Surface Feature Detection Using Graph Polygons for Curb Traversal
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack the ability to accurately identify and navigate substantially discontinuous surface features (SDSFs) using a multi-part model and integrate SDSF trajectory with graphing polygons, especially considering candidate surface feature traversal angles and path obstructions.
Innovation Solution
The method involves processing point cloud data to filter and segment SDSF features, creating concave polygons, and forming graphing polygons to determine drivable surfaces, which allows a transport device to traverse SDSFs by selecting optimal paths and adjusting speed and direction based on SDSF criteria.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If point cloud data is processed to locate SDSFs using multi-part models and graphing polygons, then identification accuracy of SDSFs is improved, but device complexity and processing time increase
Solution Approach 1:
The patent segments the complex task of SDSF identification into multiple distinct modules: point cloud data acquisition, multi-part model matching (comparing candidate regions against stored SDSF templates), graphing polygon generation, and trajectory integration. Each module handles a specific aspect of the identification process, making the overall system more manageable and maintainable while achieving high accuracy through the coordinated operation of these specialized components.
2Reliability
If multi-part model matching and graphing polygon integration are implemented, then SDSF traversal reliability is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary actions by pre-storing SDSF multi-part models and characteristics in a database before actual traversal operations. During runtime, the system quickly retrieves and matches these pre-processed models against incoming point cloud data, significantly reducing processing time compared to analyzing SDSFs from scratch. Graphing polygons are also pre-computed for known SDSFs, enabling rapid trajectory determination when SDSFs are detected.
3Reliability
If sensor-based positioning and edge/weight graph analysis are used, then navigation safety is improved, but computational requirements and device complexity increase
Solution Approach 1:
The patent introduces graphing polygons as an intermediary representation that bridges sensor data and navigation decisions. Instead of directly processing raw point cloud data for navigation, the system first converts SDSF locations into graphing polygons with associated edge and weight attributes. These polygons serve as a simplified intermediary model that captures essential traversal information, reducing the computational burden on the transport device while maintaining navigation safety through rigorous graph analysis.
Data Source
AI summary
Substantially discontinuous surface feature traversal feature of the present teachings can leverage a transport device (TD), for example, but not limited to, an autonomous device or a semi-autonomous device, to navigate in environments that can include features such as substantially discontinuous surface features. The substantially discontinuous surface feature traversal feature can enable the TD to travel on an expanded variety of surfaces. In particular, substantially discontinuous surface features can be accurately identified and labeled so that the TD can automatically maintain the performance of the TD during ingress and egress of the substantially discontinuous surface feature.