Dynamic learning method and system for robot, robot and cloud server
AssigneeCloudminds (Shenzhen) Robotics Systems Co., Ltd.
InventorZhanchao ZHANG
Life of this patent
Estimating the term…
Abstract
A dynamic learning method for a robot includes a training and learning mode. The training and learning mode includes the following steps: dynamically annotating a belonging and use relationship between an object and a person in a three-dimensional environment to generate an annotation library; acquiring a rule library, and establishing a new rule and a new annotation by means of an interactive demonstration behavior based on the rule library and the annotation library; and updating the new rule to the rule library and updating the new annotation to the annotation library when it is determined that the established new rule is not in conflict with rules in the rule library and the new annotation is not in conflict with annotations in the annotation library.
Claims12
A dynamic learning method for a robot, comprising a training and learning mode;
- wherein the training and learning mode comprises the following steps:
- dynamically annotating a belonging and use relationship between an object and a person in a three-dimensional environment to generate an annotation library;
- acquiring a rule library, and establishing a new rule and a new annotation by means of an interactive demonstration behavior based on the rule library and the annotation library;
- and
- updating the new rule to the rule library when it is determined that the established new rule is not in conflict with rules in the rule library.
A robot for dynamic learning, comprising a training and learning module, the training and learning module comprising a dynamic annotating module, an acquiring module, a rule updating module and a task performing module;
- wherein
- the dynamic annotating module is configured to dynamic annotate a belonging and use relationship between an object and a person in a three-dimensional environment, and store the belonging and use relationship to an annotation library;
- the acquiring module is configured to acquire a rule library;
- the rule updating module is configured to establish a new rule by means of an interactive demonstration behavior based on the rule library and the annotation library, and store the new rule to the rule library;
- the dynamic annotating module is further configured to establish a new annotation by means of the interactive demonstration behavior based on the rule library and the annotation library, and store the new annotation to the annotation library;
- and
- the task performing module is configured to complete a task and an interaction designated by a user based on the annotation library and the rule library.
A cloud server, comprising a storing module, a receiving module and a determining module;
- wherein
- the storing module is configured to store annotations generated when a robot dynamic annotates a belonging and use relationship between an object and a person in a three-dimensional environment to generate an annotation library;
- the storing module is further configured to store a rule library of the robot;
- the receiving module is configured to receive a new rule established by the robot by means of an interactive demonstration behavior based on the rule library and the annotation library;
- the receiving module is further configured to receive a new annotation established by the robot by means of an interactive demonstration behavior based on the rule library and the annotation library;
- and
- the determining module is configured to determine whether the new rule and the rules in the rule library, and the new annotation and the annotations in the annotation library are subjected to a conflict, and update the new rule to the rule library and update the new annotation to the annotation library when no conflict is existent.
Dependencies are inferred from the claim text.