A computer-implemented method includes recording, with a three-dimensional camera, one or more demonstrations of a user performing one or more reaching tasks. Training data is computed to describe the one or more demonstrations. One or more weights of a neural network are learned based on the training data, where the neural network is configured to estimate a goal location of the one or more reaching tasks. A partial trajectory of a new reaching task is recorded. An estimated goal location is computed, by a computer processor, by applying the neural network to the partial trajectory of the new reaching task.

A robot for outputting various reactions according to user behaviors is disclosed. A control method for a robot using an artificial intelligence model, according to the present disclosure, comprises the steps of: acquiring data related to at least one user; inputting the data related to the at least one user into the artificial intelligence model as learning data so as to learn a user state for each user of which there is at least one; determining representative reactions corresponding to the user states learned on the basis of the data related to the at least one user; and inputting the input data into the artificial intelligence model so as to determine a user state of a first user and controlling the robot on the basis of a representative reaction corresponding to the determined user state, when input data related to the first user among the users, of which there is a least one, is acquired.

An information technology system generally includes a cloud-based management platform with a micro-services architecture having a set of microservices layers including an application layer supporting at least one supply chain application and at least one demand management application. The microservices layers can include a data collection layer that can collect information from a set of Internet of Things resources that collect information with respect to supply chain entities and demand management entities related to the value chain network entities of the platform.

An information technology system generally includes a cloud-based management platform with a micro-services architecture deploying a set of adaptive intelligence facilities that can be configured to automate a set of capabilities of the platform related to at least one of the value chain network entities and the features of the platform and a set of data storage facilities that can be configured to store data collected and handled by the platform. The data can be related to at least one of the value chain network entities and the features of the platform. A set of monitoring facilities can be configured to monitor the value chain network entities. The platform can be configured to host a set of applications for directing an enterprise to manage the value chain network entities from a point of origin of a product of the enterprise to a point of customer use.

A device and method for human intention detection Sensor Band (HID). In preferred embodiments, it makes use of an array of force sensing resistors (FSRs) which are embedded inside a flexible band, which is capable of reading the muscle activity for different motion type and muscle forcein a human user. In one implementation of the invention two of such bands are attached to the forearm and the upper arm. From the readings of the sensors, the patterns for motion type and muscle force are then distinguished autonomously by machine learning, a Support Vector Machine (SVM) algorithm, or a neural network. The method is advantageous e.g. the detection of dexterous motion of the arms, upon which assistive exoskeleton can be controlled for motion assistance. The invention can also be applicable to hand gestures recognition and bilateral rehabilitation, besides this the invention can be used to control lower body exoskeleton as well.

Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

A robot for outputting various reactions according to user behaviors is disclosed. A control method for a robot using an artificial intelligence model, according to the present disclosure, comprises the steps of: acquiring data related to at least one user; inputting the data related to the at least one user into the artificial intelligence model as learning data so as to learn a user state for each user of which there is at least one; determining representative reactions corresponding to the user states learned on the basis of the data related to the at least one user; and inputting the input data into the artificial intelligence model so as to determine a user state of a first user and controlling the robot on the basis of a representative reaction corresponding to the determined user state, when input data related to the first user among the users, of which there is a least one, is acquired.

A robot training method under a virtual environment includes receiving voice signals; and controlling a robot in the virtual environment in response to the received voice signals. The voice signals include a training time signal and a training program signal. Prior to training a user may select training time of a desired training program by pronouncing a voice. The user may change the training time of the desired training program. The user may select an optimum training time based on schedule. A robot training method under the virtual environment is also provided.

Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

This disclosure pertains to machine object determination based on human interaction. In general, a device such as a robot may be capable of interacting with a person (e.g., user) to select an object. The user may identify the target object for the device, which may determine whether the target object is known. If the device determines that target object is known, the device may confirm the target object to the user. If the device determines that the target object is not known, the device may then determine a group of characteristics for use in determining the object from potential target objects, and may select a characteristic that most substantially reduces a number of potential target objects. After the characteristic is determined, the device may formulate an inquiry to the user utilizing the characteristic. Characteristics may be selected until the device determines the target object and confirms it to the user.