Abstract: An autonomous vehicle guidance system enables a partially assembled battery-electric vehicle (BEV) to be guided through an assembly process with the temporary addition of a sensor skid. The partially assembled BEV includes a vehicle body, a vehicle controller coupled to the vehicle body, a battery electrically coupled to the vehicle controller, a sensor skid configured to be coupled under the vehicle body of the BEV. The sensor skid is configured to guide the BEV through an assembly process. The sensor skid includes a skid body configured to be coupled under the vehicle body of the BEV and a plurality of sensors coupled to the skid body. The sensor skid includes a skid controller in communication with the sensors and the vehicle controller. The skid controller is coupled to the sensor skid.

Abstract: An articulated compliance mechanism for use with a support structure includes a carriage and a pair of parallel four-bar linkage arrangements. The arrangements collectively have a first set of links configured to rigidly connect to the support structure, a second set of links rotatably coupled to the carriage a distance from the first set of links, and a third set of links rotatably coupled to and spanning the distance. The compliance mechanism supports and provides the carriage, e.g., a rectangular shaped frame, with a stable equilibrium point using a gravitational restoring force, and provides the carriage with a passive translational degree of freedom along a horizontal axis in response to an input force from an operator. An additional compliance mechanism may be serially connected to provide a passive translational degree of freedom along a vertical axis. A system includes the compliance mechanism and support structure.

Abstract: A robotic system includes a jointed mechanism, position sensors, and a controller. The mechanism has an end-effector, and further includes actively-controlled joints and passive joints that are redundant with the actively-controlled joints. The position sensors are operable for measuring joint positions of the passive joints. The controller is in communication with the position sensors, and is programmed to execute a method to selectively control the actively-controlled joints in response to the measured joint positions using force control and/or a modeled impedance of the robotic mechanism. Possible control modes in impedance control include an Autonomous Mode in which an operator does not physically interact with the end-effector and a Cooperative Control Mode in which the operator physically interacts with the end-effector.

Abstract: A robotic system includes a jointed mechanism, position sensors, and a controller. The mechanism has an end-effector, and further includes actively-controlled joints and passive joints that are redundant with the actively-controlled joints. The position sensors are operable for measuring joint positions of the passive joints. The controller is in communication with the position sensors, and is programmed to execute a method to selectively control the actively-controlled joints in response to the measured joint positions using force control and/or a modeled impedance of the robotic mechanism. Possible control modes in impedance control include an Autonomous Mode in which an operator does not physically interact with the end-effector and a Cooperative Control Mode in which the operator physically interacts with the end-effector.

Abstract: An electromechanical system operates through physical interaction with an operator, and includes a plurality of joints providing multiple degrees of freedom (DOF), including actuated joints and unactuated joints. The unactuated joints are distal with respect to the actuated joints and are in redundant DOF to the actuated joints. The system includes a plurality of actuators each configured to actuate one or more of the actuated joints, and a plurality of sensors each positioned with respect to a respective one of the actuated and unactuated joints. Each sensor is configured to measure corresponding joint data indicative of a position or angle of the respective actuated or unactuated joints. A controller in communication with the sensors receives the measured joint data as feedback signals, generates control signals using the feedback signals, and transmits the control signals to the actuators to thereby control an actuation state of the actuators.

Abstract: A method for classifying a known object in a field of view of a digital camera includes developing a plurality of classifier feature vectors, each classifier feature vector associated with one of a plurality of facet viewing angles of the known object. The digital camera captures an image in a field of view including the known object and an image feature vector is generated based upon said captured image. The image feature vector is compared with each of the plurality of classifier feature vectors and one of the plurality of classifier feature vectors that most closely corresponds to the image feature vector is selected. A pose of the known object relative to the digital camera is determined based upon the selected classifier feature vector.

Abstract: An articulated compliance mechanism for use with a support structure includes a carriage and a pair of parallel four-bar linkage arrangements. The arrangements collectively have a first set of links configured to rigidly connect to the support structure, a second set of links rotatably coupled to the carriage a distance from the first set of links, and a third set of links rotatably coupled to and spanning the distance. The compliance mechanism supports and provides the carriage, e.g., a rectangular shaped frame, with a stable equilibrium point using a gravitational restoring force, and provides the carriage with a passive translational degree of freedom along a horizontal axis in response to an input force from an operator. An additional compliance mechanism may be serially connected to provide a passive translational degree of freedom along a vertical axis. A system includes the compliance mechanism and support structure.

Abstract: A system includes a first camera defining a first camera coordinate system (C1) and configured to acquire a first image of a scene. A range sensor is spaced a first distance from the first camera and defines a range sensor coordinate system (R). A controller is operatively connected to the first camera and range sensor. The controller has a processor and a tangible, non-transitory memory device on which is recorded instructions for executing a method for obtaining a two-dimensional region of interest (u1*, v1*) in the first image, which is a two-dimensional intensity image. The first image is represented by a plurality of first points (u1, v1) in a first image plane. The controller is configured to acquire a range image of the scene with the range sensor. The range image is represented by a plurality of second points (u2, v2, d) in a second image plane.

Abstract: A method for classifying a known object in a field of view of a digital camera includes developing a plurality of classifier feature vectors, each classifier feature vector associated with one of a plurality of facet viewing angles of the known object. The digital camera captures an image in a field of view including the known object and an image feature vector is generated based upon said captured image. The image feature vector is compared with each of the plurality of classifier feature vectors and one of the plurality of classifier feature vectors that most closely corresponds to the image feature vector is selected. A pose of the known object relative to the digital camera is determined based upon the selected classifier feature vector.

