AV Software Stack Configuration Across Vehicle Platforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle (AV) software stacks are specific to individual vehicle platforms and sensor configurations, requiring updates for any changes, limiting their adaptability and efficiency in managing diverse vehicle types and sensor arrangements.
Innovation Solution
A remote management system that enables the use of a generic software stack for various vehicle platforms and sensor configurations, allowing for dynamic configuration and updates, enabling different configurations based on vehicle types and sensor arrangements while maintaining compatibility across identical software stacks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional autonomous vehicle software stacks are specific to individual vehicle platforms and sensor configurations, then the software can be precisely tailored to each vehicle type, but the complexity of managing and updating software across diverse vehicle types increases significantly
Solution Approach 1:
The patent implements a universal software stack that can operate across multiple vehicle platforms and sensor configurations. The configuration manager enables a single software stack to be adapted to different vehicle types (e.g., vehicles with different sensor arrangements, platforms like Chevrolet Bolt, Cadillac CT6) through dynamic configuration files rather than requiring separate software stacks for each platform.
Solution Approach 2:
The patent segments the software architecture into a core universal software stack and separate configuration files. The configuration manager divides configuration data into platform-specific parameters, sensor-specific parameters, and component-specific parameters, allowing each segment to be independently managed and updated without affecting the entire software system.
2Manufacturing precision
If separate software stacks are created for each vehicle platform, then each software stack can be optimized for its specific platform, but the time and resources required to update and maintain multiple software stacks increase
Solution Approach 1:
A single universal software stack serves multiple vehicle platforms simultaneously. The configuration manager enables this software stack to be dynamically configured for different platforms (Chevrolet Bolt, Cadillac CT6, various sensor configurations) without requiring separate software stacks, thereby reducing update time and resource requirements.
Solution Approach 2:
The system optimizes software for specific platforms by changing configuration parameters rather than creating separate software stacks. The configuration manager modifies software behavior through parameter adjustments in configuration files, allowing rapid adaptation to different vehicle platforms without time-consuming software development and deployment cycles.
3Adaptability or versatility
If a generic software stack is used for various vehicle platforms, then adaptability to different vehicle types improves, but the precision and reliability of software for specific vehicle configurations may decrease
Solution Approach 1:
The configuration manager implements local quality by providing platform-specific and sensor-specific configuration parameters within the generic software stack. Each vehicle platform receives tailored configuration settings (e.g., sensor locations, processing parameters, platform-specific optimizations) that ensure reliable operation while maintaining the benefits of a universal software architecture.
Solution Approach 2:
The system maintains reliability for specific configurations by dynamically changing software parameters based on the detected vehicle platform and sensor configuration. The configuration manager adjusts operational parameters, sensor calibration values, and processing thresholds to match specific vehicle configurations, ensuring reliable performance across diverse platforms using a single software stack.
Data Source
AI summary
The subject disclosure relates to techniques for managing the configuration of vehicles. A process of the disclosed technology can include steps of receiving a first vehicle identifier for a first vehicle, wherein the first vehicle is associated with a first vehicle platform, identifying a first configuration for the first vehicle platform based on the first vehicle identifier, receiving a second vehicle identifier for a second vehicle, wherein the second vehicle is associated with a second vehicle platform, and wherein the first vehicle platform is different from the second vehicle platform, and identifying a second configuration for the second vehicle platform based on the second vehicle identifier, wherein the first vehicle and the second vehicle run on an identical software stack. Systems and machine-readable media are also provided.