Autonomous Vehicle Trajectory Planning via Search Graph
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle systems face challenges in efficiently planning trajectories that account for various driving environments, such as urban and highway scenarios, and ensuring safe navigation through complex road conditions.
Innovation Solution
The system generates a search graph using vehicle and object data to determine an optimal trajectory path, incorporating a cost function that considers collision avoidance, lateral offsets, and dynamic constraints, which is then provided to the vehicle's controller for implementation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional trajectory planning methods are used, then the system can handle simple driving scenarios, but it cannot efficiently plan trajectories for complex driving environments such as urban and highway scenarios
Solution Approach 1:
The trajectory planning problem is segmented into discrete grid points that form a search graph. Each grid point represents a possible vehicle state (position, orientation), and edges represent feasible transitions. This segmentation allows the system to handle complex driving environments by breaking down the continuous planning space into manageable discrete states, while maintaining computational efficiency through graph-based search algorithms.
2Reliability
If a detailed search graph with fine grid resolution is generated, then collision avoidance and precise navigation are improved, but computational complexity and processing time increase
Solution Approach 1:
The search graph implementation uses local quality by adapting grid resolution based on local environmental requirements. In areas with obstacles or narrow passages, the grid resolution is increased to provide finer control and better collision avoidance. In open areas, the resolution is reduced to maintain computational efficiency. This allows the system to achieve high reliability where needed without incurring unnecessary computational complexity throughout the entire search space.
3Productivity
If the search graph uses a coordinate system with lateral offsets relative to reference trajectory, then trajectory optimization is improved, but the system complexity increases
Solution Approach 1:
The patent introduces a reference trajectory as an intermediary element that mediates between the vehicle's current state and the desired destination. The search graph is constructed in a coordinate system where grid points are defined by lateral offsets from this reference trajectory. This intermediary reference trajectory simplifies the optimization problem by providing a baseline path, allowing the planner to focus on finding optimal deviations from this reference rather than searching the entire configuration space from scratch.
Data Source
AI summary
Systems and methods are provided for controlling a vehicle. In one embodiment, a method includes receiving vehicle and object environment data. A search graph is generated based upon the received data. The search graph contains a grid of points for locating objects and is used to determine a desired trajectory for the vehicle.