ROBOTIC VISION TECHNOLOGIES INC
As of February 2018
RVT’s patent portfolio covers technology that has been developed and enhanced for over twenty years as well as new technology currently under development. eVF, or eVision Factory, is the brand name of the software that RVT sells and licenses. It allows users to create scalable and robust vision guidance systems for industrial and non-industrial robots.
Current Patent Portfolio
- Method and Apparatus for Single-Camera 3D Vision Guided Robotics (US 6,816, 755 B2)
- Method and Apparatus for Single Image3D Vision Guided Robotics (US 8,095,237 B2)
- System and Method of Three-Dimensional Pose Estimation (US 7,957,583 B2)
- System and Method of Determining Object Pose (US 8,437,535 B2)
- Method and Apparatus for Machine Vision (US 7,336,814 B2)
- Methods and Apparatus to Facilitate Operations in Image Based Systems (US 8,559,699 B2)
- System and Method of Detection and Tracking of Item Features (US 9,734,401 B2)
- System and Method of Sensor-Based Safety Features for robotic Equipment (US 9,740,193 B2)
- System and Method of Distance Determination between RFID Tags (US 9,767,330 B2)
- System and Method of Foreground Motion Detection in compressed Video Data (US 9,712,828 B2)
Protected by our first patent is the cornerstone of eVF: Single Camera 3D (SC3D) technology. SC3D uses one camera to calculate vision information in six degrees of freedom. This patent covers picking four to six unique features on a part to train the vision system to calculate an accurate 3D position of an object for the purpose of robot guidance.
The second patent protects the technology of locating the part anywhere in the working envelope of the robot to enable the system direct/guide the robot in its interaction with that part.
The third patent reference above covers how we train a workspace using multiple 2D images and translate them into a 3D object pose.
The fourth patent of eVF contains validation tools that are built into the software framework. These tools are unique to RVT and include automatic calibration (AutoCal), automatic system training (AutoTrain), and automatic system testing (AccuTest).
The fifth patent listed protects all of the equations behind these tools.
The sixth patent covers technology that we use to ensure that parts will be picked from a bin until it has been completely emptied. Random Bin Picking (RBP) is an add-on module to eVF that allows a robot to locate and remove many parts from a bin. These parts can be randomly placed and completely unstructured.
The seventh patent is for finding features on a part automatically. Previously in eVF, the user has had to manually specify which features on a part should be used in the master image for reference. This new technology enables the software to find features on the part automatically and score them. This patent also includes controlling the lighting conditions in a work cell automatically. For instance, over the course of a day lighting conditions may change drastically. This new technology is able to control the lighting automatically using feedback from the camera. Both enhancements significantly reduce costs for the user.
The eighth patent is a new patent that focuses on humans and robots sharing a work cell, a module we call Safety Net. Currently, expensive light screens and other sensors are used to protect workers from accidentally breaching a robot’s working envelope. This new technology uses a camera-based approach and is able to detect an object coming into contact with a robot. The user interface allows an operator to designate zones where the robot would either slow down or stop, based upon where the object is at with respect to the designated zones.
The ninth patent is a collaboration patent with full exclusive rights into perpetuity. This new patent is a mesh of inexpensive passive RFID tags that are used to triangulate by radio signal flight times the location of each tag and hence the position of the robot or a part of interest. No wiring is required.
The tenth patent is a collaboration patent with full exclusive rights into perpetuity. This new patent is a high speed vision system, such as safety cameras, used to compress video to maintain a high frame rate. This method allows the background to be ignored and only the foreground objects of interest processed by the vision system.
RVT filed for 12 new patents between 2015 -2017. These new patents combine today’s advanced computing power with robot communications and 3D vision software.
- Laser and Camera Automatic Calibration
- Multi-User operation of Structured Light Based 3D Cameras
- Alignment Markers and Recognizing Deformed Objects
- 3D Object Rotation-Based Mechanical Parts Selection through 2D image Processing
- Orientation based hash space for Fast Part Orientation Sensing
- Detecting Incidental Robot-Human Contact using Physiological Tremor
- Stable Grasp Point Selection for Robot Grippers with Machine Vision & Ultrasound Beam Forming
Trademarks and Copyrights owned by RVT
- Random Bin Picking
- eVision Factory