Abstract: A sensor is coupled to a barbell and generates data indicating motion of a barbell over time. At least one trained neural network is implemented to detect and count repetitions of an exercise performed with the barbell. The at least one trained neural network detects the repetitions based on the data generated by the sensor, and based on (a) a type of exercise performed with the barbell detected from the received data or provided as labeled data, and/or (b) an identity of a user that performed the exercise as detected from the received data or provided as labeled data.

Abstract: Gripper pads are provided for use, augmentation or retrofitting in a robot manipulator. The gripper pads distinguish a dry adhesive layer with dry adhesive wedges that would interface with an object that is desired to be manipulated. The plurality of dry adhesive wedges is organized in a pattern such that the pattern has at least two different orientations for the direction of the plurality of wedges. The gripper pads further distinguish a sensor array underneath the dry adhesive layer. The data obtained from the sensor array provides an estimate of the shape and size of the contact between the gripper pad and the object when the dry adhesive layer is in contact with the object.

Abstract: Gripper pads are provided for use, augmentation or retrofitting in a robot manipulator. The gripper pads distinguish a dry adhesive layer with dry adhesive wedges that would interface with an object that is desired to be manipulated. The plurality of dry adhesive wedges is organized in a pattern such that the pattern has at least two different orientations for the direction of the plurality of wedges. The gripper pads further distinguish a sensor array underneath the dry adhesive layer. The data obtained from the sensor array provides an estimate of the shape and size of the contact between the gripper pad and the object when the dry adhesive layer is in contact with the object.