28 December 2022
aiWare4+ – Neural Processing Unit for the future
aiMotive’s latest NPU is aimed at the next-gen automated driving workloads
Read MoreNews & insights
21 October 2022
aiMetrics - Insights into the performance of your automated driving software
aiMotive has developed a comprehensive tool for evaluation of NN algorithms, detection SW and automated driving software. It tracks development progress against requirements and provides real-time insights and gap analysis.
Read More
5 October 2022
Synthetic data generation – beating the data challenge of automated driving
Data is critical to neural network (NN) development. Automatic annotation is the most effective and cheapest way to generate training and validation data from real-world recordings. But what about hard-to-capture scenarios or corner cases that hardly ever occur in real life? Automated driving systems still need to be aware of such events.
Read More
23 September 2022
aiMotive paper to be presented at a scientific conference in Vietnam
The paper titled 'A Novel Neural Network Training Method for Autonomous Driving Using Semi-Pseudo-Labels and 3D Data Augmentations' written by Tamás Matuszka and Dániel Kozma has been accepted to the 14th Asian Conference on Intelligent Information and Database Systems (Category B in the 2021 CORE conference rankings) and will be published in Springer's Lecture Notes in Artificial Intelligence. The work will be presented in Ho Chi Minh City, Vietnam, on November 28-30, 2022.
Read More
25 August 2022
Auto annotation: cost-efficient, fast and adaptive
Annotation is the most expensive element of training data generation, so truly automatic annotation remains the holy grail of automated driving development – aside from the ability to generate synthetic data that is indistinguishable from real data.
Read More
28 July 2022
Data recording — the right way
Our newest product, aiData, became available to selected partners a few months ago. The product includes five tools that can help partners and customers, ranging from data capture to data processing. In this blog series, we will take a closer look at these tools, starting with aiRec, responsible for data recording.
Read More
21 July 2022
Ensuring safety – on every level
Safety is the most critical element of automated driving — check out our aiDrive safety report which was recently revised to provide a deeper understanding of the wide range of processes we use to ensure safe testing and operation of our solutions.
Read More
14 January 2022
aiDrive 3.0 – the solution for automated driving
The latest generation of our automated driving full software stack, aiDrive 3.0, has just been released, featuring our in-house model-space based perception, which is the most solid foundation for automated driving solutions.
Read More
24 November 2021
aiSim integrates ROS
The world's first ISO26262 certified virtual validation suite, aiSim, has integrated ROS2, making it instantly compatible with one of the most popular prototyping frameworks for advanced driver-assistance systems and automated driving solutions.
Read More
20 October 2021
The most adaptive to change will survive
Bernhard Bihr joined aiMotive in the summer of 2020. With his over 30 years of automotive experience, his goal is to support aiMotive's development efforts.
Read More
7 October 2021
Which sounds scarier: a robot cutting you open or driving you to work?
A 2020 survey showed that most respondents would be more comfortable letting a robot perform surgery on them than sitting in a car with autonomous tech in it. Would you?
Read More
27 July 2021
We are on a mission – To save 1.2 million lives every year
Lately, attention is turning towards self-driving cars again. Some people envision driverless vehicles in the next couple of years; others struggle with the idea to trust a "robot" with their life. While some fear artificial intelligence with evil intentions, it might be time to wonder what are the ultimate goals that drive us and the teams at the heart of the AD and ADAS industry forward?
Read More
15 July 2021
End-to-end HiL testing with aiSim to maximize coverage
The aiSim team adapted the Hardware-In-the-Loop testing approach with a unique spin on the concept that allows for testing complete automated driving systems with live simulated sensor data without any prerecorded footage. In this post, I will provide some insights into the benefits and challenges of introducing this powerful and exciting new feature to aiSim.
Read More
15 June 2021
Efficiency, not Utilization or TOPS: why it matters
Technology leadership claims can often be “economical” with the truth, and this is particularly true for NPUs (Neural Processor Units). However, over-stated performance can lead to procurement decisions that fall short of expectations. The result is engineering targets missed, deadlines not met, and R&D costs escalating. For its aiWare NPU, AImotive focuses on benchmarking NPU efficiency to provide the best information for AI engineers. Many other NPU suppliers quote raw TOPS and hardware utilization as a measure of performance. What’s the difference, and why does it matter?
