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).

Various embodiments for enforcing safe operation of machinery performing an activity in a three-dimensional (3D) workspace includes computationally generating a 3D spatial representation of the workspace; computationally mapping 3D regions of the workspace corresponding to space occupied by the machinery and a human; and based thereon, restricting operation of the machinery in accordance with a safety protocol during physical performance of the activity. Limited-access zones are defined within which the presence of a human will not affect operation of the machinery.

Systems and methods for determining safe and unsafe zones in a workspace—where safe actions are calculated in real time based on all relevant objects (e.g., some observed by sensors and others computationally generated based on analysis of the sensed workspace) and on the current state of the machinery (e.g., a robot) in the workspace—may utilize a variety of workspace-monitoring approaches as well as dynamic modeling of the robot geometry. The future trajectory of the robot(s) and/or the human(s) may be forecast using, e.g., a model of human movement and other forms of control. Modeling and forecasting of the robot may, in some embodiments, make use of data provided by the robot controller that may or may not include safety guarantees.

A surgical robotic system including a surgical table, a surgical robotic manipulator coupled to the surgical table and comprising a plurality of links coupled together by a plurality of joints that are operable to move with respect to one another to move the surgical robotic manipulator, at least one of the plurality of links or the plurality of joints having a portion that faces another of the plurality of links or the plurality of joints, a proximity sensing assembly coupled to the portion of the at least one of the plurality of links or the plurality of joints, the proximity sensing assembly operable to detect an object prior to the surgical robotic manipulator colliding with the object and to output a corresponding detection signal, and a processor operable to receive the corresponding detecting signal and cause the manipulator or the object to engage in a collision avoidance operation.

In variants, a method for robot control can include: receiving sensor data of a scene, modeling the physical objects within the scene, determining a set of potential grasp configurations for grasping a physical object within the scene, determining a reach behavior based on the potential grasp configuration, determining a trajectory for the reach behavior, and grasping the object using the trajectory.

A method of operating a robot manipulator, the method including: specifying a maximum permissible force to be exerted on an object by the robot manipulator, specifying a target position of a reference point of the robot manipulator, determining a current position of the reference point, performing an impedance regulation, which determines a current reference force of an artificial spring component based on a spring stiffness and based on a difference between the current position and the target position of the reference point of the robot manipulator, and controlling the robot manipulator to execute an emergency control program if the current reference force exceeds the maximum permissible force.

Embodiments of the disclosure provide a box retrieval method and apparatus, a system, a robot, and a storage medium. The method is applied to a warehouse robot, and includes: acquiring a detection image, where the detection image includes an image of a target box and neighboring objects; determining a box spacing between the target box and each neighboring object according to the detection image; and if the box spacing satisfies retrieval conditions for a warehouse robot, retrieving the target box. Automatic detection of the box spacing is achieved with low detection cost and high detection accuracy, and goods is retrieved only when the spacing satisfies conditions, such that goods retrieval safety is increased, and the probability of goods damage and falling down of shelves during a retrieval process is greatly lowered.

Disclosed is a method for controlling a robot cleaner including acquiring, by a camera, an image, irradiating, by a light source, light toward a location the same as a location where the acquired image is captured, receiving, by a sensor, the light irradiated from the light source and reflected on an object, processing an image received from the sensor to contain a distance value of an individual location, and supplementing the image received from the sensor with the image captured by the camera when a singularity is found, wherein distance values calculated in adjacent portions are discontinuous at the singularity.

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.