Our journey began at the Institute of Embedded Systems at ZHAW, where we worked together on a wide range of embedded engineering projects.
Over the years, we gained experience across hardware design, firmware development, embedded Linux, high-speed interfaces and AI-enabled
edge systems.
Among these disciplines, we developed a particular passion and deep expertise for the NVIDIA Jetson ecosystem.
Working on numerous Jetson-based projects, we saw both the platform's enormous potential and its challenges. Developing reliable products around NVIDIA Jetson
requires expertise spanning hardware, firmware, Linux, and embedded software. At the same time, experienced engineers with this combination of skills are rare,
making it difficult for many companies to adopt the platform efficiently.
Conducting a feasibility study for a video transmission method that enables the transmission of formats up to 8K at 60 fps
with a maximum latency of 17 ms using a NVIDIA Jetson Orin NX.
In addition, an evaluation will be carried out of various approaches to synchronise the remote screen with the video
source across the entire transmission link.
Project →
We develop a distributed machine learning system to sort out defect plastic parts during production. Main challenge is the transferability of learnt process know-how from case to case; the solution builds on domain adaptation, continual data-centric deep learning and federated edge computing on a Jetson Orin Nano. Project →
For their novel surgical research and teaching centre OR-X, the university hospital of Balgrist needed a Data Hub solution, allowing to synchronise signals of TOF cameras, optical tracking systems and robots in a simulated operating room and exchange them with a central DGX server. The implementation is based on the NVIDIA Jetson Orin NX platform and implements a software based 25 Gbps Ethernet Switching engine. Project →
Development of a battery-powered audio-visual sensor platform for edge AI computing with highly scalable processing and ultra low power consumption. It enables AI applications at the edge while providing very long battery lifetimes. Project →
Implementation of fast photothermal off-resonance tapping in combination with data-driven control, dual actuation and advanced data-handling with machine learning support for atomic force microscopes. Project →