Vehicular Trajectory Tracking via Local Coordinate Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle driver assistance systems face challenges in accurately determining the trajectory of other vehicles, especially in situations with limited information, and require methods to navigate effectively, as they often rely on lane markings, GPS, and high-definition maps, which may not be available in all conditions.
Innovation Solution
A vehicle driver assistance system utilizing one or more cameras and sensors to capture and process image data, translating the motion and location of target vehicles into a local coordinate system of the equipped vehicle, allowing for continuous trajectory recording and noise correction, enabling autonomous navigation without relying on lane markings or GPS, using a Kalman filter for prediction and optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system uses lane markings, GPS, and high-definition maps for navigation, then navigation accuracy is improved, but the system becomes unreliable in conditions where these are unavailable (covered lane markings, tight spaces)
Solution Approach 1:
The system changes the reference frame parameter from global coordinates (GPS, maps) to local vehicle-relative coordinates. By translating target vehicle positions into the equipped vehicle's local coordinate system and continuously updating based on equipped vehicle motion, the system adapts to conditions where global reference systems are unavailable or unreliable.
2Measurement precision
If the system records and processes trajectory data continuously, then trajectory tracking accuracy is improved, but computational complexity and data processing requirements increase
Solution Approach 1:
The system dynamically updates the local coordinate system transformation parameters based on the equipped vehicle's continuous motion. Rather than static coordinate transformations, the system recalculates target vehicle positions relative to the moving equipped vehicle's current location and orientation, maintaining accuracy without requiring complex absolute positioning systems.
Solution Approach 2:
The system uses feedback from the equipped vehicle's own motion sensors (yaw rate, vehicle speed) to continuously correct and update the translated trajectory data. This feedback loop allows the system to compensate for equipped vehicle movement and maintain accurate relative positioning without requiring equally accurate global positioning throughout the trajectory.
3Measurement precision
If the system uses multiple sensing technologies for trajectory determination, then measurement accuracy is improved, but system complexity increases
Solution Approach 1:
The system merges data from multiple disparate sensing technologies (cameras for target vehicle detection, yaw rate sensors, vehicle speed sensors) into a unified local coordinate system framework. By combining these sensors and processing their data through the same transformation methodology, the system achieves accurate trajectory tracking without requiring each sensor to independently provide complete positioning information.
Data Source
AI summary
A vehicular control system includes a forward viewing camera and a non-vision sensor. The control, responsive to processing of captured non-vision sensor data and processing of frames of captured image data, at least in part controls the equipped vehicle to travel along a road. The control, responsive at least in part to processing of frames of captured image data, determines lane markers on the road and determines presence of another vehicle traveling along the traffic lane ahead of the equipped vehicle and determines a trajectory of the other vehicle relative to the equipped vehicle. The control stores a trajectory history of the determined trajectory of the other vehicle relative to the equipped vehicle as the other vehicle and the equipped vehicle travel along the traffic lane.