A refrigerator comprises a storage compartment configured to store food, a temperature detector configured to detect an internal temperature of the storage compartment, a cooler configured to supply cool air to the storage compartment, a microphone configured to receive a speech, a display configured to display information, at least one processor configured to be electrically connected to the temperature detector, the microphone, and the display; and a memory configured to be electrically connected to the at least one processor. The memory stores at least one instructions configured to, when a first speech including a food name is recognized via the microphone, allow the processor to display a food list, which comprises food information corresponding to the food name and an identification mark identifying the food information, on the display, and configured to, when a second speech referring to the identification mark is recognized via the microphone, allow the processor to display food purchase information corresponding to the identification mark, on the display.

An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; identifying, based on the utterance, a task to be performed by the computational assistant; responsive to determining, by the computational assistant, that complete performance of the task will take more than a threshold amount of time, outputting, for playback by one or more speakers operably connected to the computing device, synthesized voice data that informs a user of the computing device that complete performance of the task will not be immediate; and performing, by the computational assistant, the task.

A computer-implemented system and method for storing data associated with an agent in a multi-dimensional environment via a memory architecture. The memory architecture is structured so that each unique position in the environment corresponds to a unique position within the memory architecture, thereby allowing the memory architecture to store features located at a particular position in the environment in a memory location specific to that location. As the agent traverses the environment, the agent compares the features at the agent's particular position to a summary of the features stored throughout the memory architecture and writes the features that correspond to the summary to the coordinates in the memory architecture that correspond to the agent's position. The system and method allows agents to learn, using a reinforcement signal, how to behave when acting in an environment that requires storing information over long time steps.

Embodiments of the present disclosure are directed to a method and an apparatus for generating training data for a visual question answering (VQA) system, and a computer readable medium. The method for generating training data for a visual question answering system includes: obtaining a first set of training data of the visual question answering system, the first set of training data comprising a first question for an image in the visual question answering system and a first answer corresponding to the first question; obtaining information related to the image; generating a second question corresponding to the first answer based on the information to obtain a second set of training data for the image in the visual question answering system, the second set of training data comprising the second question and the first answer.

An automated robot design pipeline facilitates the overall process of designing robots that perform various desired behaviors. The disclosed pipeline includes four stages. In the first stage, a generative engine samples a design space to generate a large number of robot designs. In the second stage, a metric engine generates behavioral metrics indicating a degree to which each robot design performs the desired behaviors. In the third stage, a mapping engine generates a behavior predictor that can predict the behavioral metrics for any given robot design. In the fourth stage, a design engine generates a graphical user interface (GUI) that guides the user in performing behavior-driven design of a robot. One advantage of the disclosed approach is that the user need not have specialized skills in either graphic design or programming to generate designs for robots that perform specific behaviors or express various emotions.

Automated training dataset generators that generate feature training datasets for use in real-world autonomous driving applications based on virtual environments are disclosed herein. The feature training datasets may be associated with training a machine learning model to control real-world autonomous vehicles. In some embodiments, an occupancy grid generator is used to generate an occupancy grid indicative of an environment of an autonomous vehicle from an imaging scene that depicts the environment. The occupancy grid is used to control the vehicle as the vehicle moves through the environment. In further embodiments, a sensor parameter optimizer may determine parameter settings for use by real-world sensors in autonomous driving applications. The sensor parameter optimizer may determine, based on operation of the autonomous vehicle, an optimal parameter setting of the parameter setting where the optimal parameter setting may be applied to a real-world sensor associated with real-world autonomous driving applications.

An optimal control method for wastewater treatment process (WWTP) based on a self-adjusting multi-task particle swarm optimization (SA-MTPSO) algorithm belongs to the field of WWTP. To balance the relationship between the effluent water quality (EQ) and energy consumption (EC) and achieve optimization online quickly, the invention establishes a data-based multi-task optimization model for WWTP to describe the relationship between the control variables and EQ, EC. Then, the SA-MTPSO algorithm is adopted to solve the optimal set-points of the nitrate nitrogen and dissolved oxygen concentration for WWTP. The PID controller is used to track the optimal set-points, so as to reduce EC while ensuring EQ, and realize the online optimal control of WWTP.

This invention relates generally to a software-enabled, computer-implemented neural processing system for a non-player character (NPC) in a computer-enabled virtual environment. The system includes a plurality of virtual sensors configured to detect one or more virtual stimuli presented by the virtual environment to the NPC and present corresponding stimuli detection signals in response to the one or more virtual stimuli. The neural processing system may also include a virtual neo cortex, which may include a plurality of processing modules that are each configured to process stimuli detection signals output from the plurality of virtual sensors. The neural processing system also may include a virtual thalamus module configured to receive the stimuli detection signals and transmit the stimuli detection signals to the appropriate processing modules of the virtual neo cortex.

A neural network method, comprising: modeling an environment; implementing a policy based on the modeled environment, to perform an action by an agent within the environment, having at least one estimated dynamic parameter; receiving an observation and a temporally-associated cost or reward based on operation of the agent in the environment controlled according to the policy; and updating the policy, dependent on the received observation and the temporally-associated cost or reward, to improve the policy to optimize an expected future cumulative cost or reward. The policy may represent a set of parameters defining an artificial neural network having a plurality of hierarchical layers and having at least one layer which receives inputs representing aspects of the received observation indirectly from other neurons, and produce outputs to other neurons which indirectly implement the policy, the plurality of hierarchical layers being trained according to respectfully distinct training criteria.

The present invention provides a robot control method, and the method includes: collecting interaction information of a companion target, and obtaining digital person information of a companion person (101), where the interaction information includes interaction information of a sound or an action of the companion target toward the robot, and the digital person information includes a set of digitized information of the companion person; and determining, by using the interaction information and the digital person information, a manner of interacting with the companion target (103); generating, based on the digital person information of the companion person and by using a machine learning algorithm, an interaction content corresponding to the interaction manner (105); and generating a response action toward the companion target based on the interaction manner and the interaction content (107).