Asynchronous Trajectory Planning and Tracking for Low-Latency Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle navigation systems face latency and system delay due to solving a single optimization problem for both trajectory planning and tracking, which can lead to reliability issues.
Innovation Solution
Implementing asynchronous trajectory planning and tracking modules that operate at different frequencies and are event-driven, with the trajectory planning module adjusting its frequency based on the state estimate from the tracking module, allowing for independent optimization problems to be solved and an updated trajectory to be generated and tracked.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single optimization problem is solved for both trajectory planning and tracking, then the system structure is simplified, but latency and system delay increase
Solution Approach 1:
The patent divides the navigation system into separate trajectory planning and trajectory tracking modules that operate independently. The planning module generates desired trajectories while the tracking module computes actuation signals, allowing each module to optimize its own performance without being constrained by a monolithic optimization problem, thereby reducing overall system latency.
Solution Approach 2:
The patent implements dynamic frequency adjustment where the trajectory planning module can run at a lower frequency than the tracking module. This dynamic operation allows the system to adapt computational resources efficiently - the tracking module operates at high frequency for responsive control, while the planning module updates trajectories at appropriate intervals, reducing unnecessary computational overhead and latency.
2Ease of operation
If trajectory planning and tracking run at the same frequency, then synchronization is simplified, but the system cannot adapt to varying tracking abilities
Solution Approach 1:
The patent enables the trajectory planning module to dynamically adjust its operating frequency based on feedback from the tracking module about its tracking ability. When tracking performance is good, planning can run at lower frequencies; when tracking struggles, planning frequency increases to provide more frequent trajectory updates, allowing the system to adapt to varying conditions while maintaining synchronization through event-driven communication.
Solution Approach 2:
The tracking module provides feedback about its tracking ability and state estimates to the planning module. This feedback mechanism allows the planning module to adjust its behavior and frequency based on actual tracking performance, creating an adaptive system that responds to real-time conditions rather than operating at a fixed frequency.
3Ease of operation
If the trajectory planning module runs at a fixed frequency, then system operation is simplified, but it cannot respond adaptively to tracking module needs
Solution Approach 1:
The trajectory planning module transitions from fixed-frequency operation to dynamic frequency adjustment based on tracking module feedback. The module can increase its operating frequency when the tracking module indicates it needs more frequent trajectory updates, and decrease frequency when tracking is proceeding smoothly, optimizing system responsiveness without excessive computational burden.
Data Source
AI summary
A vehicle, and a system a method of navigating a vehicle. The system includes a trajectory planning module and a trajectory tracking module. The trajectory planning module operates at a processor of the vehicle to generate a trajectory for the vehicle. The trajectory tracking module operates at the processor to track the trajectory to navigate the vehicle. The trajectory planning module and the trajectory tracking module run asynchronously from each other.