Approaches presented herein enable maneuvering collaborative robots to rescue persons in a hydrological disaster. A plurality of robots are dispersed in a body of water to spread out and seek victims using cooperative foraging techniques within resource constraints. A location of victims located by a robot using sensing techniques is communicated to other robots. A situational assessment is performed using victim location information to determine a number of robots to deploy to the location. The deployed robots are directed to perform coordinated maneuvers to create a connected floatation unit to support floatation of victims for rescue.

In a mobile robot and a control method therefor according to the present disclosure, a plurality of mobile robots located in an area confirm the positions of other mobile robots and operate in cooperation with each other to cooperatively clean then area. One mobile robot moves to follow the position of another mobile robot, so that the mobile robots with different cleaning types cooperate to clean the area. Accordingly, the plurality of mobile robots can cooperatively perform cleaning without colliding within one area, and by combining or changing a plurality of position detection methods as needed, the position of another mobile robot can be easily calculated and the cleaning efficiency is greatly improved.

A method includes receiving a request for a robotic fleet to perform a job and defining a set of tasks that are to be performed in performance of the job. The method includes assigning robots selected from a robot inventory to the set of tasks based on a robot inventory data structure that indicates, for each robot, a status and set of baseline features. The robots include one or more assigned multi-purpose robots that can be configured for different tasks and different environments. The method includes determining a configuration for each assigned robot based on the respective task that is assigned and a components inventory. The components inventory indicates multiple components and, for each component, a status and a set of extended capabilities. The method includes configuring the one or more assigned multi-purpose robots based on the respective configurations. The method includes deploying the robotic fleet to perform the job.

A robotic fleet platform for configuring robot fleets with additive manufacturing capabilities includes a fleet resources data store that maintains a fleet resource inventory indicating additive manufacturing systems that can be provisioned with fleet resources and, for each additive manufacturing system, a set of 3D printing requirements, printing instructions that define configuring an on-demand production system for 3D printing, and a status of the additive manufacturing system. The platform includes additive manufacturing system provisioning rules that are accessible to an intelligence layer to ensure that provisioned additive manufacturing systems comply with the provisioning rules. The platform receives a request for a robotic fleet to perform a job and determine a job definition data structure based on the request. The job definition data structure defines a set of tasks for the job. The platform deploys the robotic fleet based on the robotic fleet configuration data structure to perform the job.

There is provided a control device, a control method, and a control system that implement a robot that flexibly executes a task in cooperation with another robot, the control device including: an ability management unit that determines capability indicating ability that can be executed by a first robot at predetermined timing as of that timing; a help management unit that compares ability required for a task to be executed by the first robot with the capability of the first robot and generates a help list indicating ability required for execution of the task; and a cooperation management unit that instructs a second robot having the capability that satisfies the ability indicated in the help list to execute the task in cooperation with the first robot.

This disclosure relates to system and method for cleaning surfaces using drones. The method includes identifying, by a first drone, a cleaning strip in contact with a surface. The cleaning strip connects a second drone and a third drone. The second drone is communicatively coupled with the third drone. The first drone is communicatively coupled with each of the second drone and the third drone. The method further includes releasing a cleaning agent at a preconfigured pressure upon a current target region of the surface near the cleaning strip. The method further includes relocating the cleaning strip upon the current target region. The method further includes performing a set of oscillations through the cleaning strip across the current target region. Each of the set of oscillations includes coordinating a displacement of the cleaning strip by a predefined distance, alternating towards each of ends of the cleaning strip.

A system and method for intermodal container transport that utilizes swarm intelligence and the autonomous locating, lifting, supporting and moving via robots working in conjunction. A port central command locates and releases robots to the container location and then transports the container to its destination.

A method of robotic collaboration comprises designating a first robot a lead robot and assigning a first task in a task area to the lead robot. Broadcasting a work query in the task area seeks the presence of subordinate robots configured to perform tasks. Receiving a work confirmation signal from a subordinate robot in the task area answers the work query with an affirmation that the subordinate robot is in the task area to perform tasks. Transmitting a task command to the subordinate robot in response to the work confirmation signal comprises a directive to perform the first task. Receiving a task confirmation signal informs the lead robot of the subordinate robot electronic characteristics comprising processing capabilities, transmit signal profile, receive signal profile, and storage device capabilities. Processing confirms whether the subordinate robot can collaborate with the lead robot to do the first task.

Methods, systems, and apparatus, including computer programs encoded on computer storage media for evaluating robot learning. In some implementations, a system receives classification examples from a plurality of remote devices over a communication network. The classification examples can include (i) a data representation generated by a remote device based on sensor data captured by the remote device and (ii) a classification corresponding to the data representation. The system assigns quality scores to the classification examples based on a level of similarity of the data representations with other data representations. The system selects a subset of the classification examples based on the quality scores assigned to the classification examples. The system trains a machine learning model using the selected subset of the classification examples.

A robot cluster scheduling system includes a user layer, an intermediate layer, an application layer, a plug-in layer and a data persistence layer. The intermediate layer includes a processor mapping module and a state acquisition module. The application layer includes a task scheduling module and a traffic scheduling module. The plug-in layer includes a task solving engine and a traffic planning engine. The task solving engine is configured to determine a target robot according to a parameter of a task and state data. The traffic planning engine is configured to determine a target route. The task solving engine and the traffic planning engine each provide an application programming interface (API).