Runtime assessment of suction grasp feasibility
AssigneeSiemens Aktiengesellschaft
InventorsYash Shahapurkar, William Yamada, Eugen Solowjow, Gokul Narayanan Sathya Narayanan
Life of this patent
Estimating the term…
Abstract
An autonomous system can detect out-of-distribution (OOD) data in robotic grasping systems, based on evaluating image inputs of the robotic grasping systems. Furthermore, the system makes various decisions based on detecting the OOD data, so as to avoid inefficient or hazardous situations or other negative consequences (e.g., damage to products). For example, the system can determine whether a suction-based gripper is optimal for grasping objects in a given scene, based at least in part on determining whether an image defines OOD data.
Claims15
An autonomous system configured to operate in an active industrial environment so as to define a runtime, the autonomous system comprising:
- a robot defining an end effector configured to grasp a plurality of objects within a container, the end effector defining a suction-based gripper or a finger-based gripper;
- a camera configured to capture an image of the container containing the plurality of objects, so as to define a captured image;
- one or more processors;
- and
- a memory storing instructions that, when executed by the one or more processors, cause the autonomous system to, during the runtime:
- based on the captured image, make a determination as to whether the plurality of objects define a structured scene or a disordered scene;
- at least partially based on the determination, select the suction-based gripper or the finger-based gripper for grasping the plurality of objects, so as to define a selected gripper;
- and
- instruct the robot to grasp the plurality of objects with the selected gripper.
A method performing by an autonomous system including a robot configured to grasp objects from containers with a suction-based gripper or a finger based-gripper, the method comprising:
- capturing an image of a container containing a plurality of objects, so as to define a captured image;
- based on the captured image, making a determination as to whether the plurality of objects define a structured scene or a disordered scene;
- at least partially based on the determination, selecting the suction-based gripper or the finger-based gripper for grasping the plurality of objects, so as to define a selected gripper;
- and
- instructing the robot to grasp the plurality of objects with the selected gripper.
Dependencies are inferred from the claim text.