Read More
3 June 2021
Introducing our new CCO – Q&A with Arnaud Lagandré
Joining AImotive with decades of automotive experience, our new Chief Commercial Officer has been at the heart of the automotive industries transition towards ever-higher levels of automation. Arnaud Lagandré brings a solution-focused attitude and in-depth cultural knowledge to AImotive. However, it's best to let people speak for themselves. We sat down with Arnaud to learn more about him and his motivation behind joining AImotive.
Read More
20 May 2021
aiSim raytracing integrates Vulkan API to supercharge validation performance
Simulating the sensor modalities used in automated driving efficiently and accurately is an immense challenge. The best solutions is to rely on GPU-accelerated raytracing techniques and the efficient distribution of tasks. Today, the Vulkan API is the only tool that can support such a system – that’s why we’ve integrated it into aiSim.
Read More
17 May 2021
Q&A: aiMotive CEO Talks Sony Car, SiliconChips and New Market Opportunities
Laszlo Kishonti sees a potential opening for aiMotive as non-traditional players look to enter the battery-electric market. In order to move quickly and be competitive, they’ll need to rely on companies like his for advanced technology, he believes.
Read More
6 May 2021
Camera simulation – GPU is the only limit
In 2020 aiMotive's aiSim™ simulator was certified to TCL 3 according to ISO 26262:2018 by TÜV-Nord. This made it the world's first ISO26262-certified comprehensive automated driving simulator for the development of automated driving solutions. Let’s go a layer deeper and see what’s under the hood: what makes aiSim's rendering engine special and unique.
Read More
11 March 2021
Automated electric vehicles will rule our roads by 2030
Is the future electric, self-driving or both? The answer is complex and influenced just as much by long-term industry trends, regulation and consumer demands, as how quickly the technology develops. Let’s take a closer look.
Read More
28 January 2021
aiWare™ Studio: helping optimize algorithms, not accelerators
For embedded applications, the biggest challenge is taking a concept from a prototype in the lab to a production-ready solution: a product that is robust over lifetime, certified to all the relevant standards, tested to ensure it always works, and cost-engineered to make sure it delivers a profit. You need tools designed to help engineers do that job as flexibly as possible.
Read More
12 January 2021
How aiDrive accelerates Sony’s VISION-S Prototype
Delivering automated driving and driver assistance functions for a brand-new vehicle designed from scratch is a huge opportunity. We can fine-tune the sensor setup, the processing platform, the vehicle signals, and find ways to integrate all of them in the vehicle as seamlessly as possible while maximizing the value offered to the driver.
Read More
13 November 2020
For software leadership, control your hardware
Apple’s recent announcement of the new M1 chip powering their latest Macs, following many years of successful deployment of their Ax chips powering their smartphones and tablets, demonstrates their use of hardware closely coupled to their software to maximize their product leadership. But why do they invest so much in their hardware platform?
Read More
11 November 2020
Automating the real world – The power of the AImotive Fleet
At AImotive, we heavily rely on perfecting simulation testing for our automated driving development efforts. This push has led to the creation of aiSim, the world’s first ISO 26262-certified simulator for automated driving systems. However, not even the best simulation can substitute the real world...
Read More
2 November 2020
Procedural traffic generation: what are the options?
In five years, AImotive has created what no company has done before: the world’s first automotive grade, ISO26262-certified simulator, aiSim. However, it is not enough to have high-fidelity vehicle dynamics, realistic sensor models and last but not least realistic traffic simulation....
Read More
21 September 2020
Bigger is not always better: exploiting parallelism in NN hardware
When considering hardware platforms for executing high performance NNs (Neural Networks), automotive system designers frequently determine the total compute power by simply adding up each NN’s requirements...
Read More
8 September 2020
Haste makes waste
Efficiency has always been at the core of everything we do at AImotive, which is why we realized early on that the quality of data collection is more important than its quantity, and that there are much smarter methods than standard data collection practices.
Read More
17 August 2020
Accelerating remote automotive development
The unprecedented situation that has developed as a result of the current COVID-19 outbreak has brought a new range of challenges to the fore in automotive software development. At AImotive, we are relying on...
Read More
11 August 2020
Ensuring safety – on every level
To build a scalable technology platform for automated driving, we need to focus on safety throughout our development cycle. We have created a public Safety Report to show the framework of our approach to safety in ADAS.
Read More
5 August 2020
The key to success is continuous development
At AImotive we are working to catalyze the mass deployment of automated driving solutions. In order to make these accessible to all, we still have to overcome several obstacles with our partners.
