Robotic Arm Object Modeling for Operating Room Collision Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robotic medical systems face challenges in avoiding collisions between robotic arms and other objects in the operating room, including medical accessories and staff, due to limited collision detection and avoidance capabilities.
Innovation Solution
The system incorporates a model of the robotic arms and medical accessories, preventing collisions by restricting robotic arm movement into keep-out zones and using sensors to update the model with real-time object positions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If robotic arms are used to control medical tools in laparoscopic procedures, then precision and control of medical tool manipulation is improved, but the risk of collision between robotic arms and other objects (including other robotic arms and medical staff) increases
Solution Approach 1:
The system performs preliminary actions by creating a digital model of the operating room environment including all objects and robotic arms before the procedure begins. This pre-established model allows the collision detection system to evaluate potential collisions before they occur, enabling preventive measures to be taken while maintaining the precision benefits of robotic arm control.
Solution Approach 2:
The patent creates a virtual copy or digital twin of the physical operating room environment, including robotic arms, medical tools, and surrounding objects. This virtual model allows for simulation and prediction of robotic arm movements without actual physical movement, enabling collision detection while preserving the precision control capabilities of the robotic system.
2Adaptability or versatility
If the workspace of robotic arms is expanded to accommodate more medical accessories and staff movement, then operational flexibility is improved, but the complexity of collision detection and avoidance increases
Solution Approach 1:
The digital model serves multiple functions: it represents the physical environment geometry, tracks object positions, predicts robotic arm trajectories, and performs collision detection all within a single unified system. This multi-functionality allows the workspace to be flexible and adaptable while managing complexity through integration rather than separate specialized systems.
Solution Approach 2:
The patent replaces complex mechanical collision avoidance mechanisms with a computational approach using digital modeling and virtual reality technology. Instead of physical sensors and mechanical constraints, the system uses software-based collision detection in the virtual model, reducing mechanical complexity while enabling greater workspace flexibility.
3Measurement precision
If real-time tracking of all objects in the workspace is implemented, then collision detection accuracy is improved, but the computational resources and system complexity increase
Solution Approach 1:
The system extracts only the essential collision-relevant information from the full environment model, such as keep-out zones and critical object positions, rather than processing complete real-time data of all objects. This selective extraction maintains collision detection accuracy while reducing computational resource consumption by focusing only on the most relevant data for safety.
Data Source
AI summary
Systems and methods for collision avoidance using object models are provided. In one aspect, a robotic medical system, includes a platform, one or more robotic arms coupled to the platform, a console configured to receive input commanding motion of the one or more robotic arms, a processor, and at least one computer-readable memory in communication with the processor. The processor is configured to control movement of the one or more robotic arms in a workspace based on the input received by the console, receive an indication of one or more objects are within reach of the one or more robotic arms, and update the model to include a representation of the one or more objects in the workspace.