Road Shape Recognition Using Reliability-Weighted Point Sequences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing road shape recognition systems fail to accurately recognize road shapes when obstacles, such as preceding vehicles, obstruct the view of the partition line, leading to erroneous recognition.
Innovation Solution
A road shape recognizer system mounted on a vehicle with a periphery detector that identifies peripheral information like partition lines, roadside objects, and movement loci, assigns reliability levels to this information, and generates a point sequence representing the road shape in a coordinate system, allowing for precise recognition even in obstructed views.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the road shape recognizer relies solely on partition line detection, then the recognition process is simple, but the reliability deteriorates when partition lines are obscured by obstacles
Solution Approach 1:
The system employs multiple detection functions simultaneously: partition line detection, roadside object detection, and other vehicle detection. These multiple detection functions work together to compensate for each other's limitations, ensuring reliable road shape recognition even when partition lines are obscured. The controller integrates information from all three detection sources to determine road shape, making the system universally applicable across various driving conditions.
2Reliability
If the system uses multiple peripheral information sources, then the reliability improves, but the device complexity increases
Solution Approach 1:
The controller merges information from partition lines, roadside objects, and other vehicles into a unified road shape determination process. By combining these multiple information sources and processing them together, the system achieves reliable road shape recognition without requiring separate independent systems for each detection type, thus managing complexity through integration.
Solution Approach 2:
The periphery detector is designed with multi-functional capability to detect partition lines, roadside objects, and other vehicles simultaneously. This universal detection capability allows the system to gather multiple types of peripheral information using a single integrated detector, reducing the need for multiple separate detection devices and thereby controlling system complexity.
3Measurement precision
If the system continuously updates road shape information, then the accuracy improves, but the processing time and computational load increase
Solution Approach 1:
The periphery detector performs periodic detection of partition lines, roadside objects, and other vehicles at regular intervals. This periodic action allows the system to continuously update road shape information in a structured manner, balancing the need for accurate real-time recognition with efficient processing by operating at optimized detection cycles rather than continuous monitoring.
Data Source
AI summary
A road shape recognizer includes a peripheral information recognizer that recognizes at least two items of peripheral information based on an output of a periphery detector. A reliability assigner assigns a reliability level to each of the peripheral information. A point sequence generator generates and places a point sequence representing a shape of a road on which the own vehicle travels, based on at least two items of peripheral information and the reliability level. The point sequence generator generates and places a point sequence by generating and placing points one by one toward a distant place from a point located at a prescribed relative position to the own vehicle. The point sequence generator generates and places the next point corresponding to an amount of change in shape and a position of a point generated and placed at the end of the point sequence. The amount of change in shape is represented by the peripheral information and determined per section having a prescribed distance.