Researchers have developed an automated way to design customized hardware that speeds up a robot's operation. The system, called robomorphic computing, accounts for the robot's physical layout in suggesting an optimized hardware architecture.

Patients with motor dysfunctions are on the rise across Japan as its population continues to age. A researcher has developed a new method of rehabilitation using virtual reality to increase the sense of agency over our body and aid motor skills.

Computer scientists developed a deep learning method to create realistic objects for virtual environments that can be used to train robots. The researchers used TACC's Maverick2 supercomputer to train the generative adversarial network. The network is the first that can produce colored point clouds with fine details at multiple resolutions.

Researchers present an optical flow-based learning process that allows robots to estimate distances through the visual appearance (shape, color, texture) of the objects in view. This artificial intelligence (AI)-based learning strategy increases the navigation skills of small flying drones and entails a new hypothesis on insect intelligence.

Scientists are combining artificial intelligence and advanced computer technology with biological know how to identify insects with supernatural speed. This opens up new possibilities for describing unknown species and for tracking the life of insects across space and time.