-
公开(公告)号:US12299800B2
公开(公告)日:2025-05-13
申请号:US18126900
申请日:2023-03-27
Applicant: NVIDIA Corporation
Inventor: Adithyavairavan Murali , Arsalan Mousavian , Clemens Eppner , Adam Fishman , Dieter Fox
Abstract: One common robotic task is the rearrangement of physical objects situated in an environment. This typically involves a robot manipulator picking up a target object and placing the target object in some target location, such as a shelf, cabinet or cubby, and requires the skills of picking, placing and generating complex collision-free motions, oftentimes in a cluttered environment. The present disclosure provides collision detection for object rearrangement using a three-dimensional (3D) scene representation.
-
公开(公告)号:US20210138655A1
公开(公告)日:2021-05-13
申请号:US16914105
申请日:2020-06-26
Applicant: NVIDIA Corporation
Inventor: Arsalan Mousavian , Clemens Eppner , Dieter Fox
IPC: B25J9/16 , G05B19/402 , G05B19/4155 , B25J13/08 , G06N3/08 , G06T7/50 , G06T7/10 , G06T7/70
Abstract: Apparatuses, systems, and techniques determine a set of grasp poses that would allow a robot to successfully grasp an object that is proximate to at least one additional object. In at least one embodiment, the set of grasp poses is modified based on a determination that at least one of the grasp poses in the set of grasp poses would interfere with at least one additional object that is proximate to the object.
-
公开(公告)号:US11724401B2
公开(公告)日:2023-08-15
申请号:US16914105
申请日:2020-06-26
Applicant: NVIDIA Corporation
Inventor: Arsalan Mousavian , Clemens Eppner , Dieter Fox , Adithyavairavan Murali
IPC: G06K9/00 , B25J9/16 , G05B19/4155 , B25J13/08 , G06N3/08 , G06T7/50 , G06T7/10 , G06T7/70 , G05B19/402
CPC classification number: B25J9/1697 , B25J9/161 , B25J9/1612 , B25J9/1666 , B25J13/08 , G05B19/402 , G05B19/4155 , G06N3/08 , G06T7/10 , G06T7/50 , G06T7/70 , G05B2219/40269 , G06T2207/10028 , G06T2207/20084 , G06T2207/20132 , G06T2207/30244
Abstract: Apparatuses, systems, and techniques determine a set of grasp poses that would allow a robot to successfully grasp an object that is proximate to at least one additional object. In at least one embodiment, the set of grasp poses is modified based on a determination that at least one of the grasp poses in the set of grasp poses would interfere with at least one additional object that is proximate to the object.
-
公开(公告)号:US20240177392A1
公开(公告)日:2024-05-30
申请号:US18126900
申请日:2023-03-27
Applicant: NVIDIA Corporation
Inventor: Adithyavairavan Murali , Arsalan Mousavian , Clemens Eppner , Adam Fishman , Dieter Fox
CPC classification number: G06T15/00 , B25J9/1697 , G06T9/001 , G06T2210/21
Abstract: One common robotic task is the rearrangement of physical objects situated in an environment. This typically involves a robot manipulator picking up a target object and placing the target object in some target location, such as a shelf, cabinet or cubby, and requires the skills of picking, placing and generating complex collision-free motions, oftentimes in a cluttered environment. The present disclosure provides collision detection for object rearrangement using a three-dimensional (3D) scene representation.
-
公开(公告)号:US20240149447A1
公开(公告)日:2024-05-09
申请号:US18243467
申请日:2023-09-07
Applicant: NVIDIA Corporation
Inventor: Albert Wu , Clemens Eppner , Dieter Fox
IPC: B25J9/16
CPC classification number: B25J9/1664 , B25J9/161 , B25J9/163 , B25J9/1653 , B25J9/1671 , B25J9/1697
Abstract: Apparatuses, systems, and techniques to generate a motion plan. In at least one embodiment, a motion plan is generated using a neural network based, at least in part, on a demonstration of a task.
-
公开(公告)号:US20240009851A1
公开(公告)日:2024-01-11
申请号:US18233624
申请日:2023-08-14
Applicant: NVIDIA Corporation
Inventor: Arsalan Mousavian , Clemens Eppner , Dieter Fox , Adithyavairavan Murali
IPC: B25J9/16 , G05B19/4155 , B25J13/08 , G06N3/08 , G06T7/50 , G06T7/10 , G06T7/70 , G05B19/402
CPC classification number: B25J9/1697 , G05B19/4155 , B25J13/08 , B25J9/1612 , B25J9/1666 , B25J9/161 , G06N3/08 , G06T7/50 , G06T7/10 , G06T7/70 , G05B19/402 , G06T2207/30244 , G05B2219/40269 , G06T2207/20084 , G06T2207/10028 , G06T2207/20132
Abstract: Apparatuses, systems, and techniques determine a set of grasp poses that would allow a robot to successfully grasp an object that is proximate to at least one additional object. In at least one embodiment, the set of grasp poses is modified based on a determination that at least one of the grasp poses in the set of grasp poses would interfere with at least one additional object that is proximate to the object.
-
公开(公告)号:US11701771B2
公开(公告)日:2023-07-18
申请号:US16809087
申请日:2020-03-04
Applicant: NVIDIA Corporation
Inventor: Arsalan Mousavian , Clemens Eppner , Dieter Fox
CPC classification number: B25J9/1612 , B25J9/1669 , B25J9/1697 , G06N3/045 , B25J9/161
Abstract: In at least one embodiment, a system determines a set of possible grasp poses that allow a robot to successfully grasp an object by generating a set of potential grasp poses, and then evaluating the performance of each potential grasp pose. In at least one embodiment, the system performs a refinement operation on the grasp poses, and based on an evaluation of the poses, creates an improved set of possible grasps for the object.
-
公开(公告)号:US20220152826A1
公开(公告)日:2022-05-19
申请号:US17199174
申请日:2021-03-11
Applicant: NVIDIA Corporation
Inventor: Michael Danielczuk , Arsalan Mousavian , Clemens Eppner , Dieter Fox
Abstract: Apparatuses, systems, and techniques for determining whether collisions will occur in potential paths of an object within a scene. In at least one embodiment, one or more neural networks determine whether collisions will occur in potential paths of an object within a scene based at least in part on point cloud data of the object and the scene.
-
-
-
-
-
-
-