Tag Archives: Autonomous

KasperskyOS : First Successful Automotive ECU Integration!

KasperskyOS : First Successful Automotive ECU Integration!

Kaspersky just announced the first integration of their new automotive KasperskyOS into the ECU of an advanced driver assistance system by AVL SFR. Here are the details…

 

Automotive KasperskyOS : What Is It?

Modern vehicles are complex systems, which makes it hard to manage the security of its components.

KasperskyOS for automotive ECUs combines a secure microkernel operating system, with a security policy enforcement engine (Kaspersky Security System), and a trusted channel encrypted framework.

It is designed to secure onboard systems and communications, ensuring safer OTA updates, fleet management and safer autonomous driving.

 

KasperskyOS Integration Into AVL ADAS ECU

The new AVL Software and Functions GmbH (AVL SFR) ADAS ECU features two high-performance SoCs (system-on-a-chip), and a safety controller..

This new ECU platform also supports Controller Area Network, and automotive Ethernet standards, allowing for secure communications between devices in the vehicle – including cameras and LIDARs.

The integration of KasperskyOS into the ECU guarantees that undeclared functionality – either unnoticed at launch, or inserted through system updates – cannot be exploited. This is especially important in the safety of autonomous vehicles.

All interactions between electronic components is controlled by the Kaspersky Security System, the security policy engine within KasperskyOS. It monitors the launch of processes, as well as communications between those components and the operating system.

This new ADAS ECU by AVL SFR is ready for prototyping projects by OEMs and Tier-1 suppliers.

 

Kaspersky Automotive Adaptive Platform for KasperskyOS

Kaspersky is also a new associate partner of AUTOSAR, a consortium aimed at developing mutual standards for automotive software architecture.

To that effect, they developed a software development kit (SDK) called Kaspersky Automotive Adaptive Platform.

With this SDK, AVL SFR can develop applications for automated and even driverless vehicles – such as delivering auto-piloting features, controlling safety systems and monitoring their health.

This set of libraries also allows for other software to be adopted, which follow AUTOSAR Adaptive requirements, and work on KasperskyOS without additional changes.

Kaspersky Automotive Adaptive Platform is ready to be delivered and AVL SFR is showcasing its auto-piloting application to several automotive customers.

 

Suggested Reading

Go Back To > AutomotiveCybersecurity | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!

NVIDIA DRIVE Deep Neural Networks : Access Granted!

NVIDIA just announced that they will be providing the transportation industry access to their NVIDIA DRIVE Deep Neural Networks (DNNs) for autonomous vehicle development! Here are the details!

 

NVIDIA DRIVE Deep Neural Networks : Access Granted!

To accelerate the adoption of NVIDIA DRIVE by the transportation industry for autonomous vehicle development, NVIDIA is providing access to the NVIDIA DRIVE Deep Neural Networks.

What this means is autonomous vehicle developers will now be able to access all of NVIDIA”s pre-trained AI models and training code, and use them to improve their self-driving systems.

Using AI is central to the development of safe, self-driving cars. AI lets autonomous vehicles perceive and react to obstacles and potential dangers, or even changes in their surroundings.

Powering every self-driving car are dozens of Deep Neural Networks (DNNs) that tackle redundant and diverse tasks, to ensure accurate perception, localisation and path planning.

These DNNs cover tasks like traffic light and sign detection, object detection for vehicles, pedestrians and bicycles, and path perception, as well as gaze detection and gesture recognition within the vehicle.

 

Advanced NVIDIA DRIVE Tools

In addition to providing access to their DRIVE DNNs, NVIDIA also made available a suite of advanced NVIDIA DRIVE tools.

These NVIDIA DRIVE tools allow autonomous vehicle developers to customise and enhance the NVIDIA DRIVE DNNs using their own datasets and target feature set.

  • Active Learning improves model accuracy and reduces data collection costs by automating data selection using AI, rather than manual curation.
  • Federated Learning lets developers utilise datasets across countries, and with other developers while maintaining data privacy and protecting their own intellectual property.

  • Transfer Learning gives NVIDIA DRIVE customers the ability to speed up development of their own perception software by leveraging NVIDIA’s own autonomous vehicle development.

 

Recommended Reading

Go Back To > Automotive | Business | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!


DiDi Adopts NVIDIA AI + GPUs For Self-Driving Cars!

At GTC China 2019, DiDi announced that they will adopt NVIDIA GPUs and AI technologies to develop self-driving cars, as well as their cloud computing solutions.

 

DiDi Adopts NVIDIA AI + GPUs For Self-Driving Cars!

This announcement comes after DiDi spliced out their autonomous driving unit as an independent company in August 2019.

In their announcement, DiDi confirmed that they will use NVIDIA technologies in both their data centres and onboard their self-driving cars :

  • NVIDIA GPUs will be used to train machine learning algorithms in the data center
  • NVIDIA DRIVE will be used for inference in their Level 4 self-driving cars

NVIDIA DRIVE will fuse data from all types of sensors – cameras, LIDAR, radar, etc – and use numerous deep neural networks (DNNs) to understand the surrounding area, so the self-driving car can plan a safe way forward.

Those DNNs (deep neural networks) will require prior training using NVIDIA GPU data centre servers, and machine learning algorithms.

Recommended : NVIDIA DRIVE AGX Orin for Autonomous Vehicles Revealed!

 

DiDi Cloud Computing Will Use NVIDIA Tech Too

DiDi also announced that DiDi Cloud will adopt and launch new vGPU (virtual GPU) cloud servers based on NVIDIA GPUs.

The new vGPU licence mode will offer more affordable and flexible GPU cloud computing services for remote computing, rendering and gaming.

 

Recommended Reading

Go Back To > Automotive | Business | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!


NVIDIA DRIVE AGX Orin for Autonomous Vehicles Revealed!

NVIDIA just introduced the DRIVE AGX Orin – a new software-defined platform for autonomous vehicles and robots!

Here is a quick primer on NVIDIA DRIVE AGX Orin, including its key capabilities and specifications!

 

NVIDIA DRIVE AGX Orin for Autonomous Vehicles + Robots

At GTC China 2019, NVIDIA unveiled the DRIVE AGX Orin – the culmination of a four-year development process.

The NVIDIA DRIVE AGX Orin is a new system-on-a-chip (SoC) designed to drive a software-defined platform for automatous machines.

The Orin is designed to handle large numbers of applications and deep neural networks simultaneously, while achieving systematic safety standards like ISO 26262 ASIL-D.

Built as a software-defined platform, the NVIDIA DRIVE AGX Orin can be used to develop architecturally-compatible platforms that are scalable from Level 2 to Level 5 (full self-driving) vehicles.

Since both Orin and Xavier are programmable through Open CUDA and TensorRT APIs and libraries, developers can work on both, leveraging their investments across both product lines.

Recommended : DiDi Adopts NVIDIA AI + GPUs For Self-Driving Cars!

 

NVIDIA DRIVE AGX Orin Performance

With 17 billion transistors, the Orin combines Arm Hercules CPU cores with NVIDIA GPU cores, as well as new deep learning and computer vision accelerators.

According to NVIDIA, the DRIVE AGX Orin delivers an aggregate performance of 200 trillion operations per second (200 TFLOPS) – almost 7X faster than the previous generation NVIDIA DRIVE Xavier SoC.

Recommended : NVIDIA DRIVE Deep Neural Networks : Access Granted!

 

Recommended Reading

Go Back To > Automotive | Business | Home

 

Support Tech ARP!

If you like our work, you can help support our work by visiting our sponsors, participating in the Tech ARP Forums, or even donating to our fund. Any help you can render is greatly appreciated!