Abstract: A method for delimiting and monitoring at least one working area for at least one autonomously operated vehicle includes transmitting, by a transmitter and receiver unit, an output signal through a signal loop. The transmitter and receiver unit is arranged outside the vehicle and is connected using signaling technology to the signal loop. The method further includes comparing the transmitted output signal with an input signal received from the signal loop, determining, by the transmitter and receiver unit, a malfunction of the signal loop in response to a deviation between the output signal and the input signal, and initiating a securing sequence for the autonomous driving operation of the at least one vehicle.

Abstract: A sensing circuit (51), a logic circuit board, a joint control board, a main controller board and a robot (400). The sensing circuit (51) comprises a connecting terminal (514) and a detection circuit (210). The connecting terminal (514) is configured to be coupled with the electrode (120) disposed on a housing (100) of a mechanical equipment; the detection circuit (210) is coupled to the connecting terminal (514) so as to detect the distance between the electrode (120) and the external conductor or a change of the distance between the electrode (120) and the external conductor according to the capacitance between the electrode and the external conductor or a change of the capacitance between the electrode (120) and the external conductor, thereby obtaining an electrical signal representing the distance between the electrode (120) and the external conductor or a change of the distance between the electrode (120) and the external conductor.

Abstract: According to one embodiment, a handling system includes a movable arm, a holding unit, a sensor, and a controller. The holding unit is attached to the movable arm and capable of holding an object by selecting one or more of a plurality of holding methods. The sensor is capable of detecting a plurality of the objects. The controller controls the movable arm and the holding unit. The controller calculates a score based on a selected holding method for each object and each holding method on the basis of information acquired from the sensor. The controller selects a next object to be held and a holding method on the basis of the score. The controller calculates a position at which the selected object is held and a posture of the movable arm.

Abstract: An autonomous movement system according to an embodiment is an autonomous movement system that performs autonomous movement in a facility including an elevator, in which the autonomous movement system moves a waiting position in a car of the elevator, based on a person that gets on the car or an object that gets on the car. The autonomous movement system may determine the person or the object before the car stops at a floor or before a car door opens.

Abstract: A fixing member includes a first side, second side parallel to the first side, and face provided between the first side and second side and including an opening. The face is provided at a position separate from a line connecting between the first side and second side, first side is brought into line contact or point contact with the first structure, and second side is brought into line contact with an end part of a strain body constituting a strain sensor, the end part being provided on the first structure. A screw is inserted into the opening and is screwed into the first structure.

Abstract: In one embodiment, a method includes generating a trajectory plan to complete a task to be executed by a robotic system, identifying objects in the environment required for completing the task, determining attributes for each of the identified objects, determining trajectory-parameters for the trajectory plan based on the determined attributes for each identified object and operational conditions in an environment associated with the robotic system, and executing the task based on the determined trajectory-parameters for the trajectory plan.

Abstract: A flexible surgical tool system includes: a mechanical arm (10) comprising a first continuum segment (12), a rigid connection segment (13), and a second continuum segment (14), the first continuum segment (12), a rigid connection segment (13) and the second continuum segment (14) being sequentially associated to form a dual continuum mechanism; a surgical effector (50) connected at distal end of the second continuum segment (14); a transmission driving unit (20) associated with the rigid connection segment (13) and with a surgical effector (50), respectively, and operable to drive the first continuum segment (12) to bend in any direction to drive the second continuum segment (14) to bend in an opposite direction, and to drive the surgical effector (50) to rotate in a first plane and/or open and close in a second plane. The flexible surgical tool system can be applied to a natural orifice or a single surgical incision of a human body and perform operations.

Abstract: An elevator control system, an elevator system, and a control method therefor. The elevator control system includes: a data collection unit configured to receive a call request signal from a machine passenger at each landing, and receive information about the machine to ride the elevator sent by the machine passenger; and a control unit configured to determine whether to accept the call request from the machine passenger based on elevator operating condition and the information about the machine to ride the elevator, and send information about the rules of riding the elevator to the machine passenger after accepting its call request.

Abstract: A medical holding apparatus includes: an arm including a plurality of links mutually coupled through one of joints, the arm having at least six degrees of freedom due to rotational motion about a rotation axis, the arm being configured to function as a balanced arm with a counterweight and support a medical device; and an arm controller configured to control motion of the arm, in which at least three of the joints in the arm each are provided with an angular sensor that detects a rotation angle of the rotation axis and an actuator that gives the joint an assist force of assisting the rotational motion, and the arm controller controls, based on respective detected results of the angular sensors, the respective assist forces of the actuators such that an amount of force in operation necessary when an operator moves the medical device supported by the arm remains in a predetermined range.

