Automated Driving Control Bypass Architecture for Fault Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated driving control systems face challenges in meeting requirements for real-time performance and safety, and struggle to quickly recover from anomalies.
Innovation Solution
The system includes a data exchange unit, computing units, a sensor fusion unit, and a planning control unit, with optional bypass configurations that allow continued operation even if individual units fail, ensuring uninterrupted automated driving functions by rerouting data and instructions through alternative pathways.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a centralized data exchange unit is used for data distribution, then system integration is simplified, but real-time performance and reliability deteriorate when anomalies occur
Solution Approach 1:
The patent divides the centralized data exchange function into multiple distributed data exchange units, each capable of independent operation. This segmentation allows the system to maintain data distribution capabilities even when individual units fail, thereby improving reliability and real-time performance without significantly increasing integration complexity.
Solution Approach 2:
The patent implements redundant data exchange units that stand by in advance to compensate for potential failures of primary units. This beforehand cushioning ensures that when anomalies occur, backup units can immediately take over, maintaining system reliability and real-time performance.
2Measurement precision
If multiple image capturing apparatuses and sensors are connected for comprehensive perception, then perception accuracy improves, but system complexity and data processing burden increase
Solution Approach 1:
The patent segments the system into modular functional units (image capturing apparatuses, sensors, data exchange units, computing units) that operate independently but coordinate through standardized interfaces. This modular segmentation maintains comprehensive perception capabilities while reducing overall system complexity through clear division of responsibilities.
Solution Approach 2:
The patent designs data exchange units and computing units with universal interfaces and protocols that can handle data from multiple different sensor types. This multi-functionality allows the system to integrate diverse sensors for improved perception accuracy without proportionally increasing system complexity, as the same communication infrastructure serves multiple purposes.
3Productivity
If high computing power is allocated for real-time processing, then real-time performance improves, but system cost and power consumption increase
Solution Approach 1:
The patent divides computing functions across multiple distributed computing units rather than concentrating all computing power in a single high-performance processor. Each computing unit handles specific processing tasks, enabling real-time performance through parallel processing while reducing the power consumption burden on any single component and allowing for more energy-efficient hardware selections.
Data Source
AI summary
The invention relates to an automated driving control system, including: a data exchange unit configured to obtain video data streams and distribute the video data streams to at least one computing unit; the at least one computing unit configured to compute perception result data based on the video data streams; a sensor fusion unit configured to fuse the perception result data and sensor data, to obtain fusion result data; and a planning control unit configured to generate a driving control instruction based on the fusion result data, where the planning control unit or the sensor fusion unit is configured to provide a bypass of the data exchange unit. When anomalies occur in any of the units, the automated driving control system may provide a corresponding bypass to keep an automated driving function going.