Abstract: A method performed by an electronic device, includes: obtaining an image of a set of markers; based on the image, detecting an arrangement of the set of markers; based on the arrangement of the set of markers, performing a measurement about a deformation of the set of markers; based on the measurement about the deformation of the set of markers, generating a plurality of signals; transforming the plurality of signals to a plurality of input commands. The plurality of input commands are used to control the electronic device.

Abstract: Provided is a method for training a hypernetwork to provide a policy for use on a previously-unseen task. The hypernetwork may be trained at a robot factory and then shipped with a robot. At the point of deployment, the robot may be given a context for the previously-unseen task. The robot then uses the context and the hypernetwork to create a policy for performing the previously-unseen task. The policy represents an artificial intelligence machine generated for the previously-unseen task.

Abstract: Systems and methods relating to tactile dexterity and control are disclosed. In one embodiment, a method of manipulating an object based on tactile sensing includes sensing an object by receiving signals from a tactile sensor of an end effector of a robotic system in contact with the object, controlling a contact state by operating the end effector to enforce a desired contact condition between the end effector and the object, estimating a pose of the object based on the received signals, and planning at least one trajectory of the object based on the estimated pose of the object and a desired pose of the object.

Abstract: Provided are a robotic device and a method for identifying a property of an object. The method may include obtaining sensor data from at least one sensor, identifying, using the sensor data, a property of interest of an object, training, using one or more neural networks, a model to predict the uncertainty about the next state of the object based on an action, and based on identifying the uncertainty about the next state of the object, controlling a movement of a robotic element to perform the action.

Abstract: Systems and methods relating to tactile dexterity and control are disclosed. In one embodiment, a method of manipulating an object based on tactile sensing includes sensing an object by receiving signals from a tactile sensor of an end effector of a robotic system in contact with the object, controlling a contact state by operating the end effector to enforce a desired contact condition between the end effector and the object, estimating a pose of the object based on the received signals, and planning at least one trajectory of the object based on the estimated pose of the object and a desired pose of the object.