Abstract: A control method for a robot includes: determining a desired zero moment point (ZMP) of the robot; obtaining a position of a left foot and a position of a right foot of the robot, and calculating desired support forces of the left foot and the right foot according to the desired ZMP, the positions of the left foot and the right foot; obtaining measured support forces of the left foot and the right foot, and calculating an amount of change in length of the left leg and an amount of change in length of the right leg according to the desired support forces of the left foot and the right foot, the measured support forces of the left foot and the right foot; and controlling the robot to walk according to the amount of change in length of the left leg and the right leg.

Abstract: It A waste sorting robot (100) comprises a manipulator (101) moveable within a working area (102). A gripper (103) is connected to the manipulator (101) and arranged to selectively grip a waste object (104, 104a, 104b, 104c) in the working area (102). A controller (108) is in communication with a sensor (107) and is configured to receive detected object parameters, and determine a throw trajectory (109) of the gripped waste object (104) towards a target position (106) based on the detected object parameters of the gripped waste object (104). The controller (108) is configured to send control instructions to the gripper (103) and/or manipulator (101) so that the gripper (103) and/or manipulator (101) accelerates the gripped waste object (104) and releases the waste object (104) at a throw position with a throw velocity and throw angle towards the target position (106) so that the waste object (104) is thrown along the determined throw trajectory (109).

Abstract: A method includes receiving sensor data for an environment about the robot. The sensor data is captured by one or more sensors of the robot. The method includes detecting one or more objects in the environment using the received sensor data. For each detected object, the method includes authoring an interaction behavior indicating a behavior that the robot is capable of performing with respect to the corresponding detected object. The method also includes augmenting a localization map of the environment to reflect the respective interaction behavior of each detected object.

Abstract: Disclosed are a mobile robot operation control method for safety management of a cleaning module and an apparatus therefor. The mobile robot operation control method for safety management according to an exemplary embodiment of the present disclosure includes a current measuring step of measuring a current value by sensing a current for a motor which is connected to a cleaning module to be driven; a cleaning module safety management step of determining a state of the cleaning module based on the measured current value and determining a safety management control mode based on the determination result; and an operation control step of controlling an operation of a mobile robot based on the safety management control mode.

Abstract: A two-stage insertion system including a gripper to grip a module, a compliance element to provide movement in the XY axis, a first stage insertion control to insert the module into a socket, to a first level, and a second stage insertion control to complete the insertion of the module into the socket, when the first stage insertion control indicates that the module is aligned to the socket, the second level insertion control exerting enough force to complete the insertion of the module into the socket.

Abstract: A growspace automation system and method. The system includes a grow space with localization structures and a mobile robot. The mobile robot comprises sensors, a mobility mechanism, and a plurality of mobility modules. The mobile robot is configured to automate growspace processes, such as transport, watering, sensing, or cleaning.

Abstract: An autonomous work machine that works in a work area while autonomously traveling in the work area, comprises a plurality of magnetic detection sensors each configured to detect a magnetic field during energization of a station wire which is configured to guide the autonomous work machine to a charging station for power supply, and a specification unit configured to specify, when the autonomous work machine is to move from a charging position of the charging station to the work area or when the autonomous work machine is to move from the work area to the charging position, an angle of the autonomous work machine with respect to the charging station based on a comparison of detection results of the magnetic detection sensors.

Abstract: A gripper device is configured to be attached to a robotic device and to pick up a food product from a pickup area and to release it from a releasing location to a receiving location. A method is provided for picking up a food product from a pickup area and releasing it from a releasing location to a receiving location can be used with the gripper device.

Abstract: A method of cleaning a floor comprises providing an autonomous surface cleaning apparatus, positioning a plurality of docking stations at different locations on the floor wherein a first docking station has an absence of an evacuation mechanism and actuating the autonomous surface cleaning apparatus whereby the autonomous surface cleaning apparatus travels across the floor to clean at least a portion of the floor and recharges at the first docking station.

