Autonomous Vehicle Obstacle Trail Analysis for Lane Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining lane configuration and predicting obstacle movement, especially in rural areas where lane markings are unclear, requiring innovative methods to navigate safely and efficiently.
Innovation Solution
The system maintains and analyzes the moving history of obstacles and the vehicle using sensor data to reconstruct trajectories, predict future movements, and infer lane configurations without relying on map data, utilizing a networked system with sensors like cameras, LIDAR, and radar to determine vehicle and obstacle states and plan optimal routes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles rely on traditional lane markings and map data for navigation, then navigation accuracy is maintained in well-marked areas, but navigation reliability deteriorates in rural areas with unclear or absent lane markings
Solution Approach 1:
The patent uses obstacle movement trails as an intermediary to infer lane configuration. Instead of directly observing lane markings (which are absent or unclear), the system tracks the movement patterns of obstacles (vehicles, pedestrians) and uses their trajectories as indirect evidence to reconstruct the underlying lane structure. This intermediary approach allows the system to navigate reliably in areas without clear visual lane markings.
Solution Approach 2:
The patent replaces the traditional visual-mechanical system of lane marking detection with a computational system based on obstacle trajectory analysis. Instead of relying on optical detection of painted lines on the road, the system uses sensor data to track obstacle positions over time and computationally reconstruct lane configurations from movement patterns, substituting physical lane markings with data-driven inference.
2Measurement precision
If the system tracks and stores movement history of all obstacles to reconstruct trajectories, then prediction accuracy improves, but computational complexity and data storage requirements increase
Solution Approach 1:
The patent extracts only the essential movement history data needed for trajectory reconstruction and prediction, rather than processing all available sensor data. By focusing specifically on obstacle position, velocity, and trajectory information, the system achieves accurate predictions while reducing computational complexity by filtering out irrelevant data.
Solution Approach 2:
The system performs preliminary tracking and storage of obstacle movement trails in advance, organizing the data in a structured format that facilitates efficient trajectory reconstruction. By pre-processing and organizing the movement history data as obstacles are detected, the system reduces the computational burden during real-time prediction phases.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables autonomous vehicles to accurately determine lane configurations and predict obstacle movements, enhancing safety and efficiency in navigating unclear environments by reconstructing trajectories and planning paths to avoid collisions, even in areas with insufficient or absent lane markings.
Implementation Method 1
utilizing a networked system with sensors like cameras, LIDAR, and radar to determine vehicle and obstacle states
Implementation Method 2
utilizing a networked system with sensors like cameras, LIDAR, and radar to determine vehicle and obstacle states
Data Source
AI summary
During the autonomous driving, the movement trails or moving history of obstacles, as well as, an autonomous driving vehicle (ADV) may be maintained in a corresponding buffer. For the obstacles and the ADV, the vehicle states at different points in time are maintained and stored in one or more buffers. The vehicle states representing the moving trails or moving history of the obstacles and the ADV may be utilized to reconstruct a history trajectory of the obstacles and the ADV, which may be used for a variety of purposes. For example, the moving trails or history of obstacles may be utilized to determine lane configuration of one or more lanes of a road, particularly, in a rural area where the lane markings are unclear. The moving history of the obstacles may also be utilized predict the future movement of the obstacles, tailgate an obstacle, and infer a lane line.