Nominal Vehicle Path Calculation Using Virtual Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for calculating nominal vehicle paths in autonomous vehicles are inefficient and prone to errors, requiring extensive human intervention and lacking real-time accuracy in lane marker detection and navigation map updates.
Innovation Solution
A method involving a computer system that serves digital frames of road segments to an annotation portal for manual lane marker labeling, calculates nominal vehicle paths, and uses a virtual simulator environment to test these paths for collisions, allowing for real-time adjustments and updates to navigation maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual lane marker labeling is used for calculating nominal vehicle paths, then accuracy of lane detection is improved, but human involvement and time consumption increase
Solution Approach 1:
The system performs preliminary automated detection of lane markers using image processing algorithms before presenting pre-processed data to human annotators. This preliminary action reduces the time required for manual labeling while maintaining high accuracy, as human annotators only need to verify and correct automated detections rather than label from scratch
Solution Approach 2:
The system creates virtual copies of road segments in a simulator environment to test nominal vehicle paths. These virtual copies allow for automated validation of path accuracy without requiring additional manual labeling, as the simulator can automatically detect collisions and validate paths against the labeled data
2Reliability
If extensive human intervention is used for path validation, then reliability of navigation is improved, but productivity and efficiency decrease
Solution Approach 1:
The system implements self-service through automated simulation testing that validates nominal vehicle paths without requiring continuous human intervention. The simulator automatically detects collisions between virtual vehicles and obstacles, and flags problematic road segments for review, allowing the system to self-validate the majority of path calculations while human annotators only handle flagged cases
Solution Approach 2:
The system establishes a feedback loop where simulation results automatically inform path validation. When the simulator detects collisions or invalid paths, this feedback triggers automated flagging and review processes, creating an efficient feedback mechanism that maintains high reliability while minimizing manual intervention requirements
3Productivity
If automated path calculation is used without simulation testing, then productivity is improved, but measurement precision and collision detection accuracy worsen
Solution Approach 1:
The system applies partial simulation testing by automatically validating only critical path segments or high-risk road segments through simulation, rather than testing every single path calculation. This partial action maintains high productivity while ensuring adequate collision detection accuracy for the most important cases
Solution Approach 2:
The system performs preliminary automated validation of nominal vehicle paths using simulation before deploying them to autonomous vehicles. This preliminary simulation testing ensures collision detection accuracy is maintained while the automated nature of the process preserves high productivity in the path calculation workflow
Data Source
AI summary
One variation of a method for calculating nominal paths for lanes within a geographic region includes: serving a digital frame of a road segment to an annotation portal; at the annotation portal, receiving insertion of a lane marker label, for a lane marker represented in the digital frame, over the digital frame; calculating a nominal path over the road segment and defining a virtual simulator environment for the road segment based on the lane marker label; during a simulation, traversing the virtual road vehicle along the nominal path within the virtual simulator environment and scanning the virtual simulator environment for collisions between the virtual road vehicle and virtual objects within the virtual simulator environment; and, in response to absence of a collision between the virtual road vehicle and virtual objects in the virtual simulator environment, updating a navigation map for the road segment with the nominal path.