Abstract: A BodyMap matrix for a pose includes elements representing Euclidean distances between markers on the object. The BodyMap matrix can be normalized and visualized using a grayscale or mesh image, enabling a user to easily interpret the pose. The pose is characterized in a low-dimensional space by determining the singular values of the BodyMap matrix for the pose and using a small set of dominant singular values to characterize and visually represent the pose. A candidate pose is classified in a low-dimensional space by comparing the characterization of the candidate pose to characterizations of known poses and determining which known pose is most similar to the candidate pose. Determining the similarity of the candidate pose to the known poses is accomplished through distance calculations, including the calculation of Mahalanobis distances from the characterization of the candidate pose to characterizations of known poses and their noisy variations.

Abstract: A system and method is disclosed for controlling a robot having at least two legs, the robot subjected to an event such as a push that requires the robot to take a step to prevent a fall. In one embodiment, a current capture point is determined, where the current capture point indicates a location on a ground surface that is the current best estimate of a stepping location for avoiding a fall and for reaching a stopped state. The robot is controlled to take a step toward the current capture point. After taking the step, if the robot fails to reach a stopped state without taking any additional steps, an updated current capture point is determined based on the state of the robot after taking the step. The current capture points can be stored in a capture point memory and initialized based on a model of the robot.

Abstract: Kinematic quantification of gait asymmetry is achieved by plotting the values of the angles of corresponding joints and then comparing the resulting figure to the figure that would have been produced based on a perfectly symmetrical gait. The comparison is based on geometric characteristics that are calculated based on the figures.

Abstract: A system and method are presented to provide assist to a user by means of an exoskeleton with a controller capable of making the exoskeleton display active impedance. The exoskeleton assists the user by reducing the muscle effort required by the user to move his or her extremities. In one embodiment, a single-degree-of-freedom (1-DOF) exoskeleton assists a user with single-joint movement using an active impedance controller. In another embodiment, a multiple-degree-of-freedom (multi-DOF) exoskeleton assists a user with multiple-joint movement using an active impedance controller.

Abstract: A legged robot subjected to a force is controlled by determining an instantaneous capture point where the robot will step with a swing leg to reach a balanced home position, the balanced home position being a state in which the Center of Mass remains substantially over the Center of Pressure and the robot is able to maintain its balance indefinitely. The capture point can be determined using a Linear Inverted Pendulum Plus Flywheel (LIPPF) model of the robot. The LIPPF model includes a flywheel with a mass and a rotational inertia, and a variable length leg link. A torque profile is applied to the flywheel and a set of capture points is determined based on this torque profile An experimentally determined error value can be added to a capture point that is determined based on the model to account for differences between an actual robot and the model.

Abstract: A BodyMap matrix for a pose includes elements representing Euclidean distances between markers on the object. The BodyMap matrix can be normalized and visualized using a grayscale or mesh image, enabling a user to easily interpret the pose. The pose is characterized in a low-dimensional space by determining the singular values of the BodyMap matrix for the pose and using a small set of dominant singular values to characterize and visually represent the pose. A candidate pose is classified in a low-dimensional space by comparing the characterization of the candidate pose to characterizations of known poses and determining which known pose is most similar to the candidate pose. Determining the similarity of the candidate pose to the known poses is accomplished through distance calculations, including the calculation of Mahalanobis distances from the characterization of the candidate pose to characterizations of known poses and their noisy variations.

Abstract: Systems and methods are presented that enable a legged robot to maintain its balance when subjected to an unexpected force. In the reflex phase, the robot withstands the immediate effect of the force by yielding to it. In one embodiment, during the reflex phase, the control system determines an instruction that will cause the robot to perform a movement that generates a negative rate of change of the robot's angular momentum at its centroid in a magnitude large enough to compensate for the destabilizing effect of the force. In the recovery phase, the robot recovers its posture after having moved during the reflex phase. In one embodiment, the robot returns to a statically stable upright posture that maximizes the robot's potential energy. In one embodiment, during the recovery phase, the control system determines an instruction that will cause the robot to perform a movement that increases its potential energy.

Abstract: Systems and methods are presented that use the rate of change of a legged robot's centroidal angular momentum ({dot over (H)}G) in order to maintain or improve the robot's balance. In one embodiment, a control system determines the current value of {dot over (H)}G, compares this value to a threshold value, and determines an instruction to send to the robot. Executing the instruction causes the robot to remain stable or become more stable. Systems and methods are also presented that use a value derived from {dot over (H)}G in order to maintain or improve the robot's balance. In one embodiment, a control system determines the location of the Zero Rate of change of Angular Momentum (ZRAM) point (A), determines the distance between A and the location of the center of pressure of the resultant ground force, compares this value to a threshold value, and determines an instruction to send to the robot.

Abstract: Kinematic quantification of gait asymmetry is achieved by plotting the values of the angles of corresponding joints and then comparing the resulting figure to the figure that would have been produced based on a perfectly symmetrical gait. The comparison is based on geometric characteristics that are calculated based on the figures.