Road Feature Occlusion Representation for Autonomous Route Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle systems face challenges in making effective driving decisions due to unobserved or unperceived vehicles and obstacles that are not accounted for in their environment.
Innovation Solution
The implementation of an architecture that provides computationally efficient occlusion representations over road features, allowing the perception module to offer occlusion information to the planning module, which can then make informed decisions for safe route planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If full occlusion mapping data is used, then measurement precision of occlusion information is improved, but device complexity and computational load increase
Solution Approach 1:
The patent segments the environment into discrete road features (lanes, intersections, crosswalks, etc.) and generates occlusion representations specifically for these features rather than creating complete occlusion maps of the entire environment. This segmentation approach maintains measurement precision for critical driving decision areas while significantly reducing system complexity and computational requirements.
Solution Approach 2:
The patent applies local quality by providing detailed occlusion information specifically for relevant road features that impact driving decisions, rather than uniformly mapping the entire environment. The occlusion representations are generated selectively for features within the vehicle's path and surrounding areas, concentrating computational resources where they are most needed for safe navigation.
2Loss of information
If complete environment mapping is performed, then loss of information about unobserved objects is reduced, but processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary action by pre-defining the set of relevant road features that impact driving decisions before generating occlusion representations. By establishing this predefined framework in advance, the system can efficiently generate occlusion information only for these specific features, reducing processing time while maintaining comprehensive information about unobserved objects in critical areas.
Solution Approach 2:
The patent extracts and focuses on only the essential occlusion information related to driving decisions by taking out specific road features from the complete environment. This extraction approach retrieves necessary information about unobserved objects in relevant areas without processing the entire environment, thereby reducing computational resources and processing time.
3Reliability
If detailed occlusion maps are generated, then reliability of driving decisions is improved, but productivity and processing efficiency decrease
Solution Approach 1:
The patent segments the occlusion mapping task into discrete road features (lanes, intersections, crosswalks, drivable areas) rather than generating continuous detailed occlusion maps. This segmentation maintains reliability for driving decisions by covering all critical features while improving productivity by reducing the overall computational scope and processing requirements.
Solution Approach 2:
The patent applies partial action by generating occlusion representations for only the necessary road features that impact driving decisions, rather than creating exhaustive detailed maps of the entire environment. This partial mapping approach maintains sufficient reliability for safe navigation while significantly improving processing efficiency by avoiding unnecessary computations for irrelevant areas.
Data Source
AI summary
Among other things, techniques are described for implementing occlusion representations over road features. In general, one innovative aspect of the subject matter described in this specification can be embodied in methods that include: obtaining area information of at least one area of interest for a vehicle, identifying occlusion data associated with the at least one area of interest, determining occlusion information associated with the at least one area of interest based on the area information and the occlusion data, providing the occlusion information for planning a route for the vehicle, and operating the vehicle in accordance with the planned route. The occlusion data includes data associated with the occlusion information, and the occlusion information has a smaller data size than the occlusion data.