Abstract: This disclosure relates to a method of controlling a collaborative robot, or “cobot”. According to the disclosed method the “cobot” is controlled so as to make it ready to perform a task in collaboration with the human operator only when the latter is about to move into a work sector to carry out the task collaborating with the robot.

Abstract: An off-line programming apparatus includes a model creation unit that creates three-dimensional models of a robot and a load, a storage unit that stores a dynamic parameter of the load, a graphic creation unit that creates a three-dimensional graphic representing the dynamic parameter based on the dynamic parameter, and a display unit that displays the three-dimensional models of the robot and the load and the three-dimensional graphic. The dynamic parameter includes inertia around three axes that are orthogonal to one another at a centroid of the load. The three-dimensional graphic is a solid defined by dimensions in three directions orthogonal to one another. The graphic creation unit sets a ratio of the dimensions in the three directions of the three-dimensional graphic to a ratio corresponding to a ratio of the inertia around the three axes.

Abstract: There is provided a moving robot including a first light source module and a second light source module respectively project a first light section and a second light section, which are vertical light sections, in front of a moving direction, wherein the first light section and the second light section cross with each other at a predetermined distance in front of the moving robot so as to eliminate a detection dead zone between the first light source module and the second light source module in front of the moving robot to avoid collision with an object during operation.

Abstract: The systems and methods disclosed herein are directed to robotically controlling a medical device to utilize manual skills and techniques developed by surgeons. The system can include an emulator representing a medical device. The system can include at least one detector configured to track the emulator. The system can also include an imaging device configured to track the medical device. The system may be configured to move the medical device to reduce an alignment offset between the location of the emulator and the location of the medical device, to move the imaging device based on the translational movement of the emulator, and/or to move the medical device based on data indicative of an orientation of the emulator.

Abstract: A teleoperational medical system for performing a medical procedure in a surgical field includes a teleoperational assembly having a plurality of motorized surgical arms configured to assist in a surgical procedure. It also includes an input device configured to receive an input to move all the arms of the plurality of motorized surgical arms to a pre-established position. A processing system is configured to receive the input form the input device and output control signals to each arm of the plurality of motorized surgical arms to move each arm to the pre-established position.

Abstract: A method includes receiving sensor data indicative of a paved surface, and identifying a defect associated with the paved surface based at least in part on the sensor data. The method also includes determining that the defect is of a defect type based on determining that a value associated with the defect is within a value range associated with the defect type. The method further includes generating a command associated with the defect that, when executed by a machine, at least partially remedies the defect. The method also includes providing the command to an electronic device via a network.

Abstract: A multicamera image processing system is disclosed. In various embodiments, image data is received from each of a plurality of sensors associated with a workspace, the image data comprising for each sensor in the plurality of sensors one or both of visual image information and depth information. Image data from the plurality of sensors is merged to generate a merged point cloud data. Segmentation is performed based on visual image data from at least a subset of the sensors in the plurality of sensors to generate a segmentation result. One or both of the merged point cloud data and the segmentation result is/are used to generate a merged three dimensional and segmented view of the workspace.

Abstract: A robot control system includes: a selector configured to perform a selection of a task object from among a plurality of workpieces by using a first vision sensor; and an operation control section configured to control a robot to perform a task on the task object by using a tool. The selection and the task are executed simultaneously and in parallel, the selector transmits the information of the selected task object to the operation control section before the task, and the operation control section controls the robot based on the transmitted information of the task object.

Abstract: The current disclosure may include a mobile robot having an ambulatory system capable of moving the robot at speeds of at least two miles per hour, a machine vision system, a communication system including a speaker that produces human-audible sounds and also configured to conduct wireless communication using a wireless communications link. Such communication may be conducted with a remote server. The robot may include a banking card receiving slot for receiving a banking card and a keypad for receiving a PIN. Some embodiments may include a document scanning and processing system in electronic communication with the communication system. In addition, the robot may use the document scanning and processing system to receive documents from the customer, scan and process the documents from the customer, and transmit information derived from the processing, to the remote server. Such information may serve to facilitate an interaction between the customer and an ATM.

