A method for load balancing of robots includes: receiving, by a first task server configured to manage a first spatial region, a task to be performed by a robot; determining, by the first task server, that the task cannot efficiently be performed within the first spatial region; finding, by the first task server, a second task server configured to manage a second spatial region to which the task can be assigned; and sending, by the first task server, the task to the second task server.

A synchronization primitive provides robots with locks, monitors, semaphores, or other mechanisms for reserving temporary access to a shared limited set of resources required by the robots in performing different tasks. Through non-conflicting establishment of the synchronization primitives across the set of resources, robots can prioritize the order with which assigned tasks are completed and minimize wait times for resources needed to complete each of the assigned tasks, thereby maximizing the number of tasks simultaneously executed by the robots and optimizing task completion. The synchronization primitives and resulting resource allocation can be implemented with a centralized coordinator or with peer-to-peer robotic messaging, whereby private keys and blockchains secure the precedence and establishment of synchronization primitives by different robots. Moreover, synchronization primitives can be established with queues to further optimize the immediate and future allocation of resources to different robots.

The invention concerns a method, arrangement and computer program product for distributing processing for a first robot in a cell among more than one processing entities. The arrangement includes a processing entity determining unit that obtains data about current limitations in the processing environment of a prospective processing entity intended to perform a processing task for the first robot, determines, based on the processing environment limitations, whether a performance requirement will be fulfilled or not if the task is performed in the prospective processing entity, and assigns the processing task for processing in the prospective processing entity or in at least one other processing entity based on the determining of whether the performance requirement is fulfilled or not.

This disclosure relates generally to autonomous devices, and more particularly to method and system to optimally allocate warehouse procurement tasks to distributed autonomous devices. The method includes obtaining, at a coordinating agent, a global task associated with the warehouse and information associated with the robotic agents. The information includes a count and status of the robotic agents. The global task is profiled to obtain a set of sub-tasks and constraints associated with the set of sub-tasks are identified. The constraints include utilization constraint and/or pricing constraints. A distributed, decentralized optimal task allocation is performed amongst the robotic agents based on constraints to obtain optimal performance of robotic agents. The distributed optimal task allocation includes performing primal or dual decomposition of the set of sub-tasks by each robotic agent and updating corresponding primal/dual variables by the coordinating agent when the optimization is performed based on utilization constraint and pricing constraints, respectively.

This disclosure relates generally to autonomous devices, and more particularly to method and system to optimally allocate warehouse procurement tasks to distributed autonomous devices. The method includes obtaining, at a coordinating agent, a global task associated with the warehouse and information associated with the robotic agents. The information includes a count and status of the robotic agents. The global task is profiled to obtain a set of sub-tasks and constraints associated with the set of sub-tasks are identified. The constraints include utilization constraint and/or pricing constraints. A distributed, decentralized optimal task allocation is performed amongst the robotic agents based on constraints to obtain optimal performance of robotic agents. The distributed optimal task allocation includes performing primal or dual decomposition of the set of sub-tasks by each robotic agent and updating corresponding primal/dual variables by the coordinating agent when the optimization is performed based on utilization constraint and pricing constraints, respectively.

A method and system for batch scheduling uniform parallel machines with different capacities based on an improved genetic algorithm are provided. The method is to solve the batch scheduling problem of uniform parallel machines with different capacities. Jobs are distributed to machines by an improved genetic algorithm, and a corresponding batching strategy and a batch scheduling strategy are proposed according to the natural of the problem to obtain a fitness value of a corresponding individual; then, the quality of the solution is improved by a local search strategy; and, a crossover operation is performed on a population based on the fitness of the solution, and the population is continuously updated by repetitive iteration to eventually obtain an optimal solution.

A dynamic multi-objective task allocation system within robotic networks that assigns tasks in real-time as they are detected, the system including a sensing device that detects a trigger event, the trigger event being associated with a task to be performed, and transmits a broadcast signal to a designated robotic network, the robotic network including one or more robots, the broadcast signal including information associated with the task to be performed, the trigger event, the task to be performed, and a location where the task is to be performed; and a distribution robot that receives broadcast signal from the sensing device, assigns itself a self-score associated with performing the task, transmits, to one or more receiving robots within the robotic network, a request for submission of an assessment score of each one of the one or more robots, and determines which robot is assigned to perform the task.

A synchronization primitive provides robots with locks, monitors, semaphores, or other mechanisms for reserving temporary access to a shared limited set of resources required by the robots in performing different tasks. Through non-conflicting establishment of the synchronization primitives across the set of resources, robots can prioritize the order with which assigned tasks are completed and minimize wait times for resources needed to complete each of the assigned tasks, thereby maximizing the number of tasks simultaneously executed by the robots and optimizing task completion. The synchronization primitives and resulting resource allocation can be implemented with a centralized coordinator or with peer-to-peer robotic messaging, whereby private keys and blockchains secure the precedence and establishment of synchronization primitives by different robots. Moreover, synchronization primitives can be established with queues to further optimize the immediate and future allocation of resources to different robots.

Embodiments of the invention relate to statistical and mathematical optimization techniques to predict completion time of parts and subassemblies in one production line. A real-time visibility of products and work-in-process is produced. Optimization techniques are utilized to allow for dynamic modification of a transportation schedule and/or batch size, thereby reducing transportation costs.

An industrial robot adapted for operation in a factory environment includes: sensors, actuators, a robot controller and a wireless interface configured to establish a sidelink to a further industrial robot or a group of industrial robots after a successful proximity verification. The industrial robot is configured to participate in execution of a utility task, which is carried out in collaboration with the further industrial robot or at least some members of the group of industrial robots, said collaboration including an exchange of operational data over the sidelink. An example utility task is the coordinated transfer of an object by multiple participating industrial robots. Another example is the collecting of map information by multiple participating industrial robots.