Machine learning model for task and motion planning
AssigneeNVIDIA Corporation
InventorsYuke Zhu, Yifeng Zhu, Stanley Thomas Birchfield, Jonathan Tremblay
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques are described that solve task and motion planning problems. In at least one embodiment, a task and motion planning problem is modeled using a geometric scene graph that records positions and orientations of objects within a playfield, and a symbolic scene graph that represents states of objects within context of a task to be solved. In at least one embodiment, task planning is performed using symbolic scene graph, and motion planning is performed using a geometric scene graph.
Claims37
One or more processors comprising:
- circuitry to cause one or more autonomous devices to perform one or more tasks within a physical environment by at least repeatedly causing one or more neural networks to use position and state information of the one or more autonomous devices to infer a subsequent sub-task of the one or more tasks based, at least in part, on one or more previous sub-tasks performed by the one or more autonomous devices and one or more changes within the physical environment.
A system comprising:
- one or more processors and computer-readable memory storing executable instructions that, as a result of being executed by the one or more processors, cause the system to cause one or more autonomous devices to perform one or more tasks within a physical environment by at least repeatedly causing one or more neural networks to use position and state information of the one or more autonomous devices to infer a subsequent sub-task of the one or more tasks based, at least in part, on one or more previous sub-tasks performed by the one or more autonomous devices and one or more changes within the physical environment.
A method comprising:
- causing one or more autonomous devices to perform one or more tasks within a physical environment by at least repeatedly causing one or more neural networks to use position and state information of the one or more autonomous devices to infer a subsequent sub-task of the one or more tasks based, at least in part, on one or more previous sub-tasks performed by the one or more autonomous devices and one or more changes within the physical environment.
A non-transitory computer-readable storage medium having stored thereon executable instructions that, as a result of being executed by one or more processors, cause a computer system to cause one or more autonomous devices to perform one or more tasks within a physical environment by at least repeatedly causing one or more neural networks to use position and state information of the one or more autonomous devices to infer a subsequent sub-task of the one or more tasks based, at least in part, on one or more previous sub-tasks performed by the one or more autonomous devices and one or more changes within the physical environment.
An autonomous device comprising:
- one or more processors;
- and
- non-transitory computer-readable storage medium having stored thereon executable instructions that, as a result of being executed by the one or more processors, cause the autonomous device to cause one or more autonomous devices to perform one or more tasks within a physical environment by at least repeatedly causing one or more neural networks to use position and state information of the one or more autonomous devices to infer a subsequent sub-task of the one or more tasks based, at least in part, on one or more previous sub-tasks performed by the one or more autonomous devices and one or more changes within the physical environment.
Dependencies are inferred from the claim text.