Maneuver-Aware Surroundings Detection for Automated Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated driving systems struggle to efficiently and resourcefully detect relevant surroundings in complex urban environments, where numerous road users and dynamic conditions require focused detection to ensure safety.
Innovation Solution
A method and device that determine relevant regions of the surroundings based on maneuver categories, using predefined base regions adjusted by current vehicle and environmental parameters, allowing focused detection and reducing computational and memory requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If comprehensive detection of all surroundings is performed, then detection completeness is improved, but computational resources and processing time increase
Solution Approach 1:
The surrounding environment is segmented into multiple base regions (front, rear, left, right, and diagonal regions) based on the vehicle's maneuver category. Each base region is further divided into relevant and irrelevant sub-regions. This segmentation allows the system to focus computational resources on detecting obstacles in relevant regions while reducing or skipping detection in irrelevant regions, thus resolving the contradiction between detection completeness and computational resource consumption.
Solution Approach 2:
Different detection strategies are applied to different regions based on their relevance. Relevant regions (where obstacles pose a safety risk) receive intensive detection and processing, while irrelevant regions (where obstacles do not pose a safety risk) receive reduced or no detection. This local differentiation optimizes computational resources by concentrating processing power where it is most needed, maintaining detection reliability for critical areas while reducing overall computational burden.
2Use of energy by moving object
If detection focus is narrowed to relevant regions, then computational resources are reduced, but detection coverage may be compromised
Solution Approach 1:
The environment is segmented into base regions that are further divided into relevant and irrelevant sub-regions. This segmentation structure ensures that detection coverage is strategically allocated: relevant regions receive full detection coverage while irrelevant regions are excluded. The segmentation approach maintains comprehensive coverage for safety-critical areas while reducing computational resources spent on non-critical areas.
Solution Approach 2:
The maneuver category determination unit acts as an intermediary that analyzes the current driving situation and selects the appropriate base region(s) for detection. This intermediary layer mediates between the need for comprehensive detection and the desire to reduce computational resources by filtering out irrelevant regions based on the determined maneuver category, thus maintaining detection coverage where needed while reducing overall processing requirements.
3Adaptability or versatility
If detection parameters are adjusted dynamically, then adaptability to changing conditions is improved, but system complexity increases
Solution Approach 1:
The system dynamically adjusts detection parameters and selected base regions based on the determined maneuver category. Different maneuver categories (e.g., straight driving, turning, lane changing) trigger different detection configurations, allowing the system to adapt to changing driving conditions. This dynamic adjustment maintains high adaptability while managing complexity through predefined maneuver category-based configuration rules.
Solution Approach 2:
The system changes detection parameters (such as detection sensitivity, region selection, and processing priority) based on the determined maneuver category. By pre-defining parameter sets for different maneuver categories and switching between them, the system achieves adaptability to changing conditions without requiring complex real-time calculations, thus managing system complexity while maintaining versatility.
Data Source
AI summary
An automated method and device detects of transportation vehicle surroundings by determining a manoeuvre category of a currently performed manoeuvre of the transportation vehicle, ascertaining, based on the determined manoeuvre category, at least one base region assigned to the determined maneuver category in a stored association, determining a respective associated relevant region of the surroundings in the transportation vehicle surroundings for the ascertained at least one base region taking into consideration of current parameters of the transportation vehicle and/or the surroundings, wherein the relevant regions of the surroundings determined for each of the at least one base region are provided for the detection of the surroundings such that the surroundings detection are performed in consideration of the surroundings regions determined in each case.