A humanoid robot has transformed from a nimble dancer to a martial arts master. In a stunning display of technological advancement, China's Unitree Robotics has unveiled its latest feat, a humanoid robot that can perform kung fu moves with astonishing precision and balance. The G1, Unitree's compact humanoid robot has transformed from a nimble dancer to a martial arts master, showcasing the rapid progress in robotics and artificial intelligence. Unitree's approach to developing the G1's skills is as fascinating as the robot itself. GET SECURITY ALERTS & EXPERT TECH TIPS -- SIGN UP FOR KURT'S THE CYBERGUY REPORT NOW The process begins in a virtual environment using Nvidia's Isaac Simulator, whereby the robot learns complex behaviors before it even exists in physical form.

Optimus Gen 2 is Tesla's second-generation humanoid robot. Tesla, the company known for its electric cars, solar panels and batteries, has also been working hard on developing humanoid robots that can perform various tasks and interact with humans. The company has recently unveiled its latest version of its robot, called Optimus Gen 2, which is lighter, faster, smoother and more capable than its predecessor. Optimus Gen 2 is the second generation of Tesla's humanoid robot. It is designed to be a general-purpose machine that can assist humans in various domains, such as manufacturing, construction, healthcare and entertainment.

The goal of RoboCup is to make research in the area of robotics measurable over time, and grow a community that works together to solve increasingly difficult challenges over the years. The most ambitious of these challenges it to be able to play against the human world champions in soccer in 2050. To better understand what members of the RoboCup community believes to be the state of the art and the main challenges in the next decade and towards the 2050 game, we developed a survey and distributed it to members of different experience level and background within the community. We present data from 39 responses. Results highlighted that locomotion, awareness and decision-making, and robustness of robots are among those considered of high importance for the community, while human-robot interaction and natural language processing and generation are rated of low in importance and difficulty.

We can proudly say that NCCR Robotics has had a truly transformational effect on the national robotics research landscape, creating novel synergies, strengthening key areas, and adding a unique signature that made Switzerland prominent and attractive at the international level.

Last week, CLAIRE and euRobotics jointly hosted an All Questions Answered (AQuA) event. This one hour session focussed on humanoid robotics, and participants could ask questions regarding the current and future state of AI, robotics and human augmentation in Europe.

As robots have steadily expanded their operations out of the controlled environments of research labs and into the chaos of real-world architectural infrastructure, getting from point A to point B has become a major challenge -- take stairs, for example. In response, roboticists have developed a number of solutions, from installing rotors so that the robot can helicopter over obstacles or, in Boston Dynamics case, execute backflips that would give Simone Biles pause. And then there's Daniele Pucci, head of the Artificial and Mechanical Intelligence lab at the Italian Institute of Technology, who has taken the audacious step of strapping a fully functional jetpack akin to what Richard Browning developed onto the back of an iRonCub synthetic humanoid with hopes of eventually blasting it into the sky. You'd think we'd have learned our lesson about the dangers of building aerial humanoid robots after our first time through Age of Ultron but Pucci's team believes that such systems could one day act as first responders to the roughly 300 natural disasters that kill around 90,000 people worldwide annually. We've seen a slew of disaster response bots -- some humanoid, some not so much -- emerge from labs for more than a decade, often with varying degrees of success.

To construct a robot that can walk as efficiently and steadily as humans or other legged animals, we develop an enhanced elitist-mutated ant colony optimization~(EACO) algorithm with genetic and crossover operators in real-time applications to humanoid robotics or other legged robots. This work presents promoting global search capability and convergence rate of the EACO applied to humanoid robots in real-time by estimating the expected convergence rate using Markov chain. Furthermore, we put a special focus on the EACO algorithm on a wide range of problems, from ACO, real-coded GAs, GAs with neural networks~(NNs), particle swarm optimization~(PSO) to complex robotics systems including gait synthesis, dynamic modeling of parameterizable trajectories and gait optimization of humanoid robotics. The experimental results illustrate the capability of this method to discover the premature convergence probability, tackle successfully inherent stagnation, and promote the convergence rate of the EACO-based humanoid robotics systems and demonstrated the applicability and the effectiveness of our strategy for solving sophisticated optimization tasks. We found reliable and fast walking gaits with a velocity of up to 0.47m/s using the EACO optimization strategy. These findings have significant implications for understanding and tackling inherent stagnation and poor convergence rate of the EACO and provide new insight into the genetic architectures and control optimization of humanoid robotics.

This is the fifth post in our Startup Spotlight series featuring new robotics companies from around the world. We're inviting representatives from these startups to describe their technologies and how they see the marketplace. The views expressed here are solely those of the author and do not represent positions of IEEE Spectrum or the IEEE. Researchers have long been trying to build robotic hands that mimic the extraordinary capabilities of the human hand. The goal has been a device with size and weight similar to our own hands, capable of performing multiple grasping motions, and powered by advanced controllers.