Multi-Face Tool Tracking for Faster Pose Lock-On
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately determining the pose of surgical tools and robotic arms during procedures, particularly in scenarios where tools rotate beyond a maximum marker angle, leading to inefficiencies in tracking and increased lock-on times.
Innovation Solution
A tracking device with multiple faces and markers, utilizing infrared light emitting diodes (IREDs) and a smart algorithm to selectively activate markers, allows for efficient determination of tool pose by predicting the face in view and reducing lock-on time through sequential activation strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If markers are continuously activated on all faces of the tracking device, then the system can track the tool pose accurately, but the lock-on time increases and processing efficiency decreases
Solution Approach 1:
The system performs preliminary action by predicting which face will be in view based on the current tool pose and rotational velocity. This prediction allows the system to pre-activate markers on the anticipated face before it enters the camera view, reducing the lock-on time when the face becomes visible while maintaining accurate tracking.
Solution Approach 2:
The system dynamically adjusts marker activation based on real-time conditions. Instead of continuously activating all markers, the system activates only the markers on the predicted face, and updates the prediction as the tool rotates. This dynamic approach reduces unnecessary marker activation and processing while maintaining continuous accurate tracking.
2Reliability
If the system processes all markers on all faces simultaneously, then complete pose information is available, but the processing complexity and computational load increase
Solution Approach 1:
The system extracts only the necessary information by processing markers on the single predicted face that is expected to be in view, rather than processing all markers on all faces. This extraction approach reduces computational complexity while maintaining tracking reliability, as the predicted face contains sufficient information to determine tool pose.
Solution Approach 2:
The system applies partial action by processing only a subset of markers (those on the predicted face) rather than all markers. This partial processing is sufficient for accurate pose determination and significantly reduces computational complexity compared to processing all markers simultaneously.
3Device complexity
If the tracking device uses a single face with markers, then the structure is simpler, but the tool cannot be tracked when it rotates beyond the camera view
Solution Approach 1:
The tracking device structure is segmented into multiple faces, each with its own set of markers. This segmentation allows the tool to be tracked as it rotates, as different faces become visible at different rotation angles. The system processes only the markers on the currently visible predicted face, maintaining structural simplicity while expanding tracking range.
Solution Approach 2:
By predicting which face will be in view based on current pose and rotational velocity, the system prepares in advance for the tool's rotation. This preliminary prediction allows continuous tracking across multiple faces without requiring complex simultaneous processing of all faces, thus maintaining structural simplicity while achieving extended tracking range.
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
The system enhances the accuracy and speed of determining tool pose, reducing lock-on time by up to 166 ms for 60Hz refresh rate, thereby improving surgical procedure efficiency and accuracy.
Implementation Method 1
utilizing infrared light emitting diodes (IREDs)
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
Systems, methods, and devices for determining a tool pose are provided. A tracking device mounted to a tool may comprise a plurality of faces and a plurality of markers defining a plurality of sets of markers. Each set of markers may comprise one or more markers of the plurality of markers and each set of markers may be disposed on a corresponding face. Information about a set of markers of the plurality of markers may be received. A face of the plurality of faces having the set of markers disposed thereon may be determined. A pose of the tool based on the information and the determined face may be determined.