Abstract: An automated method determines a safety zone for a robot. The robot carries out operations along a specified trajectory. For collision-free operation, a safety zone is determined by: dividing the specified trajectory into a plurality of subtrajectories; determining a plurality of fine-grained envelope cuboids around extreme points of each subtrajectory; and determining a number of optimized envelope cuboids from an enlargement of individual fine-grained envelope cuboids in relation to the volume occupied by the enlarged fine-grained envelope cuboids. The optimized envelope cuboids determined in this way form the safety zone for the trajectory. This automated method can be expanded to multiple trajectories of a robot, multiple robots, and replanning a trajectory for an occupied semaphore zone.

Abstract: The present disclosure relates to an autonomous cleaning robot. The autonomous cleaning robot may include a main body (1) and a cleaning assembly. The cleaning assembly is mounted on the main body (1). The cleaning assembly may include a first cleaning subassembly (2) removable and provided on the main body (1). The first cleaning subassembly (2) is moved in the forward direction or the backward direction of the main body (1) when the first cleaning subassembly (2) is loaded or removed from the main body (1). The first cleaning subassembly (2) is removable and connected to the main body (1) through a connecting member.

Abstract: A method of planning a path for an articulated arm of robot includes generating a directed graph corresponding to a joint space of the articulated arm. The directed graph includes a plurality of nodes each corresponding to a joint pose of the articulated arm. The method also includes generating a planned path from a start node associated with a start pose of the articulated arm to an end node associated with a target pose of the articulated arm. The planned path includes a series of movements along the nodes between the start node and the end node. The method also includes determining when the articulated arm can travel to a subsequent node or the target pose, terminating a movement of the articulated arm towards a target node, and initiating a subsequent movement of the articulated arm to move directly to the target pose or the subsequent node.

Abstract: A robot cleaner for performing cleaning using artificial intelligence includes a suction unit configured to suction dust, a driving unit to drive the robot cleaner, a memory configured to store a compensation model for inferring optimal suction output and driving output for cleaning environment information for learning, and a processor configured to acquire cleaning environment information, determine a suction output value and a driving speed of the robot cleaner from the acquired cleaning environment information using the compensation model, control the suction unit to suction the dust with the determined suction output value, and control the driving unit to drive the robot cleaner at the determined driving speed.

Abstract: An image-guided robotic intervention system (“IGRIS”) may be used to perform medical procedures on patients. IGRIS provides a real-time view of patient anatomy, as well as an intended target or targets for the procedures, software that allows a user to plan an approach or trajectory path using either the image or the robotic device, software that allows a user to convert a series of 2D images into a 3D volume, and localizes the 3D volume with respect to real-time images during the procedure. IGRIS may include sensors to estimate pose of the imaging device relative to the patient to improve the performance of that software with respect to runtime, robustness, and accuracy.

Abstract: A mother-child robot cooperative work system and a work method thereof include a mother robot and a charging base0, in which the mother robot is provided with a control unit and a work unit. The system also includes child robot, communicatively coupled to the mother robot. The mother robot performs cleaning for a work area under the control of the control unit, and recognizes cleanable area and assisted cleaning area in a cleaning process. After cleaning work in the cleanable area is completed, the control unit in the mother robot controls the child robot to cooperatively complete the cleaning work in the assisted cleaning area. The mother robot is provided with a child robot pose sensing unit. The unit inputs child robot pose information to the control unit; and the control unit controls the child robot to act as indicated.

Abstract: A management system for a work vehicle, includes: a traveling condition data generation unit configured to generate traveling condition data that causes a work vehicle to enter with forward movement, from an entrance of a workplace to a work point of the workplace, and exit with backward movement, from the work point to an exit of the workplace; and an output unit configured to output the traveling condition data to the work vehicle.

Abstract: A machine tool system is disclosed which can shorten time required for generating a robot program even for a machine tool user who has no experience in using a robot. A machine tool controller includes an operation panel and an interactive program generator, and sets an operation parameter of the robot using a template screen prepared for each stylized operation of the robot. The interactive program generator generates a robot preprogram using the set operation parameter, reads the robot preprogram during execution of a machine tool program, and transfers the program to a robot preprocessor. The robot preprocessor interprets the robot preprogram and outputs a control command to a robot controller.