Abstract: A robotic cleaner may include a housing, a bumper, driven wheels, and a controller. The bumper can be coupled to a front of the housing. The bumper may include a plurality of projections extending from a top edge of the bumper and above a top surface of the housing. The projections may include at least one leading projection proximate a forward most portion of the bumper and at least two side projections on each respective side of the bumper. The driven wheels may be rotatably mounted to the housing. The controller may be for controlling at least the driven wheels.

Abstract: A pose control method for a robot includes: estimating a first set of joint angular velocities of all joints of the robot according to a balance control algorithm; estimating a second set of joint angular velocities of all joints of the robot according to a momentum planning algorithm; estimating a third set of joint angular velocities of all joints of the robot according to a pose return-to-zero algorithm; and performing pose control on the robot according to the first set of joint angular velocities, the second set of joint angular velocities, and the third set of joint angular velocities.

Abstract: A method of correcting an angular transmission error for a reducer of creating correction data for correction of an angular transmission error of the reducer in a robot system including an arm, the reducer having an input shaft and an output shaft, a motor, an encoder, and an inertial sensor, includes rotating the arm in an input rotation angular range smaller than a necessary input rotation angular range, measuring and recording the angular transmission error, determining whether or not an accumulated value of measurement times is equal to or larger than a predetermined value, when the accumulated value is smaller than the predetermined value, measuring the angular transmission error of the reducer and updating a record, and, when the accumulated value is equal to or larger than the predetermined value, creating the correction data based on the recorded angular transmission error of the reducer.

Abstract: Provided are a mobile robot device and a control method thereof. The mobile robot device comprises: a driving unit; an image sensor; a plurality of geomagnetic sensors; a memory for storing at least one instruction; and a processor for executing at least one instruction, wherein the processor may obtain, while the mobile robot device moves by means of the driving unit, a plurality of image data through the image sensor and obtain sensing data through the plurality of geomagnetic sensors, extract a feature point from the plurality of image data and obtain key nodes on the basis of the feature point, obtain a node sequence on the basis of the sensing data, generate a graph structure that estimates a position of the mobile robot device on the basis of the key nodes and the node sequence, and correct the graph structure based on the mobile failing in position recognition.

Abstract: A system and method for controlling a device, such as a virtual reality (VR) and/or a prosthetic limb are provided. A biomimetic controller of the system comprises a signal processor and a musculoskeletal model. The signal processor processes M biological signals received from a residual limb to transform the M biological signals into N activation signals, where M and N are integers and M is less than N. The musculoskeletal model transforms the N activation signals into intended motion signals. A prosthesis controller transforms the intended motion signals into three or more control signals that are outputted from an output port of the prosthesis controller. A controlled device receives the control signals and performs one or more tasks in accordance with the control signals.

Abstract: A light ranging system including a shaft having a longitudinal axis; a light ranging device configured to rotate about the longitudinal axis of the shaft, the light ranging device including a light source configured to transmit light pulses to objects in a surrounding environment, and detector circuitry configured to detect reflected portions of the light pulses that are reflected from the objects in the surrounding environment and to compute ranging data based on the reflected portion of the light pulses; a base subsystem that does not rotate about the shaft; and an optical communications subsystem configured to provide an optical communications channel between the base subsystem and the light ranging device, the optical communications subsystem including one or more turret optical communication components connected to the detector circuitry and one or more base optical communication components connected to the base subsystem.

Abstract: Provided is a method for determining a coverage path of a robotic device, including: capturing, with a sensor, spatial data of the environment; detecting, with a processor, at least one obstacle within the environment based on the spatial data; determining, with the processor, a first working zone within the environment; determining, with the processor, a coverage path within the first working zone that accounts for at least one of the obstacles detected within the first working zone; actuating, with the processor, a robotic device to drive along the coverage path within the first working zone; and wherein the processor determines an adapted coverage path when a new obstacle is detected and wherein the processor actuates the robotic device to drive along the adapted coverage path.

Abstract: A wireless valve manifold is capable of wireless communication, and includes a plurality of solenoid valves. This wireless valve manifold is able to move by means of a movable unit. In addition, the wireless valve manifold includes a battery which can supply power to the plurality of solenoid valves, and a power-receiving control unit which is connected to the battery and which charges the battery with power by means of wireless power transmission from a feeder station of the wireless valve manifold.

