Research
Researching AI Safety
Our Team has been researching AI safety since 2016, focussing on hands-on solutions for a broad spectrum of industries and applications. As a result of our research our safe and certifiable AI technology Better AI™ has been implemented at the heart of our sensor AiDAR™.
Ongoing Research Projects
MUMOCAM
The aim of the project is to develop a multimodal person/ human protection system for mobile robots. The goal is to achieve a high degree of reliability in distinguishing between people and objects by merging RGB (visible light) and IR (infrared) sensor data. Part of this project involves safe person detection in accordance with safety level PL d as defined in ISO 13849-1.
SafeWahr
Our safety experts are working on the core of this BMWI research project of the German Federal Government. Focus is the safe release and reliable series operation through continuous real-time monitoring of the environment perception of autonomous vehicles.
Ai4CCam
The AI4CCAM research project is funded by the European Union and aims at developing an open environment for Trustworthy AI in CCAM operations, including:
Simulated and synthetic urban-traffic scenarios involving VRUs and an interoperable digital framework to manage and multiply these scenarios in conformance with Trustworthy AI requirements and security measures
Documentation about the risks related to the usage of AI in CAVs, an online participatory space for assessing and fostering the adoption of Trustworthy AI in CCAM
Simulated scenarios exhibiting human-vehicle AI-based interactions and ethical dilemmas, advanced AI models for CCAM situation awareness and VRUs behaviour anticipation, and car trajectory prediction.