Modularized home robot
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.
1 . A robot system, including:
a mobile base having:
a platform,
a drive mechanism mounted to the platform,
a housing,
two or more sensors rigidly coupled to the platform and directed outwardly from the platform to detect obstacles present,
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 an electrical connector of the coupling mechanism; and
a controller including one or more processors coupled to a memory storing instructions that when executed by the processor perform:
sensing the at most one modularized component coupled via the coupling mechanism as a sensed modularized component of the plurality of modularized components coupled via the electrical connector;
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 upon inputs of (i) the two or more sensors rigidly coupled to the platform and (ii) one or more sensors of the sensed modularized component.
2 . The robot system of claim 1 , wherein at least one of the two or more sensors includes a camera, the robot system further including:
one or more gaps in the housing which light can pass through to the camera.
3 . The robot system of claim 2 , wherein the camera is at least one selected from an infrared (IR) camera, a visible light (Red-Green-Blue, RGB) sensing camera, and a time of flight camera.
4 . The robot system of claim 2 , further including a second camera positioned relative to the camera of the at least one of the two or more sensors to form a pair of cameras capable of stereoscopic imaging.
5 . The robot system of claim 1 , further including a third sensor, wherein three sensors positioned approximately 120 degrees apart from one another around directed outward from a center of the platform; thereby providing sensory input around the robot system substantially contemporaneously.
6 . The robot system of claim 1 , further including:
a microphone and a speaker configured to collect audio and speech from users for input to the neural network classifier and output audio and speech from the neural network classifier respectively, and wherein at least some input and output are received from or transmitted to applications and devices via the wireless network.
7 . The robot system of claim 1 , wherein the platform is substantially round.
8 . The robot system of claim 1 , wherein the platform is approximately triangular.
9 . The robot system of claim 1 , wherein the platform is approximately quadrilateral.
10 . The robot system of claim 1 , wherein the elderly care modularized component has an adjustable height handle, and when coupled to the mobile base, enables an elderly person to hold the elderly care modularized component while the robot system, under control of instructions based upon output from the neural network classifier corresponding to the elderly care modularized component, guides the elderly person.
11 . The robot system of claim 10 , further including a medication dispenser and a monitor for dispensing medication to the elderly person and monitoring that the elderly person has taken their medication.
12 . The robot system of claim 1 , wherein the entertainment modularized component has a projection mechanism, and when coupled to the mobile base and controlled by the controller under control of instructions based upon output from the neural network classifier, the entertainment modularized component projects an augmented reality presentation, senses bodily motions of users, and reflects sensed bodily motions in changes to the augmented reality presentation.
13 . The robot system of claim 12 , further including projecting presentations selected from a set comprising of games, movies, educational activities, and entertainment activities.
14 . The robot system of claim 1 , wherein the environment modularized component has an air quality sensor, a humidification system and a purification system, and when coupled to the mobile base and controlled by the controller under control of instructions based upon output from the neural network classifier corresponding to the environment modularized component, senses air quality parameters including humidity and pollution, activates the humidification system when humidity sensed is outside a settable level, and activates the purification system when pollution sensed is outside a settable level.
15 . The robot system of claim 14 , further including the robot system under control of instructions based upon output from the neural network classifier travelling from room to room substantially contemporaneously with sensing air quality, activating the humidification system when humidity sensed is outside a settable level and activating the purification system when pollution sensed is outside a settable level.
16 . The robot system of claim 1 , wherein the pet sitter modularized component has a pet food dispenser to dispense food and a pet toy launcher to launch a toy, and when coupled to the mobile base and controlled by the controller under control of instructions based upon output from the neural network classifier, administers food to a pet and launches a toy into space to entertain the pet.
17 . The robot system of claim 16 , further including tracking position and motions of the pet.
18 . A method of configuring a home robot, the method including:
sensing at most one sensed modularized component from 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, and wherein the at most one sensed modularized component is coupled with the home robot via a coupling connector;
controlling (i) the home robot 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 corresponding to the at most one sensed modularized component, including triggering a drive mechanism of the home robot, obtaining information from two or more sensors to detect obstacles present, and sending and receiving information using a wireless network, based upon inputs of one or more sensors of the at most one sensed modularized component.
19 . 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:
sensing at most one sensed modularized component from 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, and wherein the at most one sensed modularized component is coupled with the home robot via a coupling connector;
controlling (i) the home robot and (ii) the sensed modularized component using a trained neural network classifier from a plurality of trained neural network classifiers, the trained neural network classifier corresponding to the sensed modularized component, wherein each trained neural network classifier of the plurality of trained 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 trained neural network classifier corresponding to the at most one sensed modularized component, including triggering a drive mechanism of the home robot, obtaining information from two or more sensors to detect obstacles present, and sending and receiving information using a wireless network, based upon inputs of one or more sensors of the at most one sensed modularized component.
20 . The non-transitory computer readable medium of claim 19 , wherein each modularized component of the plurality of modularized components when coupled with a robot base implements a different robot configuration from a set of mutually exclusive possible robot configurations.