Abstract: A modular robot is provided. The modular robot includes a sweeper module having a container for collecting debris from a surface of a location. The sweeper module is coupled to one or more brushes for contacting the surface and moving said debris into said container. Included is a robot module having wheels and configured to couple to the sweeper module. The robot module is enabled for autonomous movement and corresponding movement of the sweeper module over the surface. A controller is integrated with the robot module and interfacing with the sweeper module. The controller is configured to execute instructions for assigning of at least two zones at the location and assigning a work function to be performed using the sweeper module at each of the at least two zones. The controller is further configured for programming the robot module to activate the sweeper module in each of the two zones. The assigned work function is set for performance at each of the at least two zones.

Abstract: The invention relates to a method to calibrate a handling device (18) including a handling robot or parallel kinematic robot (24), with a tool head (28) suspended from at least two parallel kinematically movable arms (26). Each of the at least two arms comprises an upper arm, which is movable between two end positions about a defined upper-arm swivel axis (38). Each of the at least two arms also comprises a lower arm (40), which is swivelably mounted on the upper arm. The upper arms are brought into approximately corresponding angular positions by detection of load torques and/or of angle positions. First one, than another of the upper arms is brought into one of the two end positions, and the angular position reached is detected and used for the position initialization or angle initialization of the particular upper arm, whereupon the upper arm is returned.

Abstract: Three-dimensional measurement data is obtained (step S1). The poses of bulk parts are calculated (step S2). The gripping poses of a hand relative to the bulk parts are calculated (step S3). Individual evaluation indices are calculated (step S4). Overall evaluation indices are calculated (step S5). The gripping poses are sorted using the overall evaluation indices (step S6). The calculated gripping poses appear on a screen (step S7). The gripping poses are sorted by a user in an intended order (step S8). Determination is performed as to whether the difference between the results of the sorting in step S6 and in step S8 is small (step S9). In response to the difference being sufficiently small, parameters used in the calculation of the overall evaluation indices are stored (step S11). In response to the difference not being sufficiently small, the parameters are updated (step S10) and the processing returns to step S5.

Abstract: Techniques for planning object sorting are disclosed, including: receiving a set of current information associated with target objects on a conveyor device; determining a current state of the sorting system, wherein the sorting system comprises an actuator device that is configured to actuate a picker assembly to capture target objects from the conveyor device; determining a sequence of actions to be performed by the actuator device and the picker assembly with respect to one or more target objects based on the set of current information associated with the target objects and the current state of the sorting system; determining a selected subset of actions with respect to an identified target object from the sequence of actions; and sending an instruction to the actuator device to cause the actuator device to perform the selected subset of actions with respect to the identified target object.

Abstract: The mower fleet management device is configured to control a plurality of mowers to work in collaboration. Each of the mowers includes an on-board communication module and an on-board positioning and navigation module. The mower fleet management device includes: a map loading module configured to acquire a map of a working land parcel; a control terminal communication module configured to wirelessly communicate with the on-board communication modules to acquire status information of the mowers; and a working region assigning module configured to assign a working region to each of the mowers according to the status information and the map. The on-board positioning and navigation module of each of the mowers guides the mower to work in the corresponding working region according to the assigned working region.

Abstract: A method for controlling a robot. The method includes receiving an indication of a target configuration to be reached from an initial configuration of the robot, determining a coarse-scale value map by value iteration, starting from an initial coarse-scale state and until the robot reaches the target configuration or a maximum number of fine-scale states has been reached, determining a fine-scale sub-goal from the coarse-scale value map, performing, by an actuator of the robot, fine-scale control actions to reach the determined fine-scale sub-goal and obtaining sensor data to determine the fine-scale states reached, starting from a current fine-scale state of the robot and until the robot reaches the determined fine-scale sub-goal, the robot transitions to a different coarse-scale state, or a maximum sequence length of the sequence of fine-scale states has been reached and determining the next coarse-scale state.

Abstract: A teleoperated surgical system is provided comprising: a first robotic surgical instrument; an image capture; a user display; a user input command device coupled to receive user input commands to control movement of the first robotic surgical instrument; and a movement controller coupled to scale a rate of movement of the first robotic surgical instrument, based at least in part upon a surgical skill level at using the first robotic surgical instrument of the user providing the received user input commands, from a rate of movement indicated by the user input commands received at the user input command device.

Abstract: A gait planning method and a robot using the same as well as a computer readable storage medium are provided. The method includes: determining a reference leg length l0 and a leg length variation range A of a robot; performing a trajectory planning on a length of at least one of the legs of the robot using; an equation including the reference leg length, the leg length variation range, and a preset recurrent excitation function of a time variable t. In this manner, the trajectory planning for the leg length of the robot during motion is performed according to the characteristics of motion scene such as robot jumping or running so that the change of the leg length of the robot is adapted to the motion process, which greatly improves the stability of the robot in the motion scene such as jumping or running.

