Task execution method, apparatus, robot, and product
AssigneeBeijing Youzhuju Network Technology Co., Ltd.
InventorWei LI
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to a task execution method, an apparatus, a robot, and a computer program product. The method is applicable to an intelligent robot. The method includes obtaining a user instruction represented in a natural language, wherein the user instruction indicates an object to be grasped by the intelligent robot; generating, using a language model and based on the user instruction, a movement instruction indicating a position at which the object is located, to cause the intelligent robot to move to the position; obtaining an image obtained at the position; and generating, based on the image, a grasping instruction to cause the intelligent robot to grasp the object.
Claims20
A task execution method, applicable to a robotic system, and comprising:
- obtaining an instruction represented in a natural language, the instruction indicating an object to be grasped;
- generating a movement instruction using a model based on the instruction and moving to the position, the movement instruction indicating a position at which the object is located;
- obtaining an image obtained at the position;
- and
- generating a grasping instruction based on the image and grasping the object.
A robotic system, comprising:
- a processor;
- and
- a memory coupled to the processor, the memory having instructions stored thereon, the instructions, when executed by the processor, causing the robotic system to:
- obtain an instruction represented in a natural language, the instruction indicating an object to be grasped;
- generate a movement instruction using a model based on the instruction and move to the position, the movement instruction indicating a position at which the object is located;
- obtain an image obtained at the position;
- and
- generate a grasping instruction based on the image and grasping the object.
A computer program product, tangibly stored on a non-transitory computer-readable medium and comprising machine-executable instructions, the machine-executable instructions, when executed by a machine, causing the machine to:
- obtain an instruction represented in a natural language, the instruction indicating an object to be grasped;
- generate a movement instruction using a model based on the instruction and move to the position, the movement instruction indicating a position at which the object is located;
- obtain an image obtained at the position;
- and
- generate a grasping instruction based on the image and grasping the object.
Dependencies are inferred from the claim text.