A safety system is disclosed for failsafe servicing of areas within an order fulfillment facility. During normal operation, a number of battery-powered robots receive wireless instructions from a management control system (MCS) to transfer items to/from workstations or storage shelves in a multi-level storage structure. The order fulfillment facility may be divided into dynamically configurable service zones. When service is required in a service zone, different safety protocols may be employed based on a determination as to the priority level of service required and/or the estimated length of time service will take. One safety protocol involves physically blocking all access points to a service area with mechanical guards, so that order fulfillment operations may be proceed around the service zone while service is performed.

A robot control device (10) includes an attribute determination unit (71) that determines an attribute of an object person (T) around a robot (1); and a decision unit (74) that decides a notification action of notifying, by the robot (1), the object person (T) of presence of the robot (1), on the basis of the attribute determined by the attribute determination unit (71) and a risk of harm that may be caused to the object person (T) by the robot (1).

A robot system includes a robot collaboratively acting with a human, a force sensor provided in the robot and detecting a force, a control unit decelerating or stopping an action of the robot based on output from the force sensor, a first temperature sensor detecting a temperature of the force sensor, and an execution unit performing warm-up operation in the robot until output from the first temperature sensor reaches a first target value.

A control device 1A mainly includes an operation sequence generation means 17A. The operation sequence generation means 17A is configured to generate, based on recognition results Ra relating to types and states of objects present in a workspace where a robot which performs a task and another working body perform cooperative work, an operation sequence Sa to be executed by the robot.

A method for monitoring a robot arrangement, which robot arrangement has at least one robot includes capturing optical signals from a plurality of signal sources at least one sensor, wherein the signal sources and/or the sensor is/are positioned on the robot arrangement and triggering a monitoring reaction if a deviation of an actual arrangement of the captured optical signals from a desired arrangement of these signals exceeds a limit value. In one aspect, a reaction may be triggered if at least a predefined minimum number of signals from the desired arrangement is not present in the actual arrangement of the captured optical signals.

Example implementations described herein involve systems and methods for training and managing machine learning models in an industrial setting. Specifically, by leveraging the similarity across certain production areas, example implementations can group together these areas to train models efficiently that use human pose data to predict human activities or specific task(s) the workers are engaged in. The example implementations do away with previous methods of independent model construction for each production area and takes advantage of the commonality amongst different environments.

In an embodiment, a method for handling an order includes determining a plurality of ingredients based on an order, received from a user over a network, for a location having a plurality of robots. The method further includes planning at least one trajectory for at least one robot based on the plurality of ingredients and utensils available at the location, and proximity of each ingredient and utensil to the at least one robot. Each trajectory can be configured to move one of the plurality of ingredients into a container associated with the order. In an embodiment, the method includes executing the at least one trajectory by the at least one robot to fulfill the order. In an embodiment, the method includes moving the container to a pickup area.

A conveyance robot system according to the present disclosure includes a conveyance robot, and a robot control unit configured to control an operation of picking up an object performed by the conveyance robot, wherein the robot control unit determines that a movable range area, which is an area outside a safety cover where a robot arm is operated, satisfies a safety ensuring condition that can regard safety of the movable range area as equivalent to the safety inside the safety cover and allow the robot arm to perform a work while projecting toward the shelf.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing automated safety procedures for a robot. One of the methods includes receiving, by a robotic control system for a robot, a request to execute an automated safety procedure by a safety control subsystem for the robot. Each step of the automated safety procedure is iterated until an end of the automated safety procedure is reached, including if a step requires a new safety configuration, a respective safety configuration for the step is obtained and activated before performing one or more automatic actions for the step.

A robot comprises at least one articulate arm having members including a base, an end effector and a plurality of links, wherein each link is movably connected to two others of said members by respective joints, at least one sensor for detecting an external force acting on any one of the members, and a controller for controlling movements of the joints, so as to move the end effector along a pre-programmed path. In case of the sensor detecting an external force, the controller is adapted to adopt a first release strategy for escaping from the external force, to evaluate whether the first strategy is successful, and if not, to adopt a second release strategy.