Abstract: The present disclosure provides an industrial Internet of things for monitoring a collaborative robot and a control method, a storage medium thereof, wherein the control method comprises: obtaining position data of the workpiece to be processed as first monitoring data through the sensing network platform; selecting, based on the first monitoring data, a benchmark working parameter matching the first monitoring data from a working parameter library; obtaining, via the sensing network platform, a working parameter of the target collaborative robot as second monitoring data; comparing the second monitoring data with the benchmark working parameter to determine a working state of the target collaborative robot.

Abstract: An actuator system that picks up workpieces aims to shorten tact time and to reduce damages to workpieces. The actuator system includes an actuator that picks up a workpiece, an external force detection sensor that detects a physical quantity that is correlated with an external force that is applied to the workpiece, a head unit that is connected to the actuator and the external force detection sensor without a communication network, the head unit being configured to control the actuator based on a sensing result from the external force detection sensor when a pickup request signal that is a signal requesting pickup of the workpiece is received, and a control device that is connected to the head unit over the communication network, the control device being configured to transmit the pickup request signal to the head unit.

Abstract: A robotic surgical system includes a surgical tool including a drive housing having first and second ends, a carriage movably mounted to the drive housing, and an elongate shaft extending from the carriage and penetrating the first end, the shaft having an end effector arranged at a distal end. An instrument driver is arranged at an end of a robotic arm and includes a body having proximal and distal ends and defining a central aperture extending between the proximal and distal ends, the shaft and the end effector penetrate the instrument driver by extending through the central aperture, an outer housing extending between the proximal and distal ends, a tool drive assembly provided at the proximal end and extending into the outer housing, and a drive motor operatively coupled to the tool drive assembly and operable to cause the tool drive assembly to rotate relative to the outer housing.

Abstract: Provided is an elevator control device capable of calling attention to contact between a user and an autonomous moving body in an elevator shared by the user and the autonomous moving body. The elevator control device includes an elevator notification control unit configured to causes, based on a call for an elevator from an autonomous moving body, equipment provided in a hall of the elevator of a floor on which the autonomous moving body is present or equipment provided in a car of the elevator to provide notification of information indicating that the autonomous moving body boards or disembarks from the car.

Abstract: A modular robot system is capable of being configured to allow a plurality of cube-shaped unit robots to be coupled to one another. The modular robot system has N cube-shaped unit robots (where N is an integer greater than 2), each cube-shaped unit robot including: a cube-shaped housing; a step motor located inside the housing; and a controller located inside the housing to control the step motor, wherein the housing has a mounting groove formed on one surface thereof to mount a rotary body rotating by a rotary shaft of the step motor thereon and connection grooves with the same shape as each other formed on the five surfaces thereof, so that through connectors mounted on the connection grooves, one cube-shaped unit robot is connectable to another cube-shaped unit robot.

Abstract: Disclosed is a visual and spatial programming system for robot navigation and robot-IoT task authoring. Programmable mobile robots serve as binding agents to link stationary IoT devices and perform collaborative tasks. Three key elements of robot task planning (human-robot-IoT) are coherently connected with one single smartphone device. Users can perform visual task authoring in an analogous manner to the real tasks that they would like the robot to perform with using an augmented reality interface. The mobile device mediates interactions between the user, robot(s), and IoT device-oriented tasks, guiding the path planning execution with Simultaneous Localization and Mapping (SLAM) to enable robust room-scale navigation and interactive task authoring.

Abstract: A robot control apparatus includes a drive controller configured to control a plurality of motors which are configured to drive a plurality of link mechanisms of a parallel link robot, respectively, and abnormality determination circuitry configured to determine based on state data of the plurality of motors whether at least one of collision of the parallel link robot and dislocation in the link mechanisms occurs.

Abstract: The present disclosure provides a flexible surgical instrument system, comprising: a flexible surgical instrument comprising: a distal structural body comprising at least one distal structural segment comprising a distal fixing disk and structural backbones; a proximal structural body comprising at least one proximal structural segment comprising a proximal fixing disk, structural backbones, and driving backbones, the structural backbones of the distal structural segment being securely connected to or the same as corresponding structural backbones of the proximal structural segment; and a driving unit comprising a plurality of linear motion mechanisms operable to cooperatively push-pull the driving backbones to turn the proximal structural segment, each linear motion mechanism comprising an input end to receive a first linear motion; and a sterile barrier disposed at a proximal side of the plurality of linear motion mechanisms and operable to transfer the first linear motions to the input ends, respectively.