Read More
21 May 2020
Design, code, test, repeat
Solving continuous integration – continuous deployment (CICD) development for safety critical automotive software is a complex challenge. While simulation is a vital aspect of the solution, simply having a simulator is not everything. At AImotive, we have created a unique CICD development pipeline, that relies on simulated and real-world data to ensure safe development.
Read More
11 February 2020
Production L2-L3 ADAS begins with hardware
To get ADAS right, you have to start with the hardware. You can create the most advanced perception, robust decision making, detailed planning algorithms, but without a robust, reliable hardware platform with sufficient guaranteed performance, any deployment strategy will simply fail.
Read More
9 August 2019
How to train your wagon – Reinforcement Learning for Automated Driving
First came computer vision and traditional algorithms, then supervised-learning artificial intelligence. Yet we continue to find limitations in what machines can do. A novel approach is to train AI as we would train a pet, or even, as we often learn ourse
Read More
1 August 2019
Is liability bugging you?
Guidelines for software devs and safety drivers to mitigate personal liability. The question of personal liability in automated driving development is surprisingly common, as everyone is aware of the risks involved. At the first AImotive Meetup in Bud
Read More
18 July 2019
Standardized scenarios for safer roads
Scenarios are the base of simulation testing for automated driving systems, just as simulation testing is the base of safe automated driving. However, until recently moving scenarios from one simulator to another was almost impossible. This has to change.
Read More
2 July 2019
Powering autonomy
Higher levels of autonomy will require dedicated chips built for self-driving. However, developing hardware platforms requires unique expertise of a kind that most traditional automotive OEMs don’t have.
Read More
17 May 2019
Do AVs need distributed computing?
Currently, many AVs use a powerful central compute platform, but as the technology, safety standards, and regulations mature even these platforms cannot deliver the performance needed. Distributed processing offers some answers, especially for AVs.
Read More
30 April 2019
Open standards for safe automated driving
The proliferation of increasingly advanced automated driving technologies poses a new challenge for the automotive industry. One, that traditional safety standards are not equipped to solve.
Read More
12 April 2019
Inference at the Edge
Many believe that Neural Network (NN) hardware accelerators are great for anything using NNs. However, NN training is very different to NN inference as happens in applications like autonomous vehicles (AVs). This blog explains the differences, and why aiW
Read More
19 March 2019
From Walled Gardens to Collaboration
First people thought self-driving was a sprint race, now many think it’s a marathon. However, it’s turning out to be an ultra-marathon relay. No one can solve the challenges of self-driving alone: the future to automation lies in collaboration.
Read More
28 February 2019
Modular technology meets automotive supply chain needs
What’s the problem?Creating production-ready, compute-intensive AI-enabled hardware platforms for automotive is becoming one of the most innovative, dynamic and creative areas for the semiconductor industry.
Read More
15 February 2019
Sensor fusion paves the way to safer self-driving
No single sensor can handle the whole of self-driving, however, when utilizing sensor fusion the strengths and weaknesses of different sensor types have to be considered.
Read More
31 January 2019
It's all about collaboration
The future of automated driving lies in collaboration. However, this has its different forms and levels. The way forward is paved with standardization, modular software architectures, and flexible designs.
Read More
3 January 2019
2018 Changed Self-Driving
Much has changed in the autonomous industry over the past year, and even bigger changes are coming in 2019.
Read More
19 December 2018
Precision simulation demands flexibility and scalability
Automotive simulation has a specific set of demands. Meeting them is no simple task.
Read More
29 November 2018
Autonomous Technology Needs Better Simulation
Simulation is a game changer in autonomous technology, but more has to be done.
Read More
22 November 2018
Tackling the upgradeability of automotive computer systems
The demand for ever more advanced high-performance real-time compute processing hardware is increasing rapidly across the automotive industry.
Read More
16 October 2018
Distributed vs. central processing: the eternal debate
As computer systems became more complex the question arose: centralize all resources, or distribute processing?
Read More
1 October 2018
How self-driving cars understand the world (map)
It may sound trivial, but getting a self-driving system to understand its own movement is no easy task.
Read More
16 August 2018
Why Sensor Fusion is Critical for Self-Driving Cars
Self-driving is one of the greatest challenges of our age. For the first time, we have the technological background, spatial and temporal resolution for a robotic system to fully understand its surroundings.
Read More
12 July 2018
Safety Defines Autonomous Development
Functional safety is, without a doubt, the most crucial factor in safety-critical environments such as automotive development. Not only because you gain the trust of customers but because you would put the health and safety of test drivers and more import
Read More