Vehicle Trajectory Boundary Prediction for Road User Cut-In Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in predicting whether an object will enter into their trajectory, especially when map information is inaccurate or unreliable, such as in cases with faded or non-existent lane markings, or when the vehicle and object are not following the map due to road curvature or overlapping lane markings.
Innovation Solution
The method involves receiving sensor data to determine the object's location and trajectory boundary, calculating distances between the object's locations and the trajectory, and predicting the object's future entry into the trajectory based on these distances, without relying on pre-stored map information, using a simplified analysis that requires minimal processing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If map information is used to predict object trajectory entry, then prediction accuracy may be improved under ideal conditions, but reliability deteriorates when map information is inaccurate or unreliable
Solution Approach 1:
The patent introduces sensor data as an intermediary between the vehicle and map information. Instead of directly relying on potentially inaccurate map data, the system uses sensor observations of actual lane markings and road features as a mediator to verify and correct map information, thereby maintaining prediction reliability when maps are outdated or inaccurate
Solution Approach 2:
The system implements feedback by continuously comparing sensor-detected lane markings with map information. When discrepancies are detected (such as faded or missing lane markings), the system uses sensor data to correct its predictions, creating a closed-loop system that adapts to changing road conditions and maintains reliability
2Measurement precision
If complex analysis methods are used to predict object entry, then prediction accuracy may be improved, but processing resources and time consumption increase
Solution Approach 1:
The patent applies partial action by selectively analyzing only the most critical features for trajectory prediction. Instead of processing all available sensor data and map information equally, the system focuses on key elements such as lane marking positions, object relative velocity, and distance to trajectory, achieving sufficient accuracy with reduced computational effort
Solution Approach 2:
The system extracts only the essential features needed for trajectory prediction from the full sensor data set. By taking out and focusing on critical parameters (object position, velocity, lane marking geometry) while discarding redundant information, the system maintains prediction accuracy while significantly reducing processing requirements
3Speed
If sensor data processing is simplified to reduce computing resources, then processing speed is improved, but measurement precision of object location and trajectory deteriorates
Solution Approach 1:
The system performs preliminary filtering and organization of sensor data before detailed analysis. By pre-processing sensor inputs to identify and prioritize relevant features (such as detecting lane markings before analyzing object positions relative to them), the system reduces the computational complexity of subsequent processing while maintaining measurement precision through targeted analysis of critical data
Data Source
AI summary
The technology relates to predicting that an object is going to enter into a trajectory of a vehicle. This may include receiving sensor data identifying a first location of the object in an environment of the vehicle at a first point in time and receiving sensor data identifying a second location of the object in the environment at a second point in time. In addition, a boundary of the trajectory is determined by defining at least a two-dimensional area through which the vehicle is expected to travel in the future. A first distance between the boundary and the first location and a second distance between the trajectory and the second location are determined. The first distance and the second distance are used to determine that the object is going to enter into the trajectory at a future point in time.