Abstract: A method and computing system for performing the method are presented. The method may include receiving image information representing an object; identifying a set of one or more matching object recognition templates associated with a set of one or more detection hypotheses. The method may further include selecting a primary detection hypothesis associated with a matching object recognition template; generating a primary candidate region based on the matching object recognition template; determining at least one of: (i) whether the set of one or more matching object recognition templates has a subset of one or more remaining matching templates, or (ii) whether the image information has a portion representing an unmatched region; and generating a safety volume list based on at least one of: (i) the unmatched region, or (ii) one or more additional candidate regions that are generated based on the subset of one or more remaining matching templates.

Abstract: A lab system accesses a first protocol for performance by a first robot in a first lab. The first protocol includes a set of steps, each associated with an operation, reagent, and equipment. For each of one or more steps, the lab system modifies the step by: (1) identifying one or more replacement operations that achieve an equivalent or substantially similar result as a performance of the operation, (2) identifying replacement equipment that operates substantially similarly to the equipment, and/or (3) identifying one or more replacement reagents that, when substituted for the reagent, do not substantially affect the performance of the step. The lab system generates a modified protocol by replacing one or more of the set of steps with the modified steps. The lab system selects a second lab including a second and configures the second robot to perform the modified protocol in the second lab.

Abstract: The disclosure describes various embodiments for detecting an unexpected control state of an autonomous driving system. According to an embodiment, an exemplary method of detecting an unexpected control state of an autonomous driving system include the operations of generating environmental data of a vehicle; determining, by the autonomous driving system, a first control state based on the environmental data of the vehicle; determining, by a reference model, a second control state based on the environmental data, wherein the reference model defines at least one scenario each corresponding to a plurality of expected control states and a state switching condition, and in each of the expected control states corresponding to the scenario, an action of the vehicle in the scenario obeys a traffic rule; and determining the unexpected control state of the autonomous driving system by comparing the first control state with the second control state.

Abstract: A method for detecting a ground attribute of a legged robot includes obtaining a collision audio of a foot of the legged robot with a ground; and detecting a workable level attribute of the ground in a working environment of the legged robot according to the collision audio. The sound of the collision between the foot of the robot and the ground is collected, and the workable level attribute of the ground in the working environment of the legged robot is detected based on the sound, so that the operable level attribute can be effectively used to control the legs of the legged robot. On the one hand, the motion noise of the legged robot can be reduced, and on the other hand, the power consumption of the legged robot can be reduced, thereby increasing its range of motion.

Abstract: In a warning apparatus, a restriction unit performs restriction of the issuance of a warning about a ghost from an issuing unit. A trajectory calculator calculates an estimated trajectory of each of first and second target objects. A cancelling unit cancels the restriction of the issuance of the warning about the ghost from the issuing unit upon determination that a predetermined cancelation condition is satisfied for the first and second target objects. The cancelation condition includes a condition that a passing distance between the first and second target objects is larger than a predetermined distance threshold.

Abstract: A method for interconnecting a first robot with at least one second robot, each robot including at least: a first program, a second program, a third program, the method including the following steps, implemented by the second program after reception of a first message from the third program: conversion of the first message into a second message, the second message being formatted according to a predefined object structure including a field typ_msg indicating a type of the message amongst the types: command, query, or information; transmission of the second message to at least one program amongst: a first program belonging to the same robot, a second program of another robot.

Abstract: A ground reaction force load difference calculation unit configured to calculate a ground reaction force load difference that is an amount of a load relief for a user, on the basis of a first measured value that a weight, based on a weight of the user and a weight of the load reduction device that reduces a load on the user and has a mechanism that holds luggage and is at least worn by the user, is transmitted to a ground contact surface and of a second measured value that a weight based on the weight of the user is transmitted to the ground contact surface; and a torque control unit configured to control, on the basis of the ground reaction force load difference, torque that is output by the load reduction device to reduce the load on the user at an joint of each leg of the user.

Abstract: A method includes generating a parameter of a trajectory associated with a scenario using a path planner. The parameter is generated based on a training dataset. The method includes comparing the parameter of the trajectory against a validation parameter associated with a validation dataset. The validation parameter is based on human-based vehicle driving trajectory data associated with scenarios that satisfy a level of similarity with the scenario. The method further includes determining a level of similarity between the parameter associated with the scenario and the validation parameter associated with the scenarios, and, subsequent to determining that the level of similarity fails to satisfy a similarity threshold, the method concludes with providing training data associated with the scenario to the training dataset so that a subsequent parameter of a subsequent trajectory generated by the path planner and associated with the scenario satisfies the level of similarity against the validation parameter.

Abstract: An automation server accesses a task for a robotic device. The automation server generates motor control commands for the robotic device to complete the task. The automation server transmits, via a network and in a format defined by an Application Program Interface (API), the motor control commands from the automation server to a fleet manager associated with the robotic device, the motor control commands for forwarding from the fleet manager to the robotic device. The automation server receives, from one or more sensors attached to the robotic device and via the network, robotic device sensor data. The automation server receives, from multiple remote sensors and via the network, remote sensor data. The automation server adjusts the generated motor control commands to complete the task based on the robotic device sensor data and the remote sensor data.

Abstract: A biped robot gait control method as well as a robot and a computer readable storage medium are provided. During the movement, the system obtains a current supporting pose of a current supporting leg of the biped robot, and calculates a relative pose between the supporting legs based on the current supporting pose and a preset ideal supporting pose of a next step. The system further calculates modified gait parameters of the next step based on the relative pose between the two supporting legs and a joint distance between left and right ankle joints in an initial state of the biped robot when standing. Finally, the system controls the next supporting leg to move according to the modified gait parameters.

