Predicting Vehicle Movement Range Using Road Curvature Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods struggle to accurately predict the movement range of moving objects, especially at traffic intersections, sharp curves, or during turns, due to limitations in using position and velocity data alone.
Innovation Solution
An information processing device calculates the predicted movement range of moving objects by integrating moving object information and road information, utilizing sensors like millimeter-wave radar or LIDAR, and employing an extended Kalman filter to account for curvature and drivable ranges, thereby enhancing prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods use only position and velocity data to predict movement range, then the prediction method is simple, but the prediction accuracy deteriorates at intersections and curves
Solution Approach 1:
The patent merges multiple data sources including position data, velocity data, road curvature information, and intersection data into a unified prediction model. By combining these diverse elements, the system achieves accurate movement range prediction at complex locations like intersections and curves while maintaining a structured approach that manages complexity.
Solution Approach 2:
The patent introduces road information (curvature, intersections, drivable ranges) as intermediary elements that mediate between the vehicle's motion state and the predicted movement range. These intermediary road characteristics provide contextual information that enables accurate prediction without requiring direct observation of all possible future paths.
2Reliability
If the predicted movement range is widened to ensure safety, then collision avoidance capability is improved, but false warnings increase
Solution Approach 1:
The patent applies local quality by adjusting the predicted movement range dynamically based on location-specific characteristics. At intersections and curves, the prediction range is appropriately expanded to account for potential deviations, while on straight roads it remains tighter. This location-adaptive approach ensures safety where needed while minimizing false warnings elsewhere.
Solution Approach 2:
The patent changes the parameters defining the movement range based on road conditions, curvature, and intersection proximity. By dynamically adjusting these parameters rather than using a fixed range, the system achieves reliable collision avoidance at critical locations while maintaining precision on normal roads, thereby reducing false warnings.
3Measurement precision
If the predicted movement range is narrowed for precision, then false warnings are reduced, but safety margin deteriorates at complex road locations
Solution Approach 1:
The patent implements a dynamic prediction model that adapts the movement range based on real-time road conditions, vehicle state, and environmental factors. Rather than using a static narrow or wide range, the system continuously adjusts the prediction boundaries to match the actual risk level at each location, achieving both precision and safety.
Solution Approach 2:
The patent performs preliminary analysis of road characteristics (curvature, intersections, drivable ranges) before calculating the movement range. By pre-processing this contextual information and incorporating it into the prediction model in advance, the system prepares appropriate safety margins at complex locations while maintaining precision elsewhere.
Data Source
AI summary
According to an embodiment, an information processing device includes one or more processors. The one or more processors are configured to obtain moving object information related to a moving object; obtain road information; and calculate a predicted movement range of the moving object based on the moving object information and the road information.