Method and Device for Operating a Driver Assistance System, and Driver Assistance System and Motor Vehicle

Simple SummaryContent extracted from patent full text and abstract with AI.

The invention discloses a method and device for operating an automotive driver assistance system that can predict the movements of living objects (such as pedestrians, cyclists, or animals) in the vehicle's surroundings. It does this by using motion models tailored for different types and combinations of objects, processing sensor data (e.g., from cameras), recognizing and classifying objects, and computing their likely movements relative to each other. The system uses these predictions to improve the operation of the driver assistance system, supporting actions like steering and braking to avoid collisions.

Use CasesContent extracted from patent full text and abstract with AI.

• Autonomous or semi-autonomous driving systems that need to accurately anticipate pedestrian or cyclist movement.
• Advanced collision avoidance systems in modern vehicles.
• Urban driving scenarios where interactions with dynamic entities (pedestrians, animals, cyclists) are frequent.
• Integration into smart city infrastructure for traffic safety analytics and alerts.
• Enhanced adaptive cruise control and emergency braking features in cars.
• Fleet vehicle monitoring for improved safety analytics.
• Retrofit kits for existing vehicles to upgrade their safety systems with predictive pedestrian detection.

BenefitsContent extracted from patent full text and abstract with AI.

• Significantly improves the safety of vehicle occupants and other road users by enabling more accurate and dynamic collision avoidance interventions.
• Capable of distinguishing between different types of objects and adjusting predictions based on their specific behaviors and interactions.
• Reduces false positives and unnecessary emergency maneuvers by providing context-aware predictions of movement.
• Enables vehicles to handle complex urban environments and mixed traffic scenarios more effectively.
• Supports scalability and extensibility as additional object classes, sensors, or motion models can be integrated.
• Allows for real-time processing and prediction using sensor data from multiple sources (e.g., cameras, lidars, radars).
• Potential to improve public trust in autonomous and highly automated vehicles by increasing their reliability and perceived safety.

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

The invention relates to a method and a device (14) for operating a driver assistance system (12), and to a driver assistance system (12) and a motor vehicle (10), said method being used to predict a movement of at least one living object (16) in the surroundings (17) of the motor vehicle (10), said method comprising the following steps: a) storing motion models characterising movements for a combination of object classes; b) receiving measuring data relating to the surroundings (17); c) recognising the living object (16) and at least one other object (18, 20, 22) in the surroundings (17) and determining a relative position of the objects (16, 18, 20, 22) in relation to each other; d) identifying the object classes of the known objects (16, 18, 20, 22); e) for the living object (16): i) developing an equation of motion at least according to the respective position of the living object (16) in relation to the other object (18, 20, 22) as well as the motion model stored for the combination of the identified object classes; and ii) predicting the movement on the basis of the equation of motion; and f) operating the driver assistance system (12) taking into account the predicted movement.