Robotic Map Generation with Online Path Refinement for Local Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic mapping technologies struggle to achieve high-resolution and local accuracy simultaneously, leading to coarse maps that are insufficient for precise environmental representation.
Innovation Solution
A multistage approach is proposed, where a coarse global map is first created using conventional techniques like SLAM or SfM, followed by offline 3D path planning to maintain a targeted distance to nearest structures, and finally, online path replanning with RGB-D camera measurements to achieve targeted resolution and local accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional robotic mapping techniques (SLAM or SfM) are used to create a global map, then the map coverage is complete, but the local resolution and accuracy are coarse and insufficient
Solution Approach 1:
The patent divides the mapping process into two distinct stages: (1) global mapping using SLAM/SfM to establish overall spatial relationships, and (2) local refinement by navigating the robot along optimized paths to collect high-resolution depth measurements of specific surfaces. This segmentation allows each stage to focus on its strength without being constrained by the other's limitations.
Solution Approach 2:
The system performs preliminary global mapping to create a coarse 3D map before conducting local refinement. The coarse map serves as a foundation that guides subsequent high-resolution data collection, ensuring that detailed measurements are acquired in the correct spatial context and can be properly registered to the global coordinate system.
2Manufacturing precision
If the robot maintains a fixed distance from structures during traversal, then the traversal path is simple to plan, but the measurement resolution cannot be optimized for different regions
Solution Approach 1:
The patent implements local quality by allowing the robot to maintain different distances from structures depending on the specific region being mapped. The path planning system calculates optimal traversal distances based on desired measurement resolution, surface geometry, and sensor characteristics, enabling high-resolution mapping in critical areas while maintaining efficient coverage in less critical regions.
Solution Approach 2:
The traversal path is made dynamic rather than static, allowing the robot to adjust its distance from structures in real-time based on local geometric features and mapping priorities. The system dynamically modifies the traversal path during execution to optimize measurement quality while navigating complex environments with varying surface characteristics.
3Measurement precision
If high-resolution depth measurements are collected by moving the robot closer to structures, then the local accuracy improves, but the robot may collide with structures and the traversal becomes more constrained
Solution Approach 1:
The system performs preliminary anti-action by pre-calculating safe traversal distances that prevent collisions before the robot encounters structures. The path planning algorithm incorporates structure geometry and robot dimensions to determine maximum approach distances, creating a safety buffer that allows the robot to get close enough for high-resolution measurement while maintaining collision-free operation throughout the traversal.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables the creation of high-quality maps with both global and local accuracy, ensuring that all surfaces are accurately represented with high resolution, thereby improving the precision of robotic navigation and data collection.
Implementation Method 1
The coarse global mapping can be obtained via a LIDAR scan
Implementation Method 2
the robot configured to obtain depth sensor measurements of the nearest structure during traversal along the determined robotic traversal path
Data Source
AI summary
Various examples are provided related to generating a map of an environment. In one example, a method includes obtaining a coarse global mapping of an environmental space; determining a robotic traversal path within the environmental space using the coarse global mapping, the robotic traversal path maintaining a targeted distance to a nearest structure within the environmental space; initiating traversal of a robot along the determined robotic traversal path, the robot obtaining depth sensor measurements of the nearest structure during traversal along the determined robotic traversal path; and refining the robotic traversal path during traversal by the robot along the determined robotic traversal path based upon the depth sensor measurements, where the robotic traversal path is refined online to achieve targeted resolution and local accuracy of the depth sensor measurements. A refined map of the environmental space can be generated using the depth sensor measurements.