Pose-Lane Association for AV Route Planning Across Coverage Gaps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining accurate and efficient routes when transitioning between fully-autonomous and partially-autonomous modes, particularly due to insufficient map-based localization and invalid position data, leading to processing delays and incomplete route plans.
Innovation Solution
A vehicle computing system that receives map data with both AV lanes and coverage lanes, determines candidate lanes based on pose estimates, and generates route plans by selecting starting lanes with the highest scores, ensuring efficient navigation across both autonomous and non-autonomous modes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the autonomous vehicle uses map-based localization to determine vehicle pose, then navigation accuracy is improved, but processing delays occur due to insufficient map data and invalid position data
Solution Approach 1:
The system segments the map data into different types (AV lanes and coverage lanes) and processes them through different pathways. AV lane data is processed with high precision requirements while coverage lane data is processed with lower requirements, allowing parallel processing that reduces overall delay while maintaining navigation accuracy where needed
Solution Approach 2:
The system applies partial processing to coverage lane data where full precision is not required. By determining vehicle pose relative to coverage lanes with relaxed precision requirements compared to AV lanes, the system reduces processing complexity and time for portions of the navigation task where high precision is less critical
2Measurement precision
If the vehicle computing system processes both AV lanes and coverage lanes with high precision requirements, then navigation accuracy is improved, but device complexity and processing time increase
Solution Approach 1:
The system applies different quality levels of processing to different spatial regions. AV lanes receive high-precision processing with strict validation, while coverage lanes receive standard processing. This local differentiation maintains navigation accuracy in critical autonomous zones while reducing overall system complexity
Solution Approach 2:
The processing system is segmented into different validation pathways. AV lane processing includes comprehensive validation checks while coverage lane processing uses simplified validation, reducing overall device complexity while maintaining accuracy where required
3Reliability
If the system validates all position data with strict criteria, then reliability is improved, but processing speed decreases due to extensive validation requirements
Solution Approach 1:
The system applies full validation only to AV lane position data where reliability is critical, while applying partial validation to coverage lane data. This selective validation approach maintains data reliability for autonomous operations while improving overall processing speed
Solution Approach 2:
Different validation strictness levels are applied to different data sources. AV lane position data undergoes rigorous validation to ensure reliability, while coverage lane data undergoes standard validation, balancing reliability requirements with processing efficiency
Data Source
AI summary
An autonomous vehicle (AV) includes a vehicle computing system configured to receive map data of a geographic location, obtain position estimate data of the autonomous vehicle and determine a route of the autonomous vehicle including a plurality of roadways in the plurality of submaps. The autonomous vehicle determines a route including a plurality of roadways, determines a first roadway in the plurality of roadways closest to the position estimate and a second roadway outside the plurality of roadways closest to the position estimate of the autonomous vehicle, and determines a pose relative to the first roadway or the second roadway based on a distance between the position estimate of the autonomous vehicle and a roadway associated with a prior pose of the autonomous vehicle to control travel of the autonomous vehicle based on the vehicle pose.