Vehicle Trajectory Tree Using Learned Paths for Faster Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional rule-based approaches for vehicle navigation are computationally expensive and scale poorly to new geographies, driving scenarios, and environments, often resulting in inefficient and costly computations due to the generation of large numbers of heuristic-based trajectories that are unaware of environmental objects.
Innovation Solution
Implementing a machine-learning system that generates a diverse set of machine-learned trajectories, reducing the need for heuristic-based trajectories by using multiple ML models with different output heads to create a tree structure for determining optimal vehicle control trajectories, thereby minimizing computational expense.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If rule-based approaches are used for vehicle navigation, then trajectories can be determined using hand-engineered driving rules, but computational expense increases and scaling to new environments becomes difficult
Solution Approach 1:
The patent replaces rule-based mechanical decision-making systems with machine learning models that learn driving behaviors from data. The ML models process sensor inputs and generate trajectories without relying on hand-engineered rules, thereby reducing computational expense while improving adaptability to new environments.
Solution Approach 2:
The patent changes the fundamental parameter of trajectory generation from rule-based logic to learned patterns. By training ML models on diverse driving scenarios, the system adapts to new environments through parameter updates rather than manual rule engineering, reducing both computational expense and improving ease of adaptation.
2Productivity
If multiple machine-learning models with different output heads are used to generate diverse trajectories, then the proportion of learned trajectories increases, but the system complexity increases
Solution Approach 1:
The patent segments the trajectory generation task into multiple specialized ML models, each with specific output heads for different trajectory types. This segmentation allows parallel processing of diverse trajectory options, improving decision-making speed while managing complexity through modular architecture.
Solution Approach 2:
The patent creates a universal ML framework where multiple models share common architecture and training procedures despite having different output heads. This multi-functionality approach allows the system to handle diverse trajectory generation tasks efficiently, improving productivity while keeping system complexity manageable through standardized components.
Data Source
AI summary
Techniques for generating a tree structure based on multiple machine-learned trajectories are described herein. A planning component (“ML system”) within a vehicle may receive and encode various types of sensor and/or vehicle data. The ML system can provide the encoded data as input to multiple machine-learning models (“ML models”), each of which may be trained to output a unique candidate trajectory for the vehicle follow. In some examples, each ML model may be trained to output a unique type of learned trajectory that causes the vehicle to perform a certain type of action. Using the learned candidate trajectories, the ML system may generate a tree structure that includes some or all of the candidate trajectories. The vehicle may determine a control trajectory based on the generation and traversal of the tree structure using a tree search algorithm, and may follow the control trajectory within the environment.