Abstract: A method and system for automatic maintenance of a machine (2) comprising the steps of receiving (S1) at least one maintenance relevant event (E) from a controller (3) of the machine (2); augmenting (S2) the received event (E) with the event's machine context read from a machine maintenance ontology; matching (S3) the event's machine context with maintenance rules to generate at least one maintenance task (T) comprising an associated task description; and providing (S4) a maintenance schedule for the machine (2) assigning the generated maintenance task (T) to suitable maintenance executing entities (5) on the basis of the task description of the respective maintenance task (T).

Abstract: The present disclosure provides a method for controlling end-portions of a robot. The method includes obtaining joint information of a robot by at least one sensor and determining a first posture of an end-portion of the robot in accordance with the joint information, obtaining end-portion information of the robot by the sensor and obtaining the second posture of the end-portion of the robot including the interference information in accordance with the end-portion information of the robot and the first posture of the end-portion of the robot, and conducting a closed-loop control on the robot in accordance with an error between the second posture of the end-portion of the robot and a predetermined expected posture of the end-portion of the robot.

Abstract: A surgical instrument according to an embodiment may include: a base body including an attachment surface to be attached to the adaptor; an elongated shaft including one end connected to the base body; a treatment tool provided on a side of the other end of the shaft, elongate elements for operating the surgical tool, driven members rotatably provided on the base body and connected with end portions of the elongate elements; a holding member provided such that one end of each driven member is rotatably held by the base body and the other end of each driven member is rotatably held by the holding member; and a movable member provided movable with respect to the holding member and the base body and engageable with an adaptor. The movable member is configured, when moved with respect to the holding member and the base body, to be disengaged from the adaptor.

Abstract: A robot system includes a robot arm driven by an electric motor and a vehicle that is movable and supports the robot arm. A control method includes (a) moving the vehicle to a work station of a first type and (b) driving the robot arm in the work station of the first type. The (a) executes a first operation mode for, in a part of the movement to the work station of the first type, moving the vehicle in a state in which electric power is not supplied to the electric motor, starting supply of the electric power to the electric motor during the movement of the vehicle in the state in which the electric power is not supplied to the electric motor, and arranging the vehicle in the work station of the first type in a state in which the electric power is supplied to the electric motor.

Abstract: A method includes determining that an autonomous vehicle is in a zone associated with one or more zone rules; causing, in response to determining that the autonomous vehicle is in the zone, the autonomous vehicle to operate in a controlled mode of operation associated with the zone rules; determining that the autonomous vehicle has exited the zone; and releasing, in response to determining that the autonomous vehicle has exited the zone, the autonomous vehicle from the controlled mode of operation.

Abstract: A robot system includes a robot, a controller that controls actuation of the robot, and a first external device, wherein the robot has a first member, a second member that pivots relative to the first member, a motor that generates drive power for pivoting the second member relative to the first member, an encoder including a detection unit that detects an amount of rotation of the motor, a control unit that controls actuation of the detection unit, a communication unit that communicates with the controller, and a first device connecting part connected to the first external device, the control unit connected to the detection unit, the communication unit, and the first device connecting part, and a first communication line connecting the communication unit and the controller, and data of the first external device is transmitted to the controller via the first device connecting part and the first communication line.

Abstract: A numerical control system according to the present invention controls machine drive systems included in a machine tool that performs machining using a tool, according to a numerical control program, and includes a coordinate transformation unit that acquires a disturbance force or a disturbance torque applied to each machine drive system, and coordinate-transforms the disturbance force or the disturbance torque into a tool reference coordinate system for output, and an identification unit that calculates cutting process parameters that determine characteristics of a cutting process model and dynamic characteristic parameters that determine characteristics of a dynamics model of the machine tool, using the disturbance force or the disturbance torque output from the coordinate transformation unit, states of the machine drive systems, predetermined equation models, and cutting conditions.

Abstract: A cooperative robotic arm system includes a first robotic arm, a second robotic arm and a controller. The first robotic arm has first working vector. The second robotic arm has second working vector. The controller is configured to: (1) control the first robotic arm and the second robotic arm to stop moving; (2) determine whether a first projection vector of the first working vector projected on a first coordinate axis and a second working vector projected on the first coordinate axis overlaps; (3) when they overlap, determine whether a third projection vector of the first working vector projected on a second coordinate axis and a fourth projection vector of the second working vector projected on the second coordinate axis overlap; and, (4). when they do no overlap, control a controlled-to-moved one of the first robotic arm and the second robotic arm to move along a reset path.

