Local Traffic Behavior Models for Self-Driving Vehicle Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing self-driving vehicle technologies face challenges in cost-effectively deriving and implementing local driving strategies to adapt to characteristic behaviors of local traffic in specific regions, such as town quarters, without adequately observing and predicting the behavior of other traffic participants.
Innovation Solution
The method involves observation units that measure relative dynamic parameters of traffic situations, derive behavior models describing expected traffic participant behavior, and store these models in a spatial database for self-driving vehicles to adapt their driving strategies based on region-specific data, using a combination of onboard and backend server components for data processing and sharing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If observation units extensively observe and record traffic situations to derive accurate behavior models, then the reliability of driving strategy adaptation is improved, but the cost and complexity of the system increases
Solution Approach 1:
The system segments the observation and data processing functions into distributed observation units that operate independently in different geographic regions. Each observation unit collects and processes local traffic data separately, then contributes to region-specific behavior models. This segmentation reduces the complexity of any single observation unit while maintaining high overall reliability through distributed data collection across multiple units.
Solution Approach 2:
The system performs preliminary observation and data collection continuously in the background before actual self-driving operations begin. Observation units pre-collect traffic situation data and pre-derive behavior models for various regions, so that when a self-driving vehicle enters a region, the appropriate behavior model is already available. This preliminary action ensures high reliability without requiring complex real-time processing during critical driving moments.
2Adaptability or versatility
If behavior models are derived from extensive observation of traffic situations, then the adaptability of driving strategies to local conditions is improved, but the time and resources required for data collection increase
Solution Approach 1:
The system performs preliminary data collection and behavior model derivation in advance, continuously gathering traffic situation data in the background before it is actually needed. Observation units pre-process and store region-specific behavior models so that when a self-driving vehicle enters a region, the adaptation is immediate without requiring time-consuming real-time data collection. This eliminates the time loss while maintaining high adaptability.
Solution Approach 2:
The system introduces a backend server as an intermediary that aggregates data from multiple observation units and performs centralized behavior model derivation. Instead of each observation unit requiring extensive independent observation time, the backend server combines data from multiple sources efficiently, reducing the total time needed to derive accurate regional behavior models while improving adaptability through comprehensive data analysis.
3Productivity
If multiple observation units collect and process traffic data independently, then the productivity of data collection is improved, but the difficulty of integrating and synthesizing behavior models increases
Solution Approach 1:
The backend server acts as an intermediary that receives data from multiple independent observation units and performs centralized synthesis of behavior models. Each observation unit independently collects and pre-processes local traffic data with high productivity, then contributes its findings to the backend server. The backend server integrates these contributions using standardized protocols and algorithms, resolving the integration difficulty while preserving the productivity benefits of distributed collection.
Solution Approach 2:
The system implements homogeneous data structures and communication protocols across all observation units, ensuring that data from different sources follows the same format and standards. This homogeneity in data representation and processing interfaces significantly reduces the complexity of integrating and synthesizing behavior models from multiple independent observation units, while maintaining high data collection productivity.
Data Source
AI summary
The invention is concerned with a method for supporting an autopilot functionality (A) of a self-driving vehicle (14) in coping with a respective characteristic behavior of local traffic (26) in a specific area (18). The method comprises that at least one observation unit (11, 12) observes at least one traffic situation (29, 30) in the corresponding area (18) for which the respective driving strategy is to be provided, wherein the observation concerns at least one relative dynamic parameter (35) of traffic participants (31, 32, 33, 34), and based on the observed at least one relative dynamic parameter (35) a behavior model (17) is derived that describes an expected behavior of the traffic participants (31, 32, 33, 34), and the derived behavior model (17) is stored in a spatial database (24) and may be downloaded by the at least one self-driving vehicle (14) when entering the respective area (18).