Abstract: In a robot system provided with an articulated arm, information showing whether or not an operator holds one or more of a plurality of arms of the articulated arm. An operator's holding state of the arms are determined based on the detected information. Based on results of the determination, the rotation of motors provided at axes (joints) is controlled for selectively controlling a constrained state which constrains the rotation of the axes and release of the constrained state.

Abstract: A method of detecting a substrate hold hand optical axis deviation includes: acquiring a hand reference turning position at which an ideal optical axis extends in a horizontal first direction; performing a first search processing; performing a second search processing similar to the first search processing to a second target body; and detecting an optical axis inclination from the ideal optical axis based on a difference between the positions detected in the first search processing and the second search processing. A distance in the second direction from the turning axis to the first target body is equal to a distance in the second direction from the turning axis to the second target body. On the hand, an intersecting position between the optical axis and the first target body is different from an intersecting position between the optical axis and the second target body.

Abstract: A robot system includes robot bodies, operation devices each configured to accept operation and generate operational information for causing the robot body to operate, motion controllers configured to control operation of the corresponding robot body in response to the operational information, operation target selectors configured to receive an operation for selecting any of the robot bodies and request a permission to operate the selected robot body based on the operational information from the corresponding operation device, and an operation permitting device having a determinator configured to receive the permission request from the operation target selector and determine whether a permission is to be granted for the permission request. When the permission request is received, and the operation of the robot body selected by the operation target selector based on the operational information from a different operation device is permitted, the determinator prohibits the permission to the permission request.

Abstract: An integrated intelligent system includes a first intelligent electronic device, a second intelligent electronic device, a transferable intelligent control device (TICD) and a cross product bus. The first intelligent electronic device performs a first function and the second intelligent electronic device performs a second function. The cross product bus couples the first intelligent electronic device to the transferable intelligent control device. The TICD partially controls behaviors of the intelligent electronic device by sending commands over the cross product bus to the first intelligent electronic device and the TICD partially controls behaviors of the second intelligent electronic device to perform the second function. The TICD is first attached to the first intelligent electronic device to partially control the behaviors of the first electronic device, then detached from the first electronic device, and then attached to the second intelligent electronic device to perform the second function.

Abstract: A robot including a manipulator includes: an image-pickup acquisition unit configured to acquire an image of an environmental space including a target object to be grasped; and a control unit configured to control a motion performed by the robot, in which the control unit causes the robot to acquire, by the image-pickup acquisition unit, a plurality of information pieces of the target object to be grasped while it moves the robot so that the robot approaches the target object to be grasped, calculates, for each of the information pieces, a grasping position of the target object to be grasped and an index of certainty of the grasping position by using a learned model, and attempts to grasp, by moving the manipulator, the target object to be grasped at a grasping position selected based on a result of the calculation.

Abstract: A roll joint is provided. The roll joint may comprise: a first body; a second body disposed opposite to and spaced apart from the first body; a connection body which is disposed between the first body and the second body and is not in contact with the first body and the second body; and a connection wire member which connects the first body, the second body, and the connection body to one another so as to make a tensegrity structure.

Abstract: A method of controlling a cleaning robot includes: acquiring a marked position of a charging station in a map; controlling the cleaning robot to travel to a front position of the marked position and identifying the charging station; when the charging station is not identified, generating a finding path based on the marked position; and controlling the cleaning robot to travel in accordance with the finding path and identifying the charging station in a traveling process.

Abstract: A robot is provided having a kinematic chain comprising a plurality of joints and links, including a root joint connected to a robot pedestal, and at least one end effector. A plurality of actuators are fixedly mounted on the robot pedestal. A plurality of tendons is connected to a corresponding plurality of actuation points on the kinematic chain and to actuators in the plurality of actuators, arranged to translate actuator position and force to actuation points for tendon-driven joints on the kinematic chain with losses in precision due to variability of tendons in the plurality of tendons. A controller operates the kinematic chain to perform a task. The controller is configured to generate actuator command data in dependence on the actuator states and image data in a manner that compensates for the losses in precision in the tendon-driven mechanisms.