Robot Teleoperation with Dynamic Point-Cloud Virtual Fixtures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional robot teleoperation technologies struggle with accuracy, stability, and security in complex and changing environments, particularly due to the limitations of pre-defined virtual fixtures that cannot adapt in real time to unstructured or irregular geometries.
Innovation Solution
A robot teleoperation method that generates a point cloud from real-time images to establish virtual fixtures dynamically, using forbidden or guidance virtual fixtures based on geometric features, determining reference and control points, and applying virtual forces to guide or restrict robot movements accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If pre-defined virtual fixtures are used in conventional robot teleoperation, then the system structure is simple and easy to implement, but the system cannot adapt to complex and changing environments with irregular geometries, resulting in poor accuracy and reliability
Solution Approach 1:
The patent implements dynamic virtual fixtures that are generated in real-time based on point cloud data of the environment, rather than using static pre-defined virtual fixtures. The virtual fixture generator continuously updates the virtual environment model as the robot moves, allowing the system to adapt to changing geometries and complex environments dynamically. This resolves the contradiction by making the system adaptable while managing complexity through automated real-time generation.
Solution Approach 2:
The system uses the robot's own sensor data (point cloud) to automatically generate and update its virtual environment model without requiring external pre-programming or manual configuration. The virtual fixture generator extracts geometric features directly from the robot's perceived environment and creates corresponding virtual fixtures autonomously. This self-service approach improves adaptability to unknown environments while avoiding the complexity of manual system configuration.
2Reliability
If real-time point cloud processing and virtual fixture generation are implemented, then the robot's adaptability to complex environments improves, but the computational load and processing time increase
Solution Approach 1:
The patent performs preliminary processing of point cloud data by extracting only the necessary geometric features (edges, surfaces, vertices) that are relevant for virtual fixture generation, rather than processing the entire point cloud in detail. The system identifies and extracts key geometric characteristics in advance, which are then used to generate virtual fixtures. This preliminary extraction approach maintains reliability by capturing essential environmental features while reducing the overall processing time and computational burden.
Solution Approach 2:
The system extracts only the critical geometric features from the point cloud data that are necessary for virtual fixture generation, discarding redundant information. The virtual fixture generator takes out and processes only the essential geometric characteristics (such as surface normals, edge directions, and key vertices) needed to create accurate virtual fixtures, rather than processing all point cloud data. This extraction approach ensures operating security through accurate environmental representation while minimizing processing time by focusing computational resources on essential features.
3Measurement precision
If virtual fixtures are generated based on geometric features of point cloud data, then the accuracy of environment representation improves, but the computational complexity of processing and analyzing point cloud data increases
Solution Approach 1:
The patent segments the point cloud processing task into distinct modules: point cloud acquisition, geometric feature extraction, virtual fixture generation, and rendering. Each module handles a specific aspect of the process independently. The geometric feature extractor is further divided into sub-components that extract different types of features (surfaces, edges, vertices) separately. This segmentation maintains measurement precision by dedicating specialized processing to each feature type while reducing overall processing complexity through modular architecture and parallel processing of different feature categories.
Solution Approach 2:
The system applies different processing quality and detail levels to different regions of the environment based on their importance. Critical areas that require precise virtual fixtures (such as obstacles near the robot or narrow passages) receive higher processing quality and more detailed geometric feature extraction, while less critical areas use lower processing quality. This local quality approach ensures high measurement precision where needed for safety and operation while reducing computational complexity in less critical regions, balancing accuracy and processing requirements.
Data Source
AI summary
A robot teleoperation method, a robot and a storage medium are disclosed. The method includes: acquiring an image of a target object, and generating a point cloud of the target object according to the image; establishing a virtual fixture based on a geometric feature corresponding to the point cloud; the virtual fixture including at least one of a forbidden region virtual fixture or a guidance virtual fixture; determining a reference point of the virtual fixture and a control point of the robot, and determining a virtual force of the virtual fixture acting on the control point according to a distance between the reference point and the control point; and determining a control force applied to the control point based on the virtual force.