Sidewalk Detection Filtering for Autonomous Vehicle Behavior
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining the presence of sidewalks adjacent to roads, leading to overly cautious driving and increased trip times, as existing methods require labor-intensive manual mapping and are inefficient in identifying sidewalk locations.
Innovation Solution
Computing devices use map data and sensor data to identify potential sidewalk areas, generate topology data, apply filters to remove unlikely areas, and operate the vehicle in an autonomous driving mode based on filtered data, including the use of morphological and image filters to determine sidewalk presence and adjust vehicle behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual mapping methods are used to identify sidewalk locations, then sidewalk detection accuracy is improved, but labor intensity and time consumption increase significantly
Solution Approach 1:
The patent replaces manual mechanical mapping with an automated computer vision system that uses image processing algorithms to detect sidewalks from captured images. The system automatically identifies sidewalk features, generates location data, and updates maps without human intervention, thereby eliminating labor-intensive manual mapping while maintaining detection accuracy.
Solution Approach 2:
The system enables self-service mapping by allowing the autonomous vehicle to independently detect, process, and map sidewalks using its own onboard cameras and processing units. The vehicle performs self-mapping operations without requiring external manual surveying teams, thus reducing time consumption and labor requirements while achieving accurate sidewalk detection.
2Reliability
If autonomous vehicles operate in overly cautious mode without accurate sidewalk detection, then safety is improved, but trip times increase and traffic flow is reduced
Solution Approach 1:
The system implements feedback by continuously detecting sidewalk presence and providing real-time information to the vehicle's control system. Based on this feedback, the vehicle dynamically adjusts its driving behavior - operating cautiously when sidewalks are detected and normally when they are not - thereby maintaining safety while optimizing trip times and reducing unnecessary traffic impact.
Solution Approach 2:
The patent applies dynamics by making the vehicle's operating mode adaptable rather than static. The system continuously monitors sidewalk detection results and adjusts driving parameters in real-time, transitioning between cautious and normal operating modes based on actual environmental conditions. This dynamic adjustment ensures safety when needed while improving productivity when safe to do so.
3Measurement precision
If comprehensive filtering methods are applied to identify potential sidewalk areas, then sidewalk identification accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the sidewalk identification process into multiple sequential filtering stages: first identifying potential sidewalk areas from captured images, then applying successive filters to eliminate unlikely areas, and finally confirming actual sidewalk locations. This segmentation allows the system to achieve high identification accuracy while managing computational complexity by processing data in manageable stages rather than requiring all computations simultaneously.
Data Source
AI summary
Aspects of the disclosure relate to detecting sidewalks adjacent to roads. In this regard, a set of potential sidewalk areas adjacent to one or more roads in a vehicle's vicinity may be determined based on map data. Topology data for the set of potential sidewalk areas may be generated based on sensor data received from a perception system of the vehicle. The set of potential sidewalks may be filtered to remove areas unlikely to include a sidewalk. The vehicle may be operated based on the filtered set of potential sidewalk areas, which may include taking precautionary measures when within a predetermined distance from any of the filtered set of potential sidewalks.