Sparse Navigation Maps Using Trajectory Polynomials and Landmarks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating due to the sheer volume of data required for traditional mapping technologies, which can limit navigation efficiency and increase storage needs.
Innovation Solution
The use of a sparse map system that includes cameras for navigation, utilizing polynomial representations of target trajectories and condensed landmark signatures, allowing for efficient data storage and adaptive navigation based on real-time environmental data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional mapping technology is used for autonomous vehicle navigation, then navigation accuracy is improved, but data storage requirements and processing complexity increase significantly
Solution Approach 1:
The patent extracts only the essential navigation elements from complete traditional maps, creating sparse maps that contain only critical trajectory and landmark information. This selective extraction reduces data storage requirements while maintaining sufficient navigation accuracy for autonomous vehicle operation.
Solution Approach 2:
The patent applies different levels of detail to different parts of the navigation system. High-precision polynomial representations are used for target trajectories where accuracy is critical, while condensed landmark signatures provide sufficient detail for landmark identification. This localized quality approach optimizes the balance between navigation accuracy and data efficiency.
2Reliability
If traditional mapping technology is used for autonomous vehicle navigation, then comprehensive navigation information is provided, but system complexity and processing requirements increase
Solution Approach 1:
The patent extracts only the most critical navigation information elements needed for autonomous vehicle operation, eliminating redundant data. The sparse map contains only essential trajectory polynomials and landmark signatures, reducing system complexity while maintaining reliability for navigation decisions.
Solution Approach 2:
The patent transforms navigation data from traditional detailed map formats into polynomial representations for trajectories and condensed signatures for landmarks. This parameter transformation reduces data dimensionality and complexity while preserving the essential navigation information needed for reliable autonomous operation.
3Loss of information
If dense map data is stored for autonomous navigation, then complete environmental coverage is achieved, but data transmission and processing time increase
Solution Approach 1:
The patent transforms environmental information into compact polynomial parameters for trajectories and condensed signature representations for landmarks. This parameter transformation maintains comprehensive environmental coverage information while dramatically reducing data size, thereby decreasing transmission and processing time for autonomous navigation.
Solution Approach 2:
The patent creates simplified copy representations of the environment through sparse maps that capture essential navigation features. Instead of storing complete detailed environmental data, the system uses polynomial approximations and landmark signatures that serve as efficient copies for navigation purposes, reducing processing time while maintaining information coverage.
Data Source
AI summary
A non-transitory computer-readable medium is provided. The computer-readable medium includes a sparse map for autonomous vehicle navigation along a road segment. The sparse map includes a polynomial representation of a target trajectory for the autonomous vehicle along the road segment, and a plurality of predetermined landmarks associated with the road segment. The sparse map has a data density of no more than 1 megabyte per kilometer.