A single AI model trained to control numerous robotic bodies can operate unfamiliar hardware and adapt eerily well to serious injuries. A four-legged robot that keeps crawling even after all four of its legs have been hacked off with a chainsaw is the stuff of nightmares for most people. For Deepak Pathak, cofounder and CEO of the startup Skild AI, the dystopian feat of adaptation is an encouraging sign of a new, more general kind of robotic intelligence. "This is something we call an omni-bodied brain," Pathak tells me. His startup developed the generalist artificial intelligence algorithm to address a key challenge with advancing robotics: "Any robot, any task, one brain.

ANYmal-D combines robotics, artificial intelligence and sports, showing how advanced robots can take on dynamic, fast-paced games. At ETH Zurich's Robotic Systems Lab, engineers have created ANYmal-D, a four-legged robot that can play badminton with people. This project brings together robotics, artificial intelligence and sports, showing how advanced robots can take on dynamic, fast-paced games. ANYmal-D's design and abilities are opening up new possibilities for human-robot collaboration in sports and beyond. Sign up for my FREE CyberGuy Report Get my best tech tips, urgent security alerts, and exclusive deals delivered straight to your inbox.

The idea of a robotic dog that can move on almost any terrain might sound like something from the latest episode of Black Mirror. But as this terrifying footage shows, it has now become a reality. The state-of-the-art robot dog is called Lynx, and is the brainchild of Chinese company, Deep Robotics. Equipped with four wheels instead of paws, the bot can walk, climb, and even backflip on everything from rocks to snow. Deep Robtics hopes that it could be used in search and rescue operations. However, some sceptics have already raised concerns about the four-legged robot.

B2 is a sleek, powerful robot that can run faster, jump higher and carry more weight than its predecessor, the B1. You may have heard of Boston Dynamics, the company that created the famous four-legged robot Spot. Well, now there is another company that is making impressive strides in the field of quadruped robotics. That company is Unitree, a Chinese start-up that has been developing its own line of robot dogs since 2016. Unitree's latest product is the B2, a sleek and powerful robot that can run faster, jump higher, and carry more weight than its predecessor, the B1.

A new Chinese robot W1 by LimX Dynamics combines wheels and legs to conquer any terrain. Have you ever wondered what would happen if you combined a dog and a car? Well, you might get something like W1, a wheeled quadruped robot that can switch between walking and rolling modes depending on the terrain. W1 is the first product of LimX Dynamics, a Chinese company that specializes in legged robotics technology. It is part of a growing trend and demand for legged robots, especially in China, where the government and the industry are investing heavily in robotics and artificial intelligence.

With the increasing computing power, using data-driven approaches to co-design a robot's morphology and controller has become a promising way. However, most existing data-driven methods require training the controller for each morphology to calculate fitness, which is time-consuming. In contrast, the dual-network framework utilizes data collected by individual networks under a specific morphology to train a population network that provides a surrogate function for morphology optimization. This approach replaces the traditional evaluation of a diverse set of candidates, thereby speeding up the training. Despite considerable results, the online training of both networks impedes their performance. To address this issue, we propose a concurrent network framework that combines online and offline reinforcement learning (RL) methods. By leveraging the behavior cloning term in a flexible manner, we achieve an effective combination of both networks. We conducted multiple sets of comparative experiments in the simulator and found that the proposed method effectively addresses issues present in the dual-network framework, leading to overall algorithmic performance improvement. Furthermore, we validated the algorithm on a real robot, demonstrating its feasibility in a practical application.

Chinese tech firm Xiaomi first developed its CyberDog two years ago to compete with rival company Boston Dynamics' Spot. Now it is unveiling an enhanced model, called CyberDog 2, which is even more intelligent and lifelike. Most importantly, it now much more closely resembles a dog than just a robotic creature with legs. That's because it has adopted a number of features resembling a Doberman, including adorable ears. New model: They say every dog has its day -- and that's true for the robotic pooch that has been superseded by this moonwalking, ballet dancing upgrade The four-legged robot is also much smaller and lighter than its predecessor, weighing just 19 lbs (8.9kg) compared to the CyberDog's 31 lbs (14kg).

Scientists have trained a four-legged robot dog to become a goalkeeper – and it has an even better shot-blocking rate than Premier League keepers. The robotic goalie was trained up by scientists at the Hybrid Robotics Lab, University of California, Berkeley. Video footage shows it squat, jump, sidestep and dive to stop shots and move back to its starting position after making a block. It can save 87.5 per cent of shots taken on goal, compared to the average for human keepers of around 69 per cent, the experts say. In all competitions this year, England and Everton number one Jordan Pickford has a save rate of 69.4 per cent, for example. In all competitions this year, England and Everton number one Jordan Pickford has a save rate of 69.4 per cent, for example Reinforcement learning (RL) is a subset of machine learning that allows an AI-driven system (sometimes referred to as an agent) to learn through trial and error using feedback from its actions.

A four-legged robot took only an hour to learn how to walk without stumbling, roughly the same amount of time as newborn foals need. Felix Ruppert and Alexander Badri-Sprowitz at the Max Planck Institute for Intelligent Systems in Stuttgart, Germany, designed the half-metre-high robot called Morti and gave it the ability to teach itself how to walk, rather than to execute a preprogrammed gait. Morti is controlled by an artificial intelligence algorithm that doesn't have much information about the robot's legs, such as the exact shape of each component. The AI mimics networks of neurons that some animals have in their spinal cords and which help them walk by making their muscles contract in a predictable rhythm. The AI generates walking instructions for Morti to follow.

SPOT by boston dynamics can operate on different types of terrain with agility and autonomy, allowing the automation of routine inspection activities and the collection of data in a safe manner. 'these smart platforms for data analysis, such as that created by sprint reply, form the necessary basis for making data acquired during such robot inspections usable and accessible for applications at the archaeological park of pompeii.' 'often the safety conditions within the tunnels dug by grave robbers are extremely precarious, as a consequence of which the use of a robot could signify a breakthrough that would allow us to proceed with greater speed and in total safety,' declares director general gabriel zuchtriegel.