Environment Map Alignment Using Markers, SLAM, and Design Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual surveying of warehouse environments for robotic navigation is time-consuming and does not align marker positions with design models, leading to delayed deployment and navigation challenges.
Innovation Solution
A computing system performs simultaneous localization and mapping (SLAM) using sensor data to build maps of marker positions while determining transformations to align them with design models, enabling robots to navigate using both marker and physical feature information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual surveying is used to map warehouse environments for robotic navigation, then marker positions can be recorded, but the process is time-consuming and does not align with design models
Solution Approach 1:
The patent replaces manual mechanical surveying with an automated optical scanning system. A scanner captures images of markers in the environment, and a computing system automatically processes these images to determine marker positions and generate maps, eliminating the need for time-consuming manual measurement while maintaining or improving position accuracy.
Solution Approach 2:
The patent creates a digital copy of the physical environment by mapping marker positions from scanned images. The generated map is a digital representation that can be aligned with CAD design models, allowing virtual overlay and comparison without requiring physical measurement activities.
2Loss of information
If manual surveying methods are used, then marker positions can be obtained, but alignment with design models is not achieved
Solution Approach 1:
The patent merges the marker position data with CAD design model information by overlaying the generated map onto the digital design model. This integration allows direct comparison and alignment assessment between the physical marker placement and the planned design, preserving alignment information that would otherwise be lost.
Solution Approach 2:
The patent introduces a computing system as an intermediary that processes scanner images, determines marker positions, generates maps, and aligns them with CAD models. This intermediary automatically performs the complex alignment calculations and transformations, managing the system complexity rather than requiring manual intervention.
3Reliability
If traditional mapping approaches are used, then environment data can be collected, but real-time feedback is not provided
Solution Approach 1:
The patent enables continuous operation by allowing the robotic system to navigate using the generated map and marker information immediately after a single scanning iteration. The system does not require multiple surveying passes or extended deployment periods, providing continuous useful action from the first scan.
Solution Approach 2:
The robotic system uses the generated map and alignment information to autonomously navigate the environment without requiring additional manual intervention or repeated surveying. The system self-calibrates and self-navigates using the digital map and marker positions, improving reliability while reducing deployment time.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computing system receives and uses sensor data indicative of positions of multiple markers positioned relative to a sensor within an environment to determine a pose of the sensor and also create a map that indicates the markers positions. The computing system also receives and uses subsequent sensor data indicative of distances from the sensor to surfaces in the environment as well as the pose of the sensor to determine an occupancy grid map that represents the surfaces within the environment. The computing system may then determine a transformation between the map of the markers and a design model of the environment that relates occupied cells in the occupancy grid map to sampled points from the design model, and provide the transformation between the map of the plurality of markers and the design model.