Autonomous Vehicle Pose Switching for Sensor Failure Tolerance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in maintaining reliable pose data due to potential failures in pose measurement systems, leading to unreliable operation, as these systems can experience sensor failure, hardware failure, software bugs, communication failure, or loss of power, resulting in 'bad' quality pose data.
Innovation Solution
The implementation of a system that receives pose data from two independent pose measurement systems, determines the quality of each data set using methods like Kalman filters, and switches to the better quality data set, allowing the vehicle computer system to control the autonomous vehicle based on the determined pose data quality, ensuring safe and efficient operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single pose measurement system is used, then the device complexity is low, but the reliability of pose data deteriorates due to potential sensor failure, hardware failure, software bugs, or communication failure
Solution Approach 1:
The pose measurement system is segmented into multiple independent subsystems (first pose measurement system and second pose measurement system), each capable of independently providing pose data. This segmentation allows the system to isolate failures to individual segments while maintaining overall functionality through the other segments.
Solution Approach 2:
The system implements beforehand cushioning by having redundant pose measurement systems in place before failures occur. When one system fails or provides bad quality data, the other system is already available to take over, cushioning against the impact of the failure on overall system reliability.
2Reliability
If redundant pose measurement systems are implemented, then the reliability of pose data improves, but the device complexity increases due to multiple sensors and data processing requirements
Solution Approach 1:
The system implements feedback by continuously monitoring the quality of pose data from each measurement system and using this feedback to dynamically select the best data source. The quality determination module provides feedback about data quality, which feeds into the selection process, creating a closed-loop system that adapts to changing conditions.
Solution Approach 2:
The system employs dynamics by making the pose data selection adaptive and time-varying rather than static. The vehicle computer system dynamically switches between different pose measurement systems based on real-time quality assessments, allowing the system to adapt to changing operational conditions and failure modes.
3Reliability
If pose data quality is not monitored, then the ease of operation is high, but the reliability deteriorates when bad quality data is used for vehicle control
Solution Approach 1:
The pose measurement systems and vehicle computer system perform self-service by automatically monitoring their own data quality and making autonomous decisions about which data to use. The system self-diagnoses data quality issues and self-corrects by switching to alternative data sources without requiring external intervention.
Solution Approach 2:
The system takes preliminary action by assessing the quality of pose data before using it for vehicle control decisions. The quality determination occurs in advance of the control action, ensuring that only verified high-quality data influences vehicle operation, thereby preventing unreliable data from compromising safety.
Data Source
AI summary
Example systems and methods are disclosed for determining vehicle pose data for an autonomous vehicle. The vehicle computer system may receive pose data from multiple pose measurement systems of the autonomous vehicle. Each pose measurement system may include one or more corresponding sensors of the autonomous vehicle. The vehicle computer system may determine a pose data quality for the received pose data for each pose measurement system. The vehicle computer system may set the vehicle pose data to the pose data of the pose measurement system with the highest pose data quality. The vehicle computer system may control the autonomous vehicle based on the vehicle pose data.