A team of Chinese