Back to results
US 2026/0307239 A1Published application
Modularized home robot
AssigneeTrifo, Inc.
InventorsZhe ZHANG, Zhongwei LI
Life of this patent
Estimating the term…
Abstract
Implementations of a fully configurable, modularized home robot are described that implement trained neural network classifiers to solve problems of providing home health care and monitoring of the elderly and/or infirm, providing entertainment for the family, providing environmental and safety monitoring coupled with mechanisms to clean the air and remedy indoor climates such as humidity and temperature, and provide a mechanism for caring for pets left at home when the owner is away based upon sensory input.
Claims20
A robot system, including:
- a mobile base having:
- a platform,
- a drive mechanism mounted to the platform,
- a housing,
- two or more sensors coupled to the platform and directed outwardly from the platform,
- a communications interface to send and receive information using a wireless network,
- a plurality of modularized components, wherein each modularized component of the plurality of modularized components implements a specific functionality, and wherein the plurality of modularized components includes an elderly care modularized component, an entertainment modularized component, an environment modularized component, and a pet sitter modularized component;
- a coupling mechanism to accept at most one modularized component of the plurality of modularized components, wherein each modularized component of the plurality of modularized components is interchangeably couplable with the coupling mechanism;
- and
- a controller including one or more processors coupled to a memory storing instructions that when executed by the one or more processors perform:
- sensing the at most one modularized component coupled via the coupling mechanism as a sensed modularized component of the plurality of modularized components;
- controlling (i) the mobile base and (ii) the sensed modularized component using a neural network classifier from a plurality of neural network classifiers, the neural network classifier corresponding to the sensed modularized component, wherein each neural network classifier of the plurality of neural network classifiers is trained to control a corresponding modularized component of the plurality of modularized components;
- and
- initiating robot behaviors triggered by outputs of the neural network classifier, based, at least in part, upon inputs of (i) the two or more sensors coupled to the platform and (ii) one or more sensors of the sensed modularized component.
11 more elements
A method of configuring a home robot, the method including:
- receiving, at a robot base that comprises a controller, a communications interface configured to send and receive information via a wireless network, and configured to accept a modularized component, sensor data and one or more signals from a modularized component coupled to the robot base;
- detecting attachment or presence of the modularized component based, at least in part, upon reception of (i) one or more signals from the modularized component or (ii) sensor data from one or more sensors indicative of presence of the modularized component;
- establishing a data communication between the robot base and the coupled modularized component;
- storing, in non-transitory memory, a plurality of neural network classifiers;
- identifying a component type of the coupled modularized component based, at least in part, upon at least one of the sensor data or the one or more signals received from the modularized component;
- selecting, from the plurality of neural network classifiers, a selected neural network classifier appropriate to the identified component type;
- processing, by the controller, the sensor data and one or more signals from the modularized component based, at least in part, upon the selected neural network classifier to produce an output;
- and
- at least initiating a robot behavior based, at least in part, upon the output of the selected neural network classifier.
6 more elements
A non-transitory computer readable medium, storing instructions for configuring a home robot, which instructions, when executed by one or more processors perform tasks including:
- receiving, at a robot base that comprises a controller, a communications interface configured to send and receive information via a wireless network, and configured to accept a modularized component, sensor data and one or more signals from a modularized component coupled to the robot base;
- detecting attachment or presence of the modularized component based, at least in part, upon reception of (i) one or more signals from the modularized component or (ii) sensor data from one or more sensors indicative of presence of the modularized component;
- establishing a data communication between the robot base and the coupled modularized component;
- storing, in non-transitory memory, a plurality of neural network classifiers;
- identifying a component type of the coupled modularized component based, at least in part, upon at least one of the sensor data or the one or more signals received from the modularized component;
- selecting, from the plurality of neural network classifiers, a selected neural network classifier appropriate to the identified component type;
- processing, by the controller, the sensor data received from the modularized component based, at least in part, upon the selected neural network classifier to produce an output;
- and
- at least initiating a robot behavior based, at least in part, upon the output of the selected neural network classifier.
6 more elements
Dependencies are inferred from the claim text.