Siemens has launched a startup venture for simulating machine learning systems in autonomous vehicles and industrial automation
Simulytic is headed by CEO Andrea Kollmorgen, who was previously vice president and head of connected eMobility at Siemens and Andy Gill, the former director of connected mobility.
The startup is focused on accelerating autonomous mobility deployment at scale with reliable synthetic data. Simulytic aims to use simulation tools and digital twins to create insight into the impact and safety of autonomous driving.
Simulytic, based in Munich, is already applying Siemens’ experience in the simulation of complex, automated systems and in the use of artificial intelligence in safety-critical applications. Siemens already builds digital twins of vehicles with simulation through the Pave 360 tools and Siemens EDA technology.
This enables the venture to make competitive, comprehensive and independent assessments of incident probabilities, changing traffic flows and congestion patterns, the effects of weather and road conditions, and many other localized factors.
It is building an ecosystem of libraries of simulated driving data in digital replicas of deployment areas that can then be augmented by driving activity in the real world. Using digital tools to understand the consequences is the only way to get around the challenge and equip companies such as insurers with the data necessary to understand a complex, dynamic risk environment, says the company.
- Siemens looks to digital twin, IoT to drive growth
- Europe to build a digital twin of the earth
- Siemens acquires marine digital twin software
- Bosch builds digital twin for more accurate maps
The starting point is not likely to be comparing risk profiles of individual AV companies, but rather in identifying important risk factors for different operational domains. This starts with a digital twin of the geographical deployment area that is created from a 3D model built from high definition maps.
The model is populated with a representative traffic mix of cars, pedestrians, cyclists together with the actual infrastructure elements that are present such as traffic signs, traffic lights and road markings. The local behaviours of the traffic and vulnerable road users are used to create their respective behavioural models. All static and dynamic elements in this digital twin can be varied according to the actual variety seen in the location, including velocities, the extent to which traffic rules are obeyed, the quality of the signs and markings, the weather conditions. Meaningful edge cases and complex scenarios for the type of deployment location are also generated.