Autonomous Driving Control Under Sensor Failure Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intelligent driving systems often completely exit autonomous driving modes when sensors fail, leading to reduced availability and user experience, despite ensuring driving safety.
Innovation Solution
A vehicle control method that determines driving policies based on the impact of sensor failures, allowing for the maintenance of current autonomous driving functions by disabling specific functions or switching to alternative sensors, rather than exiting all autonomous driving functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous driving system exits all autonomous driving functions when a sensor fails, then driving safety is ensured, but availability and user experience are reduced
Solution Approach 1:
The patent segments the autonomous driving function into multiple independent running conditions (e.g., cruising, vehicle following, lane keeping, lane changing, turning, parking). When a sensor fails, only the specific running condition affected by the sensor failure is disabled, while other running conditions that do not depend on the failed sensor continue to operate. This segmentation allows the system to maintain partial autonomous driving functionality rather than completely exiting the autonomous mode.
Solution Approach 2:
The system dynamically adjusts the autonomous driving function based on sensor status. Instead of a static all-or-nothing approach, the system evaluates the impact of sensor failure on each running condition and dynamically determines which conditions can continue to operate. This dynamic adjustment optimizes the balance between safety and availability by maintaining functionality where possible while ensuring safety where required.
2Reliability
If the autonomous driving system exits all autonomous driving functions when a sensor fails, then driving safety is ensured, but user experience is reduced
Solution Approach 1:
By segmenting the autonomous driving function into multiple running conditions and selectively disabling only those affected by sensor failure, the system maintains a better user experience. Users continue to benefit from autonomous driving capabilities in conditions that remain safe and functional, rather than experiencing a complete loss of autonomous driving functionality.
3Productivity
If the system maintains all autonomous driving functions when a sensor fails, then availability and user experience are improved, but driving safety may be compromised
Solution Approach 1:
The system applies local quality by evaluating the impact of sensor failure on each running condition individually. Instead of uniformly disabling all functions or maintaining all functions, the system determines the specific quality (availability) of each running condition based on its dependence on the failed sensor. Running conditions that do not require the failed sensor maintain their full quality and continue to operate, while those that do require it are disabled or degraded.
Solution Approach 2:
The system dynamically evaluates the relationship between sensor status and running condition requirements. When a sensor fails, the system dynamically determines which running conditions can continue to operate safely based on their dependence on the failed sensor. This dynamic assessment allows the system to maintain availability where safe while compromising it only where necessary for safety.
4Productivity
If the system disables specific functions or switches to alternative sensors, then functionality is maintained with refined control, but system complexity increases
Solution Approach 1:
The system performs preliminary action by pre-establishing the dependence relationships between sensors and running conditions. Before sensor failure occurs, the system has already determined which running conditions depend on which sensors. When a sensor fails, this pre-established knowledge allows for rapid and systematic determination of which functions to disable, reducing the complexity of real-time decision-making.
Data Source
AI summary
A vehicle control method includes obtaining sensor status information and autonomous driving function information, where the sensor status information includes information indicating that one or more sensors are in a failed state. The autonomous driving function information indicates a currently running autonomous driving function. The autonomous driving function includes a plurality of running conditions, and implementation of each running condition is related to one or more sub-functions. A driving policy is implemented based on the impact of a failure of the one or more sensors on the running condition and the currently running autonomous driving function.