Published Technical Disclosure Archive

Enhanced Multi-Modal Depth Sensing for Automated Surgical Robots

Publication ID: 24-11857153_0001_PTD
Published: November 07, 2025
Category:Direct Improvements & Enhancements

Legal Citation

pr1or.art Inc., “Enhanced Multi-Modal Depth Sensing for Automated Surgical Robots,” Published Technical Disclosure No. 24-11857153_0001_PTD, Published November 07, 2025, available at https://archive.pr1or.art/24-11857153_0001_PTD
This technical disclosure describes improvements that would be readily apparent to a Person Having Ordinary Skill In The Art (PHOSITA) when considered in combination with the foundational architecture disclosed in U.S. Patent No. 11,857,153.

Summary of the Inventive Concept

An advanced system and method for multi-modal depth sensing in automated surgical robots, enabling high-resolution, real-time 3D point cloud generation and improved surgical tool tracking.

Background and Problem Solved

The original patent disclosed a system for multi-modal sensing of three-dimensional position information of a surface of an object, but had limitations in terms of imaging modalities, depth measurement accuracy, and real-time tracking capabilities. The new inventive concept addresses these limitations by introducing a multi-modal sensor array, machine learning-based refinement, and high-speed image capture, enabling more accurate and efficient surgical procedures.

Detailed Description of the Inventive Concept

The enhanced system comprises a multi-modal sensor array that captures a plurality of images of an object in a surgical scene using a combination of visible, infrared, and ultrasonic imaging modalities. The processing unit generates a high-resolution, three-dimensional point cloud of the object based on the plurality of images, and applies machine learning algorithms to refine the point cloud and improve the accuracy of the depth measurements. The system enables real-time tracking and adjustment of surgical tools, ensuring more precise and efficient surgical procedures.

Novelty and Inventive Step

The new claims introduce the novel concept of a multi-modal sensor array, machine learning-based refinement, and high-speed image capture, which provide a significant improvement over the original patent's limitations. The inventive step lies in the combination of these features, which enables high-resolution, real-time 3D point cloud generation and improved surgical tool tracking.

Alternative Embodiments and Variations

Alternative embodiments may include the use of additional imaging modalities, such as X-ray or optical coherence tomography, or the integration of the system with other surgical tools and instruments. Variations may include the use of different machine learning algorithms or the adaptation of the system for use in other medical specialties or industries.

Potential Commercial Applications and Market

The enhanced multi-modal depth sensing system has significant commercial potential in the medical device industry, particularly in the field of robotic-assisted surgery. The system's ability to provide high-resolution, real-time 3D point cloud generation and improved surgical tool tracking can improve surgical outcomes, reduce procedure time, and enhance patient safety.

CPC Classifications

SectionClassGroup
A A61 A61B1/000094
A A61 A61B1/00
A A61 A61B1/000095
A A61 A61B1/00193
A A61 A61B90/06
G G06 G06T7/521
G G06 G06T7/557
G G06 G06T7/593
H H04 H04N13/239
A A61 A61B2090/062
A A61 A61B2090/363
A A61 A61B2090/371
A A61 A61B2090/3933
A A61 A61B2090/3937

Field of Art

Surgical robotics and computer vision, specifically multi-modal imaging systems for depth sensing and 3D reconstruction in medical applications. Requires expertise in medical imaging, sensor fusion, computer vision algorithms, and robotic surgical systems

Person of Ordinary Skill (PHOSITA) Profile

A skilled practitioner with advanced degrees in biomedical engineering, computer science, or robotics, possessing expertise in multi-modal sensor integration, machine learning image processing, and surgical robotic system design

Obviousness Rationale

A person skilled in the art would recognize that extending the source patent's multi-modal depth sensing approach with machine learning refinement and high-speed image capture represents a predictable technological progression. The core sensing methodology remains consistent, with the PTD introducing incremental improvements in processing and sensor integration that would be apparent to an ordinary practitioner in surgical robotics imaging systems.

Obvious Combinations & Variations

Source Patent Element
Obtaining images using multiple imaging modalities with markers on an object
PTD Variation
Adding specific visible, infrared, and ultrasonic imaging modalities with machine learning-based point cloud refinement
Obviousness Reasoning
Combining known imaging modalities with machine learning is a standard technique for improving depth sensing accuracy, representing an obvious design optimization for a skilled practitioner
Source Patent Element
Depth measurements weighted based on image quality and imaging parameters
PTD Variation
Implementing pixel-level machine learning algorithms to dynamically refine depth measurements
Obviousness Reasoning
Applying advanced computational techniques to improve measurement precision is a predictable evolution of existing weighted measurement approaches
Source Patent Element
Three-dimensional coordinate generation for surgical objects
PTD Variation
Real-time surgical tool tracking and motion adjustment based on high-resolution point cloud generation
Obviousness Reasoning
Extending coordinate generation to dynamic surgical tool positioning represents a logical and foreseeable application of the core depth sensing technology
Source Patent Element
Multi-modal imaging system for capturing object position information
PTD Variation
High-speed image capture at 30+ frames per second with multi-modal sensor array
Obviousness Reasoning
Increasing frame rate and sensor integration is a standard performance optimization that would be obvious to a skilled practitioner seeking improved real-time tracking
Source Patent Element
Marker-based depth sensing in surgical environments
PTD Variation
Expanding marker detection across multiple imaging modalities with machine learning enhancement
Obviousness Reasoning
Integrating machine learning for improved marker detection and tracking represents a predictable technological progression in computer vision systems
35 U.S.C. § 103 Summary: Based on the teachings of US Patent 11857153 and the disclosed technical variations, a person having ordinary skill in the art would find the claimed innovations of multi-modal depth sensing with machine learning refinement and high-speed image capture to be obvious extensions of existing surgical robotics imaging technologies. The incremental improvements represent predictable advancements that would be readily conceived by a skilled practitioner in the field of medical imaging and robotic surgical systems.

Original Patent Information

Patent NumberUS 11,857,153
TitleSystems and methods for multi-modal sensing of depth in vision systems for automated surgical robots
Assignee(s)ACTIV Surgical, Inc.