75 results about "Autonomous agent" patented technology

The present invention provides a generic distributed command, control, and communication framework that allows computer systems, devices, and operational personnel to interact with the network as a unified entity. The present invention provides these services by building upon a core communication architecture that permits local or remote execution of mobile program code, static execution of program code, flexible communication formats, self-healing network techniques, and expansion by the addition of new system modules, software handlers, or mobile autonomous agents.

A distributed data processing system employing negotiation among autonomous agents for allocation of resources is presented herein. The system includes a communications network for passing messages between computers connected thereto, a plurality of computers connected to the network for running programs thereon including at least first and second autonomous agents. Each agent receives a graph associated therewith and wherein the graph represents for the associated agent what resources that agent has and what task or tasks that agent may perform. Each agent employs the associated graph to determine what resource or resources are needed by that agent to carry out the task or tasks to be performed by that agent. The agents negotiate with each other for the resources needed to carry out the task or tasks to be performed by the agents.

A system for supplying network content to a device. The system includes a first interface for communicating with a network content source for retrieving the network content. The system also includes a second interface for communicating with the device for delivering processed network content to the device. The system includes an agent framework operatively connected to the first interface and the second interface and which operates a plurality of autonomous agents including a content retrieval agent, a content personalization agent, and a content delivery agent. The content retrieval agent is for retrieving the network content from the network content source via the first interface. The content personalization agent is for processing the network content thereby producing the processed network content. The content delivery agent is for delivering the processed network content to the device via the second interface.

A computer system (61) is provided herein which comprises a network (62) having a plurality of devices (63, 65, 69, 71) connected thereto, and an agent (77) installed on each of the devices. Each agent is adapted to monitor the state of the device it is installed on and to perform actions in accordance with a set of predefined rules in an attempt to achieve a set of predefined goals.

A computer system and method according to the present invention can receive multi-modal inputs such as natural language, gesture, text, sketch and other inputs in order to simplify and improve locative question answering in virtual worlds, among other tasks. The components of an agent as provided in accordance with one embodiment of the present invention can include one or more sensors, actuators, and cognition elements, such as interpreters, executive function elements, working memory, long term memory and reasoners for responses to locative queries, for example. Further, the present invention provides, in part, a locative question answering algorithm, along with the command structure, vocabulary, and the dialog that an agent is designed to support in accordance with various embodiments of the present invention.

The urban public transport management provides technical support for the improvement of policy making and transport management efficiency. Therefore, the technical scheme of the invention is that the platform is formed by large-scale autonomous Agent loose coupling, thereby forming an MAS (Multi-Agent System). A commuter Agent represents a resident who needs to go out on duty at a morning peak. A basic mode of the platform is to measure the commuting cost after commuting when a person takes a bus to a working area for work in each simulation day, and to update an experience database and knowledge. The platform is mainly used for public transport management.

A miniature autonomous apparatus for performing scene interpretation, comprising: image acquisition means, image processing means, memory means and communication means, the processing means comprising means for determining an initial parametric representation of the scene; means for updating the parametric representation according to predefined criteria; means for analyzing the image, comprising means for determining, for each pixel of the image, whether it is a hot pixel, according to predefined criteria; means for defining at least one target from the hot pixels; means for measuring predefined parameters for at least one target; and means for determining, for at least one target whether said target is of interest, according to application-specific criteria, and wherein said communication means are adapted to output the results of said analysis.

A method for operating a host layer of a distributed computing system on a wide area network includes attaching an autonomous agent to a client-requested carrier, such as web content. The method includes the steps of receiving a request for specified content from a client node via the wide area network, and sending the content and an embedded agent to the client via the wide area network. The agent has program instructions configured to execute autonomously on the client node to perform a processing function. The processing function is configured to operate on raw data to produce process data, according to instructions determined by a solution algorithm of the distributed computing system. The method further includes sending the raw data to the client node and receiving the process data from the client node as it is processed by the agent. The host layer may comprise a web server hosting a web site containing consumer-oriented web pages, and the carrier may comprise an HTML page containing user content. The agent may comprise a web page-enabled application embedded in the HTML page, such as a Java™ applet.

A technique for consistently simulating at two different complexities of simulation is described. This technique is particularly relevant to simulation of a creature-like autonomous agent (biological or artificial or hybrid). The model, in the particular case a model of the creature, comprises at least two portions. The first portion contains functions used in both of the different complexities of simulation. The second portion comprises two alternative versions, a first version for use in one complexity of simulation, and a second version for use in the other complexity of simulation.

