Directed Graph Vehicle Control for Complex Traffic Interactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle planning systems struggle to accurately determine navigation commands in complex driving environments due to increased computational costs and simplistic modeling of vehicle interactions, leading to potential gridlock and inefficient resource usage.
Innovation Solution
Utilizing directed graphs to model and predict vehicle interactions by identifying relevant entities and their behaviors, allowing for more efficient computation and smoother navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the vehicle considers more objects in complex driving environments, then navigation accuracy improves, but computational cost increases
Solution Approach 1:
The patent segments the set of all detected objects into two categories: connected entities (those with direct interaction relationships modeled by the directed graph) and non-connected entities. This segmentation allows the system to focus computational resources on predicting behaviors of only the connected entities, thereby maintaining navigation accuracy while reducing computational cost.
Solution Approach 2:
The patent extracts and models only the relevant interaction relationships between vehicles using a directed graph structure. By taking out and explicitly modeling only the connected entities that directly impact the host vehicle's navigation, the system eliminates unnecessary computational overhead from analyzing all detected objects, thus resolving the contradiction between accuracy and computational cost.
2Measurement precision
If the vehicle considers more objects in complex driving environments, then navigation accuracy improves, but decision making time increases
Solution Approach 1:
The patent segments objects into connected and non-connected entities based on interaction relationships. By making this segmentation, the system reduces the number of objects requiring detailed behavior prediction, thereby reducing decision making time while maintaining navigation accuracy through focused analysis of connected entities.
Solution Approach 2:
The patent performs preliminary action by pre-establishing the directed graph structure that encodes interaction relationships between vehicles before the decision-making process. This pre-modeling of relationships allows the system to quickly query and utilize interaction information during real-time decision making, reducing overall decision making time while preserving navigation accuracy.
3Productivity
If simplified modeling of vehicle interactions is used, then computational load decreases, but navigation accuracy deteriorates
Solution Approach 1:
The patent changes the parameter representation by using a directed graph structure to model interaction relationships. This parameter change allows the system to efficiently represent complex vehicle interactions with a manageable number of parameters (edges in the graph), achieving both computational efficiency and navigation accuracy by capturing essential interaction dynamics without excessive complexity.
4Productivity
If directed graphs are used to model vehicle interactions, then computational load decreases, but model complexity increases
Solution Approach 1:
The patent uses a directed graph as a simplified copy or abstraction of the complex real-world vehicle interaction system. This graphical model copies only the essential interaction relationships (edges) between vehicles (nodes), providing computational efficiency while managing model complexity by representing complex dynamics in a structured, manageable format.
Data Source
AI summary
Controlling autonomous vehicles requires accurate information about how entities behave in an environment with respect to one another. In an example, a data structure is used to associate entities in an environment of the vehicle with the vehicle and/or with each other. For example, associations between entities can be based on locations of the entities relative to each other and/or relative to segments of a drivable surface. Information about associations between the vehicle and/or entities in the environment may be used to identify entities that may influence travel of the vehicle and/or other entities and, in some implementations, vehicle controls can be generated based on these relevant entities.