Autonomous Vehicle Path Planning Graph Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in quickly determining suitable paths while avoiding obstacles, particularly in scenarios like unprotected left turns, merging into oncoming traffic, and maneuvering around double-parked cars, due to difficulties in predicting and integrating object paths within a planning horizon.
Innovation Solution
A path planning system that receives sensor data to define a region of interest and constructs a graph with nodes representing vehicle states, including position, velocity, acceleration, and proximity to objects, using a cost function to determine a path that minimizes total cost, such as occupant comfort, energy usage, and distance to obstacles, and automatically implements this path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the autonomous vehicle uses traditional path planning methods to determine a suitable path while avoiding obstacles, then the vehicle can navigate through the environment, but the system fails to quickly determine paths in complex scenarios such as unprotected left turns, merging into oncoming traffic, and maneuvering around double-parked cars
Solution Approach 1:
The patent segments the path planning problem into discrete graph nodes representing specific vehicle states (position, velocity, acceleration) and uses a cost function to evaluate each node. This segmentation allows the system to efficiently process complex scenarios by breaking them down into manageable state transitions rather than treating the entire planning horizon as a single continuous problem.
Solution Approach 2:
The system performs preliminary action by pre-defining the graph structure with all possible vehicle states and transitions before executing the path search. The cost function is pre-configured with weights for different factors (occupant comfort, energy usage, safety), enabling rapid path determination without recalculating fundamental planning parameters during real-time execution.
2Productivity
If the autonomous vehicle optimizes path planning to minimize total cost considering occupant comfort and energy usage, then the system enhances passenger experience and efficiency, but the computational complexity of evaluating multiple cost factors increases processing time
Solution Approach 1:
The patent applies parameter changes by using a cost function with configurable weights that can adjust the relative importance of different factors (occupant comfort, energy usage, safety). This allows the system to optimize for different operational conditions by changing parameter values rather than restructuring the entire evaluation framework, reducing computational complexity while maintaining flexibility.
Solution Approach 2:
The system creates equipotentiality by normalizing different cost factors (occupant comfort, energy usage, safety) into a unified cost metric that can be directly compared across all graph nodes. This transformation allows the processor to evaluate multiple factors simultaneously using simple arithmetic operations rather than complex multi-criteria decision algorithms.
3Measurement precision
If the autonomous vehicle uses a graph-based path planning method with multiple nodes representing vehicle states, then the system can determine optimal paths that minimize total cost, but the memory requirements and processing load increase with the number of nodes and states
Solution Approach 1:
The patent segments the state space into discrete graph nodes with specific vehicle states (position, velocity, acceleration) at defined time intervals. This segmentation reduces memory requirements by representing continuous states as discrete nodes rather than storing all possible continuous state combinations, while maintaining sufficient precision for path optimization.
Solution Approach 2:
The system applies partial action by selectively evaluating only the necessary graph nodes and transitions relevant to the current driving scenario rather than processing the entire state space. The cost function prioritizes evaluation of nodes that are more likely to be part of the optimal path, reducing processing load while maintaining path optimization precision.
Data Source
AI summary
Systems and method are provided for controlling a vehicle. In various embodiments, a method of path planning for a vehicle includes receiving sensor data relating to an environment associated with the vehicle; defining a region of interest for the vehicle, based on the sensor data; defining a graph comprising a plurality of nodes, each of the plurality of nodes comprising a state of the vehicle and an associated cost, based on a cost function as applied to the state of the vehicle, at one of a plurality of points in time; and performing, via a processor, a search of the graph, based on the associated costs of each node of the graph, to determine a selected path for the vehicle through the region of interest that minimizes a total cost via the graph.