A Grid application framework uses semantic languages to describe the tasks and resources used to complete them. A Grid application execution framework comprises a plurality of mobile agents operable to execute one or more tasks described in an intent based task specification language; VO circuitry operable to receive input that describes a task in the task specification language; an analysis engine for generating a solution to the described task; and an intent knowledge base operable to store information contained within tasks of the plurality of mobile agents

Systems and methods for intelligently implementing an autonomous agent include: implementing a computer-based control circuit that generates computer-based control signals for controlling a driving operation of an autonomous agent; enabling a non-computer control source that provides non-computer-based control signals for controlling the operation of the autonomous agent; implementing a dedicated arbiter circuit that selectively passes control signals from either the computer-based control circuit or the non-computer control source to lower-level driving mechanisms; and implementing a takeover circuit that source s a takeover signal to the dedicated arbiter circuit based on detecting non-computer-based control signals having non-nominal control values from the non-computer control source, wherein in response to the takeover signal, the dedicated arbiter circuit dynamically switches from passing the computer-based control signals from the computer-based control circuit to passing non-computer-based control signals from the non-computer control source for controlling the lower-level driving mechanisms of the autonomous agent.

A learning control apparatus for an autonomous agent including a functional module having a function of multiple inputs and multiple outputs, the function receiving at least one variable and outputting at least one value, includes an estimating unit for estimating a causal relationship of at least one variable, a grouping unit for grouping at least one variable into a variable group in accordance with the estimated causal relationship, a determining for determining a behavior variable corresponding to each of the variable groups, and a layering unit for layering, in accordance with the variable group and the behavior variable, the function corresponding to each variable group, the function receiving the variable grouped into the variable group and outputting the behavior variable.

A computer-based system for dynamic assignment of carrier frequencies to computerized access points of a wireless local area network (WLA) is connected to the access points via a communication connection. Present operational values, such as the present number of associated users and the present number of received faulty and errorless data packets, are captured from the access points via the communication connection by autonomous agent modules of the computer-based system. In the computer-based system, individual weighting factors for the access points are calculated, based on the captured operational values. Access point data about the access points, which include present carrier frequencies and weighting factors, are stored in the computer-based system. Based on the stored access point data, optimal carrier frequencies, or respectively radio frequency channels, are determined in the computer-based system to reduce instances of interference between the access points, and are set in the access points via the communication connection. Optimal carrier frequencies, or respectively radio frequency channels, can thus be determined and set in the access points without resources of the local mobile radio network having to be used for this purpose and without changes having to be made at the access points.

Systems and methods for improving question-answering recall for complex, multi-sentence, convergent questions. More specifically, an autonomous agent accesses an initial answer that partly answers a question received from a user device. The agent represents the question and the initial answer as discourse trees. From the discourse trees, the agent identifies entities in the question that are not addressed by the answer. The agent forms an additional discourse tree from an additional resource such as a corpus of text. The additional discourse tree rhetorically connects a non-addressed entity with the answer. The agent designates this discourse tree as an imaginary discourse tree. When combined with the initial answer discourse tree, the imaginary discourse tree is used to generate an improved answer relative to existing solutions.

Methods and systems for the evolution of electronic neural assemblies toward directed goals. A compact computing architecture includes electronics that allows users of such an architecture to create autonomous agents, in a real or a virtual world and add intelligence to machines. An intelligent machine is composed of four basic modules: one or more sensors, one or more motors, a (Reward Input Output System) RIOS, and a cortex. A number of genetically evolved detectors can project both to cortex and RIOS. At first the neurons within the cortex evolve to predict the structure of the sensory data followed by the structure of proprioceptive activations of its own motor system. Finally, once the cortex has learned its sensory and motor programs, it evolves to predict the reward signals, which comes in multiple channels but is dominated by the detection of the aquisition of free-energy.

A miniature autonomous apparatus for performing scene interpretation, comprising: image acquisition means, image processing means, memory means and communication means, the processing means comprising means for determining an initial parametric representation of the scene; means for updating the parametric representation according to predefined criteria; means for analyzing the image, comprising means for determining, for each pixel of the image, whether it is a hot pixel, according to predefined criteria; means for defining at least one target from the hot pixels; means for measuring predefined parameters for at least one target; and means for determining, for at least one target whether said target is of interest, according to application-specific criteria, and wherein said communication means are adapted to output the results of said analysis.

Systems, devices, and methods of the present invention relate to text classification. A text classification system accesses an utterance of text. The utterance includes at least one word. The text classification system generates a parse tree for the utterance. The parse tree includes at least one terminal node with a word type. The terminal node represents a word of the utterance. The text classification system applies one or more rules to the text. The text classification system then classifies the utterance as a question or a request for an autonomous agent to perform an action.

Techniques for computer-generated conversation are disclosed. In an example, a method identifies text postings from a conversation. The method creates, for each text fragment of each text posting, a syntactic tree and a discourse tree. The method creates parse thickets, each parse thicket including the syntactic tree and discourse tree of a unique pair of text postings. The method extracts, from each parse thicket, a common text segment and obtains a set of candidate search results by providing the common text segments to a search engine. The candidate search results can be further refined for relevancy and mental state and posted as a response to a conversation.

