3D-2D vision system for robotic carton unloading
Robotic carton loader or unloader incorporates three-dimensional (3D) and two-dimensional (2D) sensors to detect respectively a 3D point cloud and a 2D image of a carton pile within transportation carrier such as a truck trailer or shipping container. Edge detection is performed using the 3D point cloud, discarding segments that are two small to be part of a product such as a carton. Segments that are too large to correspond to a carton are 2D image processed to detect additional edges. Results from 3D and 2D edge detection are converted in a calibrated 3D space of the material carton loader or unloader to perform one of loading or unloading of the transportation carrier. Image processing can also detect jamming of products sequence from individually controllable zones of a conveyor of the robotic carton loader or unloader for singulated unloading.
1. A method of determining locations of individual cartons in a handling system, the method comprising:
receiving, by a carton detection system that is positioned on a robotic carton handling system, a two-dimensional (2D) image and a three dimensional (3D) point cloud of at least one portion of a carton pile;
detecting, by a processing subsystem in connection with the carton detection system, a set of segments within the 3D point cloud;
detecting, by the processing subsystem in connection with the carton detection system, another set of segments within the 3D point cloud;
qualifying, by the processing system, the set of segments as 3D detected cartons and the another set of segments as 2D detected cartons;
combining, by the processing subsystem, the 2D and 3D detected cartons into a detection result; and
converting, by the processing subsystem, the detection result using calibration information into a 3D location for cartons targeted for removal.
2. The method of claim 1 , wherein the set of segments are qualified as the 3D detected cartons if the set of segments are lesser than a segment threshold.
3. The method of claim 1 , wherein the another set of segments are qualified as the 2D detected cartons if the another set of segments are greater than a segment threshold.
4. The method of claim 3 , wherein when the another set of segments are greater than the segment threshold:
determining a 2D mask corresponds to the another set of segments;
determining a portion of the 2D image that corresponds to the 2D mask;
detecting the another set of segments within the portion of the 2D image; and
qualifying detected another set of segments as the 2D detected cartons.
5. The method of claim 1 , further comprising: receiving the 2D image and 3D point cloud from one or more sensors to detect the at least one portion of the carton pile;
receiving a 2D image and 3D point cloud from another one or more sensors to detect a contiguous portion of the carton pile; and
combining the 2D and 3D detected cartons from both the one portion and the contiguous portion to form the detection result.
6. The method of claim 1 , wherein qualifying the another set of segments as the 2D detected cartons further comprises discarding, by the processing subsystem, edges that form a smaller rectangle fully encompassed within a larger rectangle.
7. The method of claim 1 , further comprising stitching the 2D image and the 3D point cloud together to obtain an image of the carton pile.
8. The method of claim 1 , further comprising.
performing one of a loading operation and an unloading operation by the robotic carton handling system using the 3D location.
9. A carton detection system to facilitate unloading cartons in a carton pile by a robotic carton handling system:
a sensor configured to provide a two-dimensional (2D) optical image and a three-dimensional (3D) point cloud of at least one portion of a carton pile resting on a floor of a transportation carrier;
a processing subsystem in communication with the sensor, the processing subsystem:
detects a set of segments within the 3D point cloud;
detects another set of segments within the 3D point cloud;
qualifies the set of segments as 3D detected cartons and the another set of segments as 2D detected cartons;
combine the 2D and 3D detected cartons into a detection result; and
convert the detection result using calibration information into a 3D location for cartons targeted for removal to enable the robotic carton handling system to remove the cartons from the carton pile.
10. The robotic carton handling system of claim 9 , wherein the set of segments are qualified as the 3D detected cartons if the processing subsystem determines that the set of segments are lesser than a segment threshold.
11. The robotic carton handling system of claim 9 , wherein the another set of segments are qualified as the 2D detected cartons if the if the processing subsystem determines that the another set of segments are greater than a segment threshold.
12. The robotic carton handling system of claim 11 , wherein in response to determining that the another set of segments are greater than the segment threshold, the processing subsystem:
determines a 2D mask that corresponds to the another set of segments;
determines a portion of the 2D image that corresponds to the 2D mask;
detects the another set of segments within the portion of the 2D image; and
qualifies detected another set of segments as the 2D detected cartons.
13. The robotic carton handling system of claim 9 , wherein:
the sensor is positioned on the robotic carton handling system to detect the one portion of the carton pile;
the robotic carton handling system further comprises another sensors positioned on the robotic carton handling system to detect a contiguous portion of the carton pile; and
the processing subsystem combines the 2D and 3D detected cartons from both the one portion and the contiguous portion to form the detection result.
14. The robotic carton handling system of claim 9 , wherein the processing subsystem qualifies the one or more segments as the 2D detected cartons at least in part by discarding edges that form a smaller rectangle fully encompassed within a larger rectangle.
15. The robotic carton handling system of claim 9 , wherein the processing subsystem is further configured to stitch the 2D image and the 3D point cloud together to obtain an image of the carton pile.
16. The robotic carton handling system of claim 9 , further comprising an automation controller in communication with the processing subsystem, the automation controller causes a robotic carton manipulator to perform one of the loading operation and the unloading operation by the robotic carton handling system using the 3D location.
17. A material handling system comprising:
a robotic carton handling system for unloading cartons in a carton pile, the robotic carton handling system movable across a floor, the robotic carton handling system comprising:
a mobile body;
a movable robotic manipulator attached to the mobile body and comprising an end effector at an end thereof, the end effector configured to unload one or more cartons from the carton pile;
a conveyor mounted on the mobile body configured to receive the one or more cartons from the end effector and to move the one or more cartons towards a rear of the robotic carton handling system;
a carton detection system comprising:
one or more sensors coupled respectively to one of the mobile body and the movable robotic manipulator to provide a two-dimensional (2D) optical image and a three-dimensional (3D) point cloud of at least one portion of carton pile resting on a floor of a transportation carrier;
a processing subsystem in communication with the one or more sensors, the processing subsystem:
detects a set of segments within the 3D point cloud;
detects another set of segments within the 3D point cloud;
qualifies the set of segments as 3D detected cartons and the another set of segments as 2D detected cartons;
combine the 2D and 3D detected canons into a detection result; and
convert the detection result using calibration information into a 3D location for cartons targeted for removal,
an automation controller in communication with the processing subsystem, the automation controller causes a robotic carton manipulator to perform the selected one of the loading operation and the unloading operation by the robotic carton handling system using the 3D location; and
an extendable conveyor system having a proximal end coupled to a stationary conveyor system and a movable distal end positioned proximate to the robotic carton handling system to transfer cartons between the stationary conveyor and the robotic carton handling system.
18. The material handling system of claim 17 , wherein the processing subsystem is further configured to:
receive the 2D image and 3D point cloud from one or more sensors positioned on the robotic carton handling system to detect the one portion of the carton pile;
receive a 2D image and 3D point cloud from another one or more sensors positioned on the robotic carton handling system to detect a contiguous portion of the carton pile; and
combine the 2D and 3D detected cartons from both the one portion and the contiguous portion to form the detection result.
19. The material handling system of claim 17 , where in the processing subsystem is further configured to:
determine a 2D mask that corresponds to the another set of segments;
determine a portion of the 2D image that corresponds to the 2D mask;
detect the another set of segments within the portion of the 2D image; and
quality detected another set of segments as the 2D detected cartons.