Vehicle Path Prediction Using Future-Frame Travel Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current path prediction systems in intelligent driving monitoring systems (IDMS) and autonomous driving systems face challenges in accurately predicting paths of travel, especially in complex and dynamic real-world scenarios with unclear or occluded lane markings, and require large amounts of labeled training data, which is cumbersome and expensive to obtain.
Innovation Solution
The system employs a 'Back-to-the-Future' approach that incorporates information from later time points to determine and map the path of travel, using a combination of camera, GPS, Lidar, and radar data, allowing for faster and higher-resolution processing, and reduces the need for human-labeled data by using future data as machine-labeled inputs for training.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional path prediction systems use current time data only, then processing is simpler and faster, but prediction accuracy deteriorates in complex and dynamic real-world scenarios
Solution Approach 1:
The system performs preliminary actions by incorporating future time point data into the path prediction process. Instead of only using current time data, the system proactively integrates information from future time points (t1, t2, t3) to improve prediction accuracy before the actual prediction is needed, resolving the contradiction between accuracy and complexity.
Solution Approach 2:
The patent applies inversion by mapping the determined path of travel back to a reference frame based on camera position at an earlier time point. This reverse mapping approach (from future to past reference frames) enables accurate path prediction while managing processing complexity through clever coordinate transformation.
2Measurement precision
If large amounts of labeled training data are used, then model accuracy improves, but data collection time and cost increase
Solution Approach 1:
The system employs self-service by using its own future time point data as machine-labeled training inputs. The path prediction system generates its own training data by processing future time points and using these predictions as labeled examples, eliminating the need for external human-labeled datasets and significantly reducing data collection time and cost.
Solution Approach 2:
The patent changes the parameter of training data labeling from manual human annotation to automated machine labeling using future time point predictions. This parameter change transforms the training process, allowing the system to generate unlimited labeled data automatically, thereby improving model accuracy without increasing data collection time.
3Measurement precision
If high-resolution processing is applied to image or video frames, then object detection accuracy improves, but processing speed decreases
Solution Approach 1:
The system performs preliminary processing by incorporating future time point data that has already been captured and processed. This allows the system to work with pre-captured high-resolution frames from future time points without requiring real-time high-resolution processing, thereby maintaining both accuracy and speed.
Data Source
AI summary
The present disclosure provides systems and methods for mapping a determined path of travel. The path of travel may be mapped to a camera view of a camera affixed to a vehicle. In some embodiments, the path of travel may be mapped to another view that is based on a camera, such as a bird's eye view anchored to the camera's position at a given time. These systems and methods may determine the path of travel by incorporating data from later points in time.