Automated Vehicle Object Classification Using Digital Map Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated vehicles face challenges in efficiently distinguishing static and non-static objects in their environment, which affects their safe operation and resource allocation for trajectory planning and actuator control.
Innovation Solution
A method that uses environmental sensor systems to acquire data, compare it with a digital map, and determine the motion behavior of non-static objects to develop a travel strategy for the vehicle, optimizing resource use by distinguishing static and non-static objects and allocating computing capacity accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If all detected objects are processed with equal computational resources, then safety is maintained, but computing capacity is wasted on static objects
Solution Approach 1:
The patent segments objects into two categories: static objects (encompassed by digital map environmental features) and non-static objects (not encompassed by digital map). This segmentation allows different computational resource allocation strategies to be applied to different object types, optimizing overall system efficiency while maintaining safety.
Solution Approach 2:
The patent applies different levels of processing quality to different objects based on their static/non-static nature. Static objects receive minimal processing (identification only), while non-static objects receive full processing (motion behavior analysis, trajectory planning). This local quality differentiation optimizes computing capacity usage without compromising safety.
2Productivity
If computing capacity is reduced to optimize efficiency, then resource usage improves, but object detection accuracy may deteriorate
Solution Approach 1:
By segmenting objects into static and non-static categories, the system can apply appropriate detection precision to each category. Static objects are detected with lower precision requirements (sufficient for identification), while non-static objects receive higher precision processing (necessary for motion analysis and safety), thus optimizing overall resource usage without sacrificing critical detection accuracy.
Solution Approach 2:
The patent changes the processing parameters (computational resources allocated) based on the object type. Different parameter sets are applied: minimal parameters for static objects, full parameters for non-static objects. This dynamic parameter adjustment maintains necessary detection accuracy while optimizing resource consumption.
3Reliability
If motion behavior analysis is performed on all objects, then safety is improved, but computing capacity is wasted on static objects
Solution Approach 1:
The patent segments the object processing workflow into two paths: static objects are identified and tracked with minimal resource usage, while non-static objects undergo full motion behavior analysis. This segmentation ensures safety-critical processing is applied only where necessary, optimizing computing capacity usage.
Solution Approach 2:
The patent extracts the motion behavior analysis step from the universal processing pipeline and applies it only to non-static objects. By taking out this computationally intensive operation and applying it selectively, the system maintains safety for dynamic objects while avoiding waste of computing capacity on static objects.
Data Source
AI summary
A method and apparatus for operating an automated vehicle. The method includes: acquiring environmental data values which represent objects in an environment of the automated vehicle; determining a position of the automated vehicle; comparing the environmental data values with a digital map, depending on the position of the automated vehicle, the digital map including environmental features, a first subset of the objects being determined as static objects when these objects are comprised as environmental features in the digital map, and a second subset of the objects are determined as non-static objects, when these objects are not comprised as an environmental feature in the digital map; determining a motion behavior of the non-static objects relative to the automated vehicle; determining a travel strategy for the automated vehicle, depending on the motion behavior of the non-static objects; and operating the automated vehicle, depending on the travel strategy.