Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing an olfaction training program by an online service executing on a server using an AR enabled headset. The objects in the vicinity of the users are identified and highlighted. If the objects have an aroma, the objects are used for olfaction tests. The user interacts with the AR environment to select an object in response to detecting an aroma. The user responses is transmitted back to the online service. The online service determines a subsequent object based on the user response. The subsequent object is then highlighted in the AR environment and the user is prompted to take a subsequent olfaction test.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing an olfaction training program by an online service executing on a server. A first object and an aroma of the first object is transmitted to the client device of a user that presents the first object in a virtual reality environment and disperses the first aroma. In response, the user interacts with the vital reality environment. The user response is transmitted back to the online service. The user response is stored in a database along with the first data and the first aroma. The online service determines a second object and an aroma of the second obj ect based on the user response. The second object and the aroma of the second object is transmitted to the client device.

Abstract: This document describes neuromorphic controllers. In one aspect, a method for controlling one or more joints of a robotic arm includes receiving, by neuromorphic controller comprising a spiking neural network (SNN), a target value of a joint control variable for a joint of the robotic arm. The SNN includes two position proprioceptor neurons, two-speed proprioceptor neurons, a presynaptic inhibitory neuron, an extensor motor neuron, and a flexor motor neuron. The neuromorphic controller updates an actual value of the joint control variable for the joint of the robotic arm based on the target value of the joint control variable. The updating includes generating, by one of the two position proprioceptor neurons, the first spikes to one of the extensors motor neurons or the flexor motor neuron based on a difference between the actual value of the joint control variable and the target value of the joint control variable.