Remote distance estimation system and method

A method for estimating distance, comprising:

• emitting, with a laser light emitter disposed on a robot at an angle relative to a horizontal plane, a laser beam, the laser beam projecting a line on a surface opposite the laser light emitter;
• capturing, with at least one image sensor disposed on the robot, images of the projected line;
• identifying, with a processor of the robot, the projected line in the images;
• determining, with the processor of the robot, a position of the projected line within the images;
• determining, with the processor of the robot, distances to objects within the images based on a relationship that relates position of the projected line within an image with distance between the robot or a sensor thereof and the surface on which the projected line is projected;
• capturing, with the image sensor disposed on the robot, images of the environment;
• obtaining, with the processor of the robot, the captured images;
• comparing, with the processor of the robot, at least one object from the captured images to objects in an object dictionary;
• identifying, with the processor of the robot, a class to which the at least one object belongs using an object classification unit;
• and
• instructing, with the processor of the robot, the robot to execute at least one action based on the object class identified.

A method for identifying a projected laser light in a captured image of the projected laser light, comprising:

• identifying, with a processor, at least one potential laser light in a captured image;
• determining, with the processor, a width of the at least one potential laser light;
• extracting, with the processor, an expected width of the projected laser light based on a relationship that relates width of the projected laser light to distance from a surface onto which the projected laser light is projected for a known distance from the surface onto which the projected laser light is projected;
• comparing, with the processor, the width of the at least one potential laser light with the expected width of the projected laser light;
• and
• identifying, with the processor, the projected laser light when the width of the at least one potential laser light is within a predetermined threshold from the expected width of the projected laser light.

A method for aligning images of a projected laser light, comprising:

• detecting, with a processor of a robot, a first feature at a first position in the first image based on a derivative of pixel values in the first image;
• detecting, with the processor of the robot, a second feature at a second position in the first image based on the derivative of pixel values in first image;
• detecting, with the processor of the robot, a third feature at a third position in the second image based on a derivative of pixel values in the second image;
• determining, with the processor of the robot, that the third feature of the second image is not the same feature as the second feature of the first image based on the characteristics of the third feature and the second feature not matching;
• determining, with the processor of the robot, that the third feature of the second image is the same feature as the first feature of the first image based on characteristics of the first feature and the third feature at least partially matching, wherein the first feature and the second feature are a projected laser light;
• and
• determining, with the processor of the robot, a first translation vector that associates the first image with the second image, the first translation vector corresponding with the displacement of the robot from the first location to the second location.