Artificial intelligence networks have learnt a new trick: being able to create photo-realistic faces from just a few pixelated dots, adding in features such as eyelashes and wrinkles that can’t even be found in the original.

Before you freak out, it’s good to note this is not some kind of creepy reverse pixelation that can undo blurring, because the faces the AI comes up with are artificial – they don’t belong to real people. But it’s a cool technological step forward from what such networks have been able to do before.

The PULSE (Photo Upsampling via Latent Space Exploration) system can produce photos with up to 64 times greater resolution than the source images, which is 8 times more detailed than earlier methods.

In recent years, many research teams worldwide have been developing and evaluating techniques to enable different locomotion styles in legged robots. One way of training robots to walk like humans or animals is by having them analyze and emulate real-world demonstrations. This approach is known as imitation learning.

Researchers at the University of Edinburgh in Scotland have recently devised a framework for training humanoid robots to walk like humans using human demonstrations. This new framework, presented in a paper pre-published on arXiv, combines imitation learning and deep reinforcement learning techniques with theories of robotic control, in order to achieve natural and dynamic locomotion in humanoid robots.

“The key question we set out to investigate was how to incorporate useful human knowledge in robot locomotion and human motion capture data for imitation into deep reinforcement learning paradigm to advance the autonomous capabilities of legged robots more efficiently,” Chuanyu Yang, one of the researchers who carried out the study, told TechXplore. We proposed two methods of introducing human prior knowledge into a DRL framework.”

In a paper, researchers at DeepMind propose a system that can efficiently navigate virtual city environments it hasn’t seen before.

Robots capable of the sophisticated motions that define advanced physical actions like walking, jumping, and navigating terrain can cost $50,000 or more, making real-world experimentation prohibitively expensive for many.

Now, a collaborative team at the NYU Tandon School of Engineering and the Max Planck Institute for Intelligent Systems (MPI-IS) in Tübingen and Stuttgart, Germany, has designed a relatively low-cost, easy-and-fast-to-assemble quadruped robot called “Solo 8” that can be upgraded and modified, opening the door to sophisticated research and development to teams on limited budgets, including those at startups, smaller labs, or teaching institutions.

The researchers’ work, “An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research,” accepted for publication in Robotics and Automation Letters, will be presented later this month at ICRA, the International Conference on Robotics and Automation, one of the world’s leading robotic conferences, to be held virtually.