Autonomous Vehicle Control Architecture for Steering-Speed Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating complex environments, such as urban areas, due to the need for precise determination of steering and speed commands to ensure safe and efficient travel along predetermined trajectories while avoiding obstacles and adhering to traffic rules.
Innovation Solution
The system receives constraints on speed and position, determines steering and speed commands independently, and navigates the vehicle based on these commands using a control circuit, incorporating reference trajectories, lateral constraints, and speed profiles to adjust the path and speed accordingly, utilizing various control architectures and modules like path optimizers and combined movement models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If steering and speed commands are determined using a unified control architecture, then the control logic is simpler, but the independence and precision of individual command determination is reduced
Solution Approach 1:
The control architecture is segmented into independent modules: a path optimizer that determines steering commands based on lateral constraints and reference trajectories, and a movement model that determines speed commands based on speed constraints and path curvature. This segmentation allows each module to specialize in one type of command determination, improving precision while maintaining manageable complexity through modular design.
2Measurement precision
If the vehicle follows a predetermined reference trajectory strictly, then the navigation accuracy is improved, but the ability to adapt to dynamic obstacles and changing conditions is reduced
Solution Approach 1:
The path optimizer dynamically adjusts the steering commands by considering both the reference trajectory and lateral constraints that represent safe operating boundaries. The system continuously re-evaluates the optimal path within these constraints, allowing adaptation to dynamic conditions while maintaining navigation accuracy through continuous reference to the original trajectory goals.
Solution Approach 2:
The control system incorporates feedback loops where the determined steering and speed commands are executed, and the resulting vehicle state is continuously monitored. The path optimizer and movement model use this feedback to adjust subsequent commands, ensuring the vehicle adapts to changing conditions while maintaining accurate navigation toward the destination.
3Productivity
If the vehicle increases speed to improve travel efficiency, then the productivity is improved, but the safety margin and control precision are reduced
Solution Approach 1:
The movement model dynamically adjusts speed commands by changing the velocity parameter based on multiple factors including path curvature, lateral constraints, and safety requirements. The system optimizes speed within the speed constraints, allowing higher speeds on straight paths while reducing speed on curved paths or when approaching obstacles, thereby maintaining both efficiency and safety margins through continuous parameter optimization.
Data Source
AI summary
The subject matter described in this specification is generally directed control architectures for an autonomous vehicle. In one example, a reference trajectory, a set of lateral constraints, and a set of speed constraints are received using a control circuit. The control circuit determines a set of steering commands based at least in part on the reference trajectory and the set of lateral constraints and a set of speed commands based at least in part on the set of speed constraints. The vehicle is navigated, using the control circuit, according to the set of steering commands and the set of speed commands.