ML Vehicle Trajectory Guidance Without HD Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional approaches for autonomous vehicles to perform maneuvers like lane changes, lane splits, and turns rely heavily on high-definition (HD) maps, which are not universally available, require significant computational resources, and can lead to unsafe operations in unmapped areas.
Innovation Solution
The use of machine learning models that compute vehicle control data based on sensor data, control inputs, low-resolution map data, and vehicle status data, allowing autonomous vehicles to perform maneuvers without relying on HD maps, thereby enhancing their ability to operate in any location.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional approaches use HD maps for autonomous vehicle maneuvers, then maneuver guidance is provided, but the system requires significant computational resources and cannot operate in unmapped areas
Solution Approach 1:
The patent extracts the essential guidance information from HD maps and implements a simplified map representation that retains only critical maneuver data. This allows the system to operate with reduced computational requirements while maintaining maneuver guidance capability in both mapped and unmapped areas.
Solution Approach 2:
The system changes the parameter of map resolution from high-definition to reduced-detail representation. By adjusting the level of map detail according to operational needs, the system achieves versatility across different locations while reducing computational burden for maneuver guidance.
2Measurement precision
If HD maps are used for vehicle maneuvers, then accurate navigation is achieved, but computational expense and energy consumption increase significantly
Solution Approach 1:
The patent applies parameter changes by adjusting map resolution levels dynamically. Full HD maps are used only when high navigation accuracy is critical, while reduced-detail maps are used for routine maneuvers, thereby reducing overall computational energy consumption while maintaining necessary navigation precision.
Solution Approach 2:
The system applies partial action by using detailed map data only for specific critical maneuvers rather than continuously processing full HD maps for all operations. This selective approach reduces computational energy consumption while maintaining navigation accuracy when needed.
3Adaptability or versatility
If HD maps are generated and maintained for autonomous operation, then comprehensive location support is provided, but processing power and bandwidth requirements increase
Solution Approach 1:
The system changes the parameter of map data detail level based on operational context. By using reduced-detail representations for general navigation and reserving full HD map processing for specific scenarios, the system achieves broad location coverage without requiring excessive processing power for map generation and maintenance.
Solution Approach 2:
The patent segments map data into different levels of detail, allowing the system to process and store only the necessary information for each operational context. This segmentation reduces overall processing power requirements while maintaining versatility across diverse locations.
Data Source
AI summary
In various examples, a trigger signal may be received that is indicative of a vehicle maneuver to be performed by a vehicle. A recommended vehicle trajectory for the vehicle maneuver may be determined in response to the trigger signal being received. To determine the recommended vehicle trajectory, sensor data may be received that represents a field of view of at least one sensor of the vehicle. A value of a control input and the sensor data may then be applied to a machine learning model(s) and the machine learning model(s) may compute output data that includes vehicle control data that represents the recommended vehicle trajectory for the vehicle through at least a portion of the vehicle maneuver. The vehicle control data may then be sent to a control component of the vehicle to cause the vehicle to be controlled according to the vehicle control data.