The Deep Robotics bionic dog combines AI technology with robotic software, to enable maneuverability in a variety of terrains. Through first-person real-time image transmission and self learning capabilities this robot dog exhibits autonomous and agile movements. High torque density and reverse transmission make it so nothing will keep this little dog down. | Mashable

AI helps robot dogs navigate the real world 🤖🐕️⁠ ⁠ Four-legged robot dogs learned to perform new tricks by practicing in a virtual platform that mimics real-world obstacles. Researchers @MIT developed their training platform “LucidSim” by taking a popular computer simulation software that follows the principles of real-world physics and inserting a generative AI model to produce artificial environments such as a stone pathway. This technology could be a possible shortcut for training robots fa

Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots This autonomous navigation system, developed for Robotic Systems Lab's wheeled-legged quadrupeds, is designed for efficient navigation in large urban environments. Using neural network policies, the unified control system supports smooth gait transitions, intelligent navigation planning, and responsive obstacle avoidance in urban settings. Video source: Robotic Systems Lab: Legged Robotics at ETH Zürich #robotics #tec

Boston Dynamics released a new demonstration video of its Atlas robots navigating a parkour course, complete with synchronized backflips. | CNET

Meet all the robots of Boston Dynamics. | What the Future