organizations in Project OWHEEL, which will produce recommendations for improving ride dynamics and passenger comfort through innovative wheel-corner designs.

Established in 1996, Marie Skłodowska-Curie Actions (MSCA) is a fellowship program that awards grants to promote interdisciplinary research and international collaborations. The EU Research Executive Agency has awarded more than €6 billion in MSCA grants for projects dedicated to excellence and worldwide mobility in research.

Partners in Project OWHEEL will develop and benchmark the performance of four next-generation wheel-corner concepts – passive corner with stationary wheel positioning, passive composite corner, active corner with conventional ride dynamics control, and active corner with integrated wheel positioning control – intended to enhance passenger comfort in autonomous operation. Project partners will collaborate in development design, extensive simulation studies and experimental validation of each proposed concept.

Plus.ai 1st Coast-to-Coast

Plus.ai a leading provider of self-driving trucking technology, announced that it has completed the first coast-to-coast commercial freight run with an autonomous truck on behalf of Land O’Lakes, Inc. Spanning 2,800 miles, Plus.ai’s L4 autonomous truck completed the hub-to-hub trip from Tulare, CA to Quakertown, PA in less than three days. This is the first L4 U.S. cross-country commercial pilot hauling a fully-loaded refrigerated trailer of perishable cargo.

The truck was equipped with Plus.ai’s advanced autonomous driving system which utilizes multimodal sensor fusion, deep learning visual algorithms, and simultaneous location and mapping (SLAM) technologies. The journey was an important milestone in validating the system’s ability to safely handle a wide range of weather and road conditions. The vehicle drove primarily in autonomous mode through the 2,800 miles across interstate 15 and interstate 70, passing through varied terrains and weather conditions. A safety driver was onboard at all times to monitor and assume control if needed, and a safety engineer was present to monitor system operations.

On its continuous cross-country journey, the Plus.ai autonomous truck safely navigated driving day and night through the expansive plains of Kansas, winding roads of the Rockies, road construction, multi-mile tunnels, over 11,000 feet elevation, and was greeted with rainy and snowy roads heading east, all in under three days. This is a powerful demonstration of the safety and efficiency that can be achieved when autonomous trucks become commercially available.

Quanergy Partners with Geely

Quanergy Systems, Inc., a leading provider of LiDAR (Light Detection and Ranging) sensors and smart sensing solutions, announced that the company was selected as a LiDAR partner for Geely Automotive Group (“Geely”), one of the largest and most innovative automotive companies in the industry. Geely and Quanergy will have a deep collaboration in developing and commercializing solutions for the broad deployment of smart city and autonomous vehicle systems.

Nuro & Walmart Grocery Delivery in Houston

Nuro, a robotics company transforming local commerce, and Walmart are announcing today a collaboration to bring grocery delivery to Houston-based customers. The pilot program will offer a new, affordable and accessible delivery option to a select group of Walmart customers in Houston through Nuro’s autonomous vehicles.

In the coming months, the autonomous delivery service will be available to Houston customers who have opted into the program. The service will use R2, Nuro’s custom-built delivery vehicle that carries only products with no onboard driver or passengers, and autonomous Toyota Priuses, all powered by Nuro’s proprietary self-driving software and hardware.

Read all autonomous vehicle news.

SUBSCRIBE

You are welcome to subscribe to receive emails with the latest Autonomous Self-Driving Driverless and Auto-Piloted Car News , you can also get weekly news summaries or midnight express daily news summaries.