AI Technologies
Sensor Fusion & Physical AI
Combining information from different physical measurement sources – camera, radar, LiDAR, and other sensors – as the basis for systems that act in the real world.
Tested in road traffic
AI-Based Environment Perception for Autonomous Public Transport
Perception in the vehicle and the digital environment model of the operating area work hand in hand: what the vehicle detects becomes permanently usable knowledge about the environment.
Starting point
If a vehicle is to make decisions without a driver, it is not enough to see what is happening in front of it right now. It also has to know how its world is structured, how that world changes and which rules apply there.
Approach
- In the vehicle: camera, LiDAR, radar and satellite positioning capture the immediate surroundings in real time
- In the operating area: digital twin, high-precision map and geodata form the memory of the overall system
- Detections are localised, classified and rated with a measure of reliability
- Every detection is assigned a spatial position and entered into the digital twin
What is in place
- Measurement drives through the Kaßberg district of Chemnitz: road users, roadway, traffic lights and traffic signs are detected automatically
- Traffic sign recognition with multimodal fusion of image crop, standard description and example symbol
The same principle extends beyond the tram: to autonomous shuttles, micromobility and goods transport as well as autonomous mobile machinery.
Two kinds of perception
| In the vehicle | In the operating area | |
|---|---|---|
| Task | Capture the immediate surroundings in real time | Model the environment over the long term |
| Sources | Camera, LiDAR, radar, satellite positioning | Digital twin, high-precision map, cadastral and traffic data |
| Result | Objects, traffic signs, lanes, other road users | Context for decisions, basis for planning and simulation |
Six questions every vehicle has to answer
- Where am I?
- Where am I allowed to drive?
- What is a permanent part of my world?
- What has changed?
- What is moving right now?
- And how certain am I of that?
The same methods that the vehicle uses in operation build and maintain the knowledge about the environment, automatically and continuously. Because traffic spaces change: construction sites appear, vegetation grows.
Further topics
AI Technologies
Multimodal AI
Every data source has its strengths and limits. The result becomes reliable when text, images, audio, sensor data, and geodata are interpreted together.
AI Technologies
Vision AI
Image-based and video-based AI, grown out of many years of experience in industrial machine vision.
AI Technologies
GeoAI & Spatial Intelligence
Analysing spatial information intelligently and combining it with visual and other data.
Industries
Automotive and Mobility
Environment perception, sensor data fusion and digital environment models, plus AI support for the software engineering process.
Would you like to make AI usable in your company?
Whether a first AI adoption or a complex development task – we discuss the requirements and suitable next steps with you.