Top-Down Motion Prediction for Complex Traffic Interactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current prediction techniques for determining future states of entities in an environment, such as autonomous vehicles, often rely on physics-based modeling or rules-of-the-road simulations, which may not accurately account for complex interactions between objects and dynamic environments.
Innovation Solution
A machine learning-based system that processes multi-channel images from sensors to generate trajectory templates and predicted trajectories, incorporating top-down representations of environments and object interactions, using convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to output heat maps and probability distributions for future object movements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physics-based modeling or rules-of-the-road simulations are used for prediction, then the system can determine future states of entities, but the accuracy is insufficient to account for complex interactions between objects and dynamic environments
Solution Approach 1:
The patent replaces physics-based modeling and rules-of-the-road simulations with a machine learning model that processes multi-channel images. The ML model learns patterns from training data containing images and ground truth trajectories, substituting mechanical prediction methods with data-driven approaches that better capture complex object interactions and environmental dynamics.
2Measurement precision
If machine learning models process multi-channel images to predict trajectories, then prediction accuracy improves, but computational complexity and processing requirements increase
Solution Approach 1:
The patent segments the prediction task into distinct processing stages: the ML model first processes multi-channel images to generate heat maps representing probability distributions, then extracts predicted trajectories from these heat maps. This segmentation allows the system to handle computational complexity in manageable steps while maintaining high prediction accuracy through specialized processing for each stage.
Data Source
AI summary
Techniques for determining predictions on a top-down representation of an environment based on object movement are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) may capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle, a pedestrian, a bicycle). A multi-channel image representing a top-down view of the object(s) and the environment may be generated based in part on the sensor data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) may also be encoded in the image. Multiple images may be generated representing the environment over time and input into a prediction system configured to output a trajectory template (e.g., general intent for future movement) and a predicted trajectory (e.g., more accurate predicted movement) associated with each object. The prediction system may include a machine learned model configured to output the trajectory template(s) and the predicted trajector(ies).