Abstract: A handling appliance, in particular a robot, includes at least one handling device that is movable in at least one direction of movement, a collision protection device configured for limiting contact forces due to collisions of the handling device with objects, and an acquisition device. The collision protection device includes a kinematic system that mechanically enables a relative movement of the handling device relative to the carrier of the handling device and that can be inhibited by at least one actuator device. The acquisition device determines forces acting on the actuator device and/or the handling device and on components of the collision protection device decoupled by the actuator device, and the collision protection device accounts for the forces and, via the actuator device, in the absence of a collision prevents, and in the case of a collision triggers and/or enables, relative movement of the handling device relative to the carrier.

Abstract: A robot interference checking motion planning technique using point sets. The technique uses CAD models of robot arms and obstacles and converts the CAD models to 3D point sets. The 3D point set coordinates are updated at each time step based on robot and obstacle motion. The 3D points are then converted to 3D grid space indices indicating space occupied by any point on any part. The 3D grid space indices are converted to 1D indices and the 1D indices are stored as sets per object and per time step. Interference checking is performed by computing an intersection of the 1D index sets for a given time step. Swept volumes are created by computing a union of the 1D index sets across multiple time steps. The 1D indices are converted back to 3D coordinates to define the 3D shapes of the swept volumes and the 3D locations of any interferences.

Abstract: A method and system for dynamic collision avoidance motion planning for industrial robots. An obstacle avoidance motion optimization routine receives a planned path and obstacle detection data as inputs, and computes a commanded robot path which avoids any detected obstacles. Robot joint motions to follow the tool center point path are used by a robot controller to command robot motion. The planning and optimization calculations are performed in a feedback loop which is decoupled from the controller feedback loop which computes robot commands based on actual robot position. The two feedback loops perform planning, command and control calculations in real time, including responding to dynamic obstacles which may be present in the robot workspace. The optimization calculations include a safety function which efficiently incorporates both relative position and relative velocity of the obstacles with respect to the robot.

Abstract: A total centroid state estimation method as well as a humanoid robot and a computer readable storage medium using the same are provided. The method includes: obtaining a motion state of each real joint of the humanoid robot and a motion state of its floating base, where the floating base is equivalent to a plurality of sequent-connected virtual joints; calculating a joint position, a centroid position, and a rotation matrix of each link in the world coordinate system in sequence using the chain rule of homogeneous multiplication according to the position of the joint corresponding to the link to solve a Jacobian matrix of the centroid of the link; solving a total centroid Jacobian matrix based on the Jacobian matrix of the centroid of each link and the total mass; and calculating the total centroid velocity based on the total centroid Jacobian matrix and other parameters.

Abstract: A humanoid hugging assembly includes a humanoid animatronic that has a torso, a pair of arms and a pair of hands each is disposed on a respective one of the arms. The arms are positionable in a resting position having the arms extending downwardly along the torso and having a palm of each of the hands facing the torso. Each of the arms is positionable in a hugging position has each of the arms is crossed in front of the torso wherein the pair of arms is configured to embrace the user. A motion sensor is integrated into the humanoid animatronic to sense motion of the user approaching the humanoid animatronic. A motion unit is integrated into the humanoid animatronic and the motion unit actuates each of the arms into the hugging position when a predetermined duration of time has passed when motion sensor senses motion.

Abstract: It is an object of the present invention to obtain a work determination apparatus capable of preventing or reducing a time lag between the occurrence and determination of an anomaly in work. A work determination apparatus includes: a sensor data output unit that outputs sensor data with an output interval of an integral multiple of a control period with which a motion of a robot is controlled, the sensor data representing a state of work of the robot; and a determination unit that determines a quality of the work of the robot by inference using a recurrent neural network, based on the sensor data outputted from the sensor data output unit.

Abstract: The present disclosure relates to a method of controlling movement of a cart in response to a change in a travel surface using artificial intelligence and a cart implementing the same, and in a cart robot of one embodiment, an IMU sensor senses a change in a travel surface, and an obstacle sensor senses a distance from an installed object placed in a direction of an advance of the cart robot, to control a moving part of the cart robot.

Abstract: A fitting method includes (a) detecting a first position as a position where fitting of a first object and a second object is determined, (b) moving the first object from the first position toward a determination direction different from a fitting direction and detecting a second position as a position where magnitude of a force applied to the first object reaches a predetermined reference value, and (c) determining that a fitting condition of the first object and the second object is good when a predetermined determination condition including a condition that the second position is within an acceptable position range set according to the first position is satisfied.

Abstract: Systems, methods, and systems are disclosed for a robotic manipulator system including a robotic manipulator, a controller, one or more sensors, and a support structure. The support structure may be non-planar and/or deformable and may be designed to support an object on an upper surface. The one or more sensors may be directed towards the support structure and object. The controller and/or another computing device in communication with the controller may determine geometry of the support structure and may know or determine a compression value of the support structure. Using the compression value and/or geometry of the support structure, the controller may cause the robotic manipulator to grasp the object from the support structure and move the object to a new location.

Abstract: Provided is a process including: obtaining a first set of one or more images generated via an optical gas imaging (OGI) camera and a second set of one or more images generated via a second camera, wherein the first set and the second set correspond to a first location of a plurality of locations in a facility; classifying, via a convolutional neural network (CNN), the first set of one or more images according to whether the one or more images depict a gas leak; and storing a result of classifying the first set in memory.