Abstract:
Adding a 3-D camera to a robotics system can improve throughput by computing the coordinates of the next object while the robot is busy with another task. In this case, we are using the Kinect camera for our 3-D camera. By sampling the 3-D position information of 64 points in a picture and their corresponding points in the coordinate of robot simultaneously, the coordinate transformation matrix can be found and as a result it is able to describe the one-to-one mapping rule. For example, if one figures out the position in a picture, where the robot is going to implement a picking, one can locate the corresponding picking position in robotic system.
By implementing cross-correlation of the template and targets, one can find the location with highest probability which usually can be expected location. After identifying shapes and locations of targets, we obtain the coordinate information in the pictures and transform them to the robotic coordinates. Once the robot has the coordinates, it can move to that location and pick up the object.
Adding a 3-D camera to a robotics system can improve throughput by computing the coordinates of the next object while the robot is busy with another task. In this case, we are using the Kinect camera for our 3-D camera. By sampling the 3-D position information of 64 points in a picture and their corresponding points in the coordinate of robot simultaneously, the coordinate transformation matrix can be found and as a result it is able to describe the one-to-one mapping rule. For example, if one figures out the position in a picture, where the robot is going to implement a picking, one can locate the corresponding picking position in robotic system.
By implementing cross-correlation of the template and targets, one can find the location with highest probability which usually can be expected location. After identifying shapes and locations of targets, we obtain the coordinate information in the pictures and transform them to the robotic coordinates. Once the robot has the coordinates, it can move to that location and pick up the object.