Autonomous Driving Fallback Routing for External Perception Failures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving systems face challenges in ensuring safety when external physical situation perception fails due to unpredictable situations such as road construction or accidents, which were not anticipated during the design phase.
Innovation Solution
A method and device for handling external abnormalities in autonomous driving systems that include collecting physical situation information from multiple sensors, repeatedly performing situation perception operations, selecting operation modes based on perception results, and generating route plans to ensure safe driving, even in low-performance computing environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple sensors and repeated perception operations are used to improve reliability, then safety is improved, but device complexity and computational burden increase
Solution Approach 1:
The patent segments the autonomous driving system into multiple independent sensors (camera, radar, LiDAR) and divides the perception task into repeated operations. Each sensor operates independently to collect data, and the system performs multiple perception cycles to ensure reliable detection, thereby improving safety through distributed redundancy rather than centralized complexity.
Solution Approach 2:
The system performs preliminary sensor calibration and establishes backup perception protocols before critical failures occur. By pre-configuring multiple sensors and defining fallback procedures in advance, the system ensures safety without requiring complex real-time decision-making when failures are detected.
2Reliability
If multiple sensors and repeated perception operations are performed to improve reliability, then safety is improved, but processing time increases
Solution Approach 1:
The patent implements periodic perception operations at optimized intervals rather than continuous processing. Sensors collect data at regular intervals, and the system performs perception cycles periodically, balancing the need for reliable detection with acceptable response time for autonomous driving decisions.
Solution Approach 2:
The system uses multiple sensors to create redundant copies of environmental perception data. Instead of performing extensive processing on a single data source, the system collects parallel data copies from different sensors (camera, radar, LiDAR) and uses simple fusion logic to ensure safety, reducing overall processing time while maintaining reliability.
3Measurement precision
If advanced perception algorithms are used to improve accuracy, then measurement precision is improved, but computational requirements increase
Solution Approach 1:
The patent employs sensors and algorithms that serve multiple functions simultaneously. The same sensor data is used for both detailed object recognition and basic presence detection. Multi-functional perception algorithms process data to achieve high accuracy for critical targets while maintaining lower computational overhead for general environmental awareness, reducing overall energy consumption.
Solution Approach 2:
The system dynamically adjusts perception algorithm parameters based on operational context. For high-priority targets requiring high accuracy, the system increases measurement precision with more computationally intensive processing. For lower-priority detection tasks, the system uses simplified algorithms with lower computational requirements, optimizing the balance between accuracy and energy consumption.
Data Source
AI summary
A method of handling an external abnormality in an autonomous driving system, performed in a device including a memory and a processor electrically connected to the memory, includes collecting physical situation information outside an autonomous vehicle from at least one sensor installed in the autonomous vehicle through the processor, repeatedly performing a physical situation perception operation for a preset critical time through the processor, selecting one of a plurality of operation modes according to a result of the physical situation perception operation and generating a route plan for the autonomous vehicle through the processor, and controlling driving of the autonomous vehicle according to the route plan through the processor.