Abstract: An automated vending system includes a physical item storage unit, and a plurality of land-based transportation mechanisms, or vehicles, arranged to store a predicted number and assortment of items to vend. A processing resource can communicate with the plurality of transportation vehicles, and is arranged to support a machine learning module. A plurality of data sources is arranged to provide data to the machine learning module to determine a plurality of respective actions for the plurality of transportation vehicles. The processing resource can communicate respective control instructions to the plurality of transportation vehicles. A selected transportation mechanism which receives the control instruction can operate in response to the control instruction in order to convey the item to a determined vending location.

Abstract: 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.

Abstract: A robot operating device includes a camera that is attached to a distal end of a robot arm or a position adjacent to the distal end and that acquires an image; a display which displays the image acquired by the camera; an operation-accepting unit which accepts an operation that is performed by an operator on the image displayed on the display unit; and a controller which moves the robot arm based on the operation accepted by the operation-accepting unit.

Abstract: A multi-robot system includes a first a mobile cleaning robot that has a local storage device to store a persistent map of an environment, at least one sensor to sense the environment, and a control module. The control module is configured to: control the mobile cleaning robot to navigate in the environment using the persistent map and sensing data provided by the at least one sensor, share the persistent map with a second mobile cleaning robot, and coordinate with the second mobile cleaning robot to perform cleaning tasks.

Abstract: A fastener feeding system and method for automatically delivering fasteners to a plurality of different manufacturing cells in a manufacturing line from a single load point. The fastener feeding system includes a fastener distribution assembly and a transport assembly for selecting and delivering fasteners to the manufacturing cells. Individual fasteners are selected from a fastener reservoir by a robotic manipulator of the fastener distribution assembly, and are placed on a fastener carrier supported on conveying structure extending between the fastener distribution assembly and the manufacturing cells for movement therealong. The fastener carrier is controlled to move along the track to deliver one or more fasteners to a manufacturing cell.

Abstract: A technique for providing reliable control of a robot (304) in a cloud robotics system (300) is disclosed. A computing unit configured to execute a concealment component (100) for concealing delayed or lost commands sent to the robot (304) by a robot controller (302) in the cloud robotics system (300) comprises at least one processor and at least one memory, wherein the at least one memory contains instructions executable by the at least one processor such that the concealment component (100) is operable to detect a missing command expected to be received by the robot (304) from the robot controller (302), the missing command detected based on a delay or loss of the command in a communication path between the robot (304) and the robot controller (302), generate a substitutional command corresponding to an expected instruction of the missing command, and send the substitutional command to the robot (304).

Abstract: An information providing device has an operation program using information on a structure related to a work robot and information on a processing model related to the structure to execute processing of the processing model by the structure in a virtual space. In addition, the information providing device includes a control section for acquiring data of a development target object including at least one of a new structure and a new processing model from an information processing device used by a developer, executing the operation program using the acquired data of the development target object to execute processing by the development target object in the virtual space, and outputting a processing result by the development target object.

Abstract: A robotic surgical instrument, comprising: a shaft; an end effector element; an articulation at a distal end of the shaft for articulating the end effector element, the articulation comprising: a first and second joint permitting the end effector element to adopt a range of configurations relative to a longitudinal axis of the shaft, the first joint being driveable by a first pair of driving elements having a first positional accuracy requirement and the second joint being driveable by a second pair of driving elements having a second positional accuracy requirement lower than the positional accuracy requirement of the first pair of driving elements; and an instrument interface at a proximal end of the shaft, comprising: a chassis formed from the attachment of a first chassis portion to a second chassis portion, the first chassis portion comprising a mounting surface to which the shaft is mounted; wherein the first pair of driving elements are secured relative to the first chassis portion.

Abstract: A method and a device for controlling a number of robots to emergency stop are provided. The method includes arranging multiple position points in a site where robots work and position identifiers corresponding to the position points, and providing corresponding recognizers at bottoms of the robots; when fault signals reported by the robots are detected, determining, according to the fault signals, whether all the robots in the site need to be controlled to emergency stop, wherein if yes, according to current positions and moving speeds of the robots, position points in the site are allocated to the robots as respective emergency stop positions, the robots are controlled to move to the corresponding emergency stop positions, and thereafter the robots are controlled to stop movement. The device comprises a configuration module, a determination module, an allocation module and a control module.

