19 June 2025
Deploying high-accuracy neural networks on embedded systems is a major challenge. Developers are forced to balance performance, memory constraints, and power consumption – all while ensuring model accuracy remains intact. That’s where quantization-aware training (QAT) becomes essential.
Read More
15 May 2025
At aiMotive, we're constantly pushing the boundaries of what's possible in virtual testing. Today, we're excited to share a breakthrough setting a new industry benchmark: in partnership with AVL ZalaZONE , we've created the world's first neural-reconstructed, fully digitalized automotive proving ground.
Read More
13 March 2025
Neural reconstruction has advanced significantly in the past year, and dynamic models are becoming increasingly common. However, these models are limited to handling in-domain objects that closely follow their original trajectories.
Read More
19 February 2025
Testing Advanced Driver Assistance Systems (ADAS) and Automated Driving (AD) systems is an enormous challenge. The sheer number of possible driving scenarios is overwhelming, and traditional Design of Experiments (DoE) methods struggle to efficiently identify edge cases—those rare but critical situations where system performance is pushed to its limits.
Read More
5 November 2024
In the world of automotive sensor simulation, designing realistic and high-fidelity 3D environments is crucial. These environments form the foundation for testing and validating ADAS (Advanced Driver Assistance Systems) and automated driving technologies. However, creating such detailed virtual worlds presents a number of significant challenges and design considerations. This blog post dives into those product-level decisions and trade-offs we face when implementing neural reconstruction techniques.
Read More
24 September 2024
Welcome to the third edition of our newsletter: Automotive Simulation Meets AI. Read Tamás Matuszka 's blog about aiMotive's research contributions to global conferences. If you like this blog and enjoy reading technical texts on AI, neural rendering, simulation, and other automated driving-related technologies, consider subscribing to this newsletter!
Read More
16 August 2024
Read Zoltán Hortsin's blog about aiSim’s General Gaussian Splatting renderer. If you like this blog and enjoy reading technical texts on AI, neural rendering, and simulation, consider subscribing to the Automotive Simulation Meets AI newsletter on LinkedIn.
Read More
23 April 2024
aiWare achieves ASIL B compliance with only 15% silicon area overhead and less than 1% performance impact.
Read More
17 February 2022
The choice of hardware platform for tomorrow's ever-more-complex vehicles is a daunting prospect. Many designers select the most flexible hardware they can find, as it has the best chance to accommodate software developed in the years ahead.
Read More
17 November 2021
aiSim high-fidelity sensor & environment simulation and AVL tools provide a flexible solution for testing automated emergency manoeuvres end-to-end. Check out our latest joint whitepaper about this topic.
Read More
27 November 2020
Conventional wisdom says to execute a huge computation task like AI you need a single huge processor. In our latest white paper, Tony King-Smith explains how by understanding the inherent parallelism in NN algorithms used in automotive AI systems, multiple smaller processors can deliver the same throughput with superior scalability, flexibility and robustness.
Read More
14 May 2020
This case study, explores the path Nextchip took to create something truly unique. By looking beyond the requirements of the hardware itself to the solutions their customers needed, Nextchip found a supplier of industry-leading hardware IP in AImotive.
Read More