The technology described herein is directed to a system that quickly and efficiently transmits photographs from a camera to one or more computing devices. The link for such a transmission is easily and automatically configured. Once the photographs are stored in the one or more computing devices, they can be submitted to a photograph management system that facilitates distribution of the photographs as well as collaboration with other individuals or autonomous agents for editing and re-editing of photographs.

In a computer network including a plurality of network elements, a network management architecture including a plurality of agents, each of the agents corresponding to a different one of the network elements, and a plurality of device components, each of the device components modeling at least one aspect of one of the network elements, the aspect being either of a physical and a functional characteristic of the network element, where each of the agents includes a plurality of the device components, and where at least of the two device components within at least one of the agents are logically interconnected, each logical interconnection corresponding to either of a physical and a functional interconnection found within or between any of the network elements.

The technology described herein is directed to a system that quickly and efficiently transmits photographs from a camera to one or more computing devices. The link for such a transmission is easily and automatically configured. Once the photographs are stored in the one or more computing devices, they can be submitted to a photograph management system that facilitates distribution of the photographs as well as collaboration with other individuals or autonomous agents for editing and re-editing of photographs.

Systems, devices, and methods of the present invention relate to text classification. A text classification system accesses an utterance of text. The utterance includes at least one word. The text classification system generates a parse tree for the utterance. The parse tree includes at least one terminal node with a word type. The terminal node represents a word of the utterance. The text classification system applies one or more rules to the text. The text classification system then classifies the utterance as a question or a request for an autonomous agent to perform an action.

Techniques are disclosed for improved autonomous agents that can provide a recommendation in a non-intrusive, conversational manner. In an aspect, a method determines a first sentiment score for a first utterance and a second sentiment score for a second utterance, each sentiment score indicating an emotion indicated by the respective utterance. The method further identifies that a difference between the first sentiment score and the second sentiment score is greater than a threshold. The method further extracts a noun phrase from the second utterance. The method identifies a text fragment that includes an entity that corresponds to the noun phrase. The method identifies that the text fragment addresses a claim of the second utterance. The method forms a third utterance that includes the a recommendation related to the second utterance and adds the third utterance to the sequence of utterances after the second utterance.

This invention is a robot that enables efficient care of plants within the home or office environment via sensor readings and actuators which influence the environment accordingly. Several of these robots may be active at the same time, which leads to opportunities for cooperation and competition among these autonomous agents.

The behavior of automated agents, such as autonomous vehicles, drones, and the like, can be improved by control systems and methods that implement a combination of neighbor following behavior, or neighbor-averaged information transfer, with delayed self-reinforcement by utilizing time-delayed movement data to modify course corrections of each automated agent. Disclosed herein are systems and methods by which a follower agent, or a multiple follower agents in formation with a plurality of automated agents, can be controlled by generating course correction data for each follower agent based on the movement of neighboring agents in formation, and augmenting the course correction data based on time-delayed movement data of the follower agent. The delayed self-reinforcement behavior can (i) increase the information-transfer rate between autonomous agents without requiring an increased, individual update-rate; and (ii) cause superfluid-like information transfer between the autonomous agents, resulting in improvements in formation-keeping performance of the autonomous agents.

In a computer system functioning as an autonomous agent with a robotic controller wherein the computer system need not be programmed to perform a specific task, values in an array of error variables are obtained from comparison between an array of resources variables used to indicate resource use and state of an Autonomous Agent and an array of corresponding desired levels for the resource variables. Each individual value in the array of error variables represents an error in the actual value of a particular resource variable as compared to its desired value. Derivative variables for the resource variables and for parameters controlling behavior of the Autonomous Agent are created. The values of the array of error variables and their associated derivative variables are used to adjust values of the behavior-controlling parameters thereby modifying behavior of the Autonomous Agent.

A method for operating a host layer of a distributed computing system on a wide area network includes attaching an autonomous agent to a client-requested carrier, such as web content. The method includes the steps of receiving a request for specified content from a client node via the wide area network, and sending the content and an embedded agent to the client via the wide area network. The agent has program instructions configured to execute autonomously on the client node to perform a processing function. The processing function is configured to operate on raw data to produce process data, according to instructions determined by a solution algorithm of the distributed computing system. The method further includes sending the raw data to the client node and receiving the process data from the client node as it is processed by the agent. The host layer may comprise a web server hosting a web site containing consumer-oriented web pages, and the carrier may comprise an HTML page containing user content. The agent may comprise a web page-enabled application embedded in the HTML page, such as a Java™ applet.

Systems and methods for improving question-answering recall for complex, multi-sentence, convergent questions. More specifically, an autonomous agent accesses an initial answer that partly answers a question received from a user device. The agent represents the question and the initial answer as discourse trees. From the discourse trees, the agent identifies entities in the question that are not addressed by the answer. The agent forms an additional discourse tree from an additional resource such as a corpus of text. The additional discourse tree rhetorically connects a non-addressed entity with the answer. The agent designates this discourse tree as an imaginary discourse tree. When combined with the initial answer discourse tree, the imaginary discourse tree is used to generate an improved answer relative to existing solutions.