Abstract: A human monitoring system includes a plurality of cameras and a visual processor. The plurality of cameras are disposed about a workspace area, where each camera is configured to capture a video feed that includes a plurality of image frames, and the plurality of image frames are time-synchronized between the respective cameras. The visual processor is configured to receive the plurality of image frames from the plurality of vision-based imaging devices and determine an integrity score for each respective image frame. The processor may then isolate a foreground section from two or more of the views, determine a principle body axis for each respective foreground section, and determine a location point according to a weighted least squares function amongst the various principle body axes.

Abstract: A system includes a robotic gripper and a grasp controller. The gripper, which has a sensory matrix that includes a plurality of sensors, executes selected grasp poses with respect to a component in the corresponding method to thereby grasp the component in response to a grasp command signal from the controller. The controller has a touch-screen or other interactive graphical user interface (GUI) which generates a jog signal in response to an input from a user. Sensory maps provide calibrated limits for each sensor contained in the sensory matrix for the selected grasp pose. The controller transmits the grasp command signal to the gripper in response to receipt of the jog signal from the GUI. The GUI may display a jog wheel having icons, including a hub corresponding to a neutral pose of the robotic gripper and icons corresponding to grasp poses arranged around a circumference of the jog wheel.

Abstract: A human monitoring system includes a plurality of cameras and a visual processor. The plurality of cameras are disposed about a workspace area, where each camera is configured to capture a video feed that includes a plurality of image frames, and the plurality of image frames are time-synchronized between the respective cameras. The visual processor is configured to identify the presence of a human within the workspace area from the plurality of image frames, generate a motion track of the human within the workspace area, generate an activity log of one or more activities performed by the human throughout the motion track, and compare the motion track and activity log to an activity template that defines a plurality of required actions. The processor then provides an alert if one or more actions within the activity template are not performed within the workspace area.

Abstract: A human monitoring system includes a plurality of cameras and a visual processor. The plurality of cameras are disposed about a workspace area, where each camera is configured to capture a video feed that includes a plurality of image frames, and the plurality of image frames are time-synchronized between the respective cameras. The visual processor is configured to receive the plurality of image frames from the plurality of vision-based imaging devices and determine an integrity score for each respective image frame. The processor may then isolate a foreground section from two or more of the views, determine a principle body axis for each respective foreground section, and determine a location point according to a weighted least squares function amongst the various principle body axes.

Abstract: A system includes a first camera defining a first camera coordinate system (C1) and configured to acquire a first image of a scene. A range sensor is spaced a first distance from the first camera and defines a range sensor coordinate system (R). A controller is operatively connected to the first camera and range sensor. The controller has a processor and a tangible, non-transitory memory device on which is recorded instructions for executing a method for obtaining a two-dimensional region of interest (u1*, v1*) in the first image, which is a two-dimensional intensity image. The first image is represented by a plurality of first points (u1, v1) in a first image plane. The controller is configured to acquire a range image of the scene with the range sensor. The range image is represented by a plurality of second points (u2, v2, d) in a second image plane.

Abstract: A system includes a robotic gripper and a grasp controller. The gripper, which has a sensory matrix that includes a plurality of sensors, executes selected grasp poses with respect to a component in the corresponding method to thereby grasp the component in response to a grasp command signal from the controller. The controller has a touch-screen or other interactive graphical user interface (GUI) which generates a jog signal in response to an input from a user. Sensory maps provide calibrated limits for each sensor contained in the sensory matrix for the selected grasp pose. The controller transmits the grasp command signal to the gripper in response to receipt of the jog signal from the GUI. The GUI may display a jog wheel having icons, including a hub corresponding to a neutral pose of the robotic gripper and icons corresponding to grasp poses arranged around a circumference of the jog wheel.

Abstract: A system is configured to determine the performance of a braking system for a joint of a robot. The braking system is configured to apply a brake to the joint and a servo system is configured to apply a torque to the joint. The system measures performance data at the joint, identifies a performance parameter, and defines performance regions and limits that are used to evaluate the performance parameter.

Abstract: A method and apparatus for assembling a fuel cell stack is disclosed, wherein the apparatus includes a plurality of dunnage cassettes adapted to cooperate with a plurality of containers, a fixture, and an assembly device to simultaneously assemble a plurality of membrane electrode assemblies together with a plurality of bipolar plates.

Abstract: A mechanical implement adapted for use in an autonomously functioning device, such as a robot arm, and including an active material, such as shape memory polymer, element that when activated and/or deactivated is operable to modify the mechanical impedance of a joint or link in the device.

Abstract: A mechanical gripper adapted for grasping a plurality of differing objects, and comprising a plurality of fingers, wherein each finger includes at least one variable impedance member comprising an active material element, the element, when activated and deactivated, undergoes a reversible change in impedance, and the change in impedance enables the gripper to be advantageously reconfigured, and/or locked in a reconfigured state.

Abstract: A reconfigurable fixture device system, including: a base member; a reconfigurable pad disposed on the base member, wherein the reconfigurable pad comprises a shape memory material configured to selectively conform to a surface contour of a workpiece; an activation device in operative communication with the shape memory material; a controller in operable communication with at least one of the reconfigurable pad, the activation device, and the base member; a plurality of sensors for sensing a parameter associated with at least one of the reconfigurable pad, the base member, the fixture device, and the workpiece, wherein the plurality of sensors is in operable communication with the controller; and an actuator in operable communication with the controller and the at least one of the reconfigurable pad, the base member, the fixture device, and the workpiece.