Abstract: A power off delay system and method is configured to delay termination of electrical power to a digital pathology device in a power off condition. If the apparatus includes a UPS, the power off delay system and method delays termination of electrical power when a power switch is turned off and when a catastrophic power failure occurs. During the delay of the termination of electrical power, the digital pathology device is configured to control the scanning stage system and the glass slide conveyor system and the slide rack conveyor system to place each of these systems into a known state and position all glass slides into a known position prior to the termination of electrical power to the digital pathology device. This allows the digital pathology device to resume normal operation upon power up.

Abstract: Systems and methods for remote operating and/or monitoring of a robot are disclosed. In some exemplary implementations, a robot can be communicatively coupled to a remote network. The remote network can send and receive signals with the robot. In some exemplary implementations, the remote network can receive sensor data from the robot, allowing the remote network to determine the context of the robot. In this way, the remote network can respond to assistance requests and also provide operating commands to the robot.

Abstract: Provided is an electronic device. The electronic device may include: a user interface; a processor operatively connected to the user interface; and a memory operatively connected to the processor, wherein the memory may store instructions that, when executed, cause the processor to control the electronic device to: receive an input via the user interface; determine a task including plural actions based on the input; execute a first action among the plural actions of the determined task; obtain context information related to the task while executing the first action; determine at least one first threshold associated with the first action based at least in part on the obtained context information; and determine the result of the first action based on the execution of the first action being completed based on the at least one first threshold.

Abstract: The present disclosure discloses a dispatching method and device, and a non-transitory readable storage medium, and relates to the field of computer technology. The method of the present disclosure includes: obtaining path condition information within a warehouse; calculating pickup time of each candidate robot of a plurality of candidate robots according to a location of the candidate robot and the path condition information; dispatching a target robot to perform a pickup task according to the pickup time of each candidate robot.

Abstract: Aspects of the present invention relate presentation of digital content, in a see-through display, representing a known location in an environment proximate to a head worn computer. Embodiments may involve a first wearable head device configured to be worn by a first person. The first wearable head device may comprise a see-through display. One or more processors may be configured for determining a first geo-spatial location of the first wearable head device and receiving a second geo-spatial location of a second wearable head device configured to be worn by a second person. The see-through display may be configured for presenting a virtual content on the see-through display at a location associated with the second geo-spatial location. The virtual content may be aligned with a vector from the first geo-spatial location to the second geo-spatial location.

Abstract: A slide rack gripper apparatus is provided that simultaneously conveys a plurality of glass slides in the protection of a slide rack within a digital slide scanning apparatus. The slide rack gripper apparatus conveys the plurality of glass slides from a slide rack carousel to a scanning stage for processing. The slide rack gripper includes a first motor attached to a base configured to drive a finger mount attached to the base along a first linear axis. The slide rack gripper apparatus also includes a second motor attached to the finger mount and configured to drive opposing gripper fingers attached to the finger mount along a second linear axis. The second motor is also configured to drive individual gripper fingers along a third linear axis to move the gripper fingers toward each other and away from each other to grasp or release a slide rack.

Abstract: “Feature points” in “point clouds” that are visible to multiple respective cameras (i.e., aspects of objects imaged by the cameras) are reported via wired and/or wireless communication paths to a compositing processor which can determine whether a particular feature point “moved” a certain amount relative to another image. In this way, the compositing processor can determine, e.g., using triangulation and recognition of common features, how much movement occurred and where any particular camera was positioned when a latter image from that camera is captured. Thus, “overlap” of feature points in multiple images is used so that the system can close the loop to generate a SLAM map. The compositing processor, which may be implemented by a server or other device, generates the SLAM map by merging feature point data from multiple imaging devices.

Abstract: The invention relates to a process for producing a dental restoration part using a machine tool (10), especially a dental processing machine intended for a dentist's office, wherein, in a first step, a rotating processing tool (16) rotationally mills or processes or grinds a workpiece (18) while, except from at least one entry and/or exit path, it is in continuous contact with the workpiece (18), i.e. with 0% air battle, by machining the outer profile (19) of the workpiece (18) substantially completely in helical-shape. The invention also relates to a dental processing machine.

Abstract: A robot in a location interacts with a user. The robot includes a camera, an image recognition processor, a microphone and a loudspeaker, a voice assistant, and a wireless transceiver. The robot moves around and creates a model of the location, and recognizes changes. It recognizes objects of interest, beings, and situations. The robot monitors the user and recognizes body language and gesture commands, as well as voice commands. The robot communicates with the user, the TV, and other devices. It may include environment sensors and health status sensors. It acts as a user companion by answering queries, executing commands, and issuing reminders. It may monitor to determine if the user is well. The robot may monitor objects of interest, their placement and their status. When necessary, it communicates with the user.

Abstract: One variation of a method for autonomously scanning and processing a part includes: accessing a part model representing a part positioned in a work zone adjacent a robotic system; retrieving a sanding head translation speed; retrieving a toolpath for execution on the part defining positions, orientations, and target forces applied by the sanding head to the part. The method includes traversing the sanding head along the toolpath, at the sanding head translation speed; reading a sequence of applied forces from a force sensor coupled to the sanding head at positions along the toolpath; and deviating from the toolpath to maintain the set of applied forces within a threshold difference of a sequence of target forces along the toolpath. In one variation of the method, the robotic system executes a toolpath at a duration less than target duration by selectively varying target force and sanding head translation speed across the part.

Abstract: An apparatus includes a robot body, at least one sensor coupled to the robot body and positioned to receive stimuli from a passenger cabin of a vehicle, an actuatable component coupled to the robot body, and a computer coupled to the robot body and communicatively coupled to the sensor and the actuatable component. The computer is programmed to predict an imminent anomalous event in the vehicle based on data from the at least one sensor, and in response to the determination, actuate the actuatable component to remediate the anomalous event.

Abstract: An apparatus for verifying electrical connectivity between a first device and a second device includes: a signal generator configured to generate a first signal having a voltage waveform. under control of a processor; a second device connector configured to transmit the first signal to the second device and acquire a second signal output from the second device in response to the first signal; a processor connector configured to transmit the first and second signals to the processor; a current controller configured to control a magnitude of current such that the first signal has a given current value; and the processor configured to verify the electrical connectivity between the first and second devices based on the first and second signals received through the processor connector.

Abstract: A robot control system and a method for updating camera calibration is presented. The method comprises the robot control system performing a first camera calibration to determine camera calibration information, and outputting a first movement command based on the camera calibration information for a robot operation. The method further comprises outputting, after the first camera calibration, a second movement command to move a calibration pattern within a camera field of view, receiving one or more calibration images, and adding the one or more calibration images to a captured image set. The method further comprises performing a second camera calibration based on calibration images in the captured image set to determine updated camera calibration information, determining whether a deviation between the camera calibration information and the updated camera calibration information exceeds a defined threshold, and outputting a notification signal if the deviation exceeds the defined threshold.

Abstract: An information processing apparatus, an information processing method, and an information medium control motion of a moving body according to position information corresponding to a predetermined array pattern. An information processing apparatus includes an information acquisition unit acquires position information from a sensor configured to read a predetermined array pattern, and a motion control unit controls motion of a first moving body including movement in a real space based on the position information.

Abstract: A gateway retrieval alert device is configured for use in an aircraft ground support system. The gateway retrieval alert device is connected to an intercom gateway, either through a direct wireless connection or through a direct connection to a headset of a tug operator, the headset in turn being wirelessly connected to the intercom gateway. The integrity of the wireless link to the intercom gateway is monitored, and when the integrity of the link falls below a set threshold, an alert is issued. The alert is issued externally to the communication network between the ground crew and pilot.

Abstract: A method for computing joint torques applied by actuators to perform a control of a movement of a robot arm having several degrees of freedom is provided. The method includes the act of providing, by a trajectory generator, trajectory vectors specifying a desired trajectory of the robot arm for each degree of freedom. The trajectory vectors are mapped to corresponding latent representation vectors that capture inherent properties of the robot arm using basis functions with trained parameters. The latent representation vectors are multiplied with trained core tensors to compute the joint torques for each degree of freedom.