System and method for determining depth perception in vivo in a surgical robotic system
Inventors
Santini, Fabrizio • KHALIFA, Sammy
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12731278-B2
Publication Date
2026-09-08
Expiration Date
Abstract
A system and method for generating a depth map from image data in a surgical robotic system that employs a robotic subsystem having a camera assembly with first and second cameras for generating image data. The system and method generates based on the image data a plurality of depth maps, and then converts the plurality of depth maps into a single combined depth map having distance data associated therewith. The system and method can then control the camera assembly based on the distance data in the single combined depth map.
Core Innovation
The invention describes a surgical robotic system that uses image data from first and second cameras to generate two different types of depth maps selected from autofocus, parallax, or disparity depth maps. The depth maps are converted into a single combined depth map with associated distance data. The system also generates confidence values for points or regions in the combined depth information.
The combined depth and confidence data can be used to control the camera assembly or robotic arms and to support collision avoidance, navigation, and surgical-scene mapping. The description states that CNN-based fusion reduces noise and ambiguity in the individual depth maps. The supplied content does not explicitly describe the background problem being solved.
Claims Coverage
The two independent claims cover a surgical robotic system and a method for generating and using a combined depth map. Together, they contain two main inventive features.
Surgical robotic system with a combined depth map
A robotic subsystem has a camera assembly with first and second cameras, a processor, a control unit, and a depth perception subsystem. The depth perception subsystem generates two different types of depth maps selected from autofocus, parallax, or disparity depth maps and converts them into a single combined depth map with associated distance data.
Method for generating and using a combined depth map
The method generates image data using first and second cameras, generates two different types of depth maps selected from autofocus, parallax, or disparity depth maps, and converts them into a single combined depth map with associated distance data. The camera assembly is controlled based on the distance data.
The independent claims cover both the system that combines depth maps from two cameras and the method that generates the combined map and uses its distance data to control the camera assembly.
Stated Advantages
CNN-based fusion reduces noise and ambiguity in the individual depth maps.
Documented Applications
The combined depth and confidence data support collision avoidance, navigation, and surgical-scene mapping.
Distance data from the single combined depth map can control the camera assembly or robotic arms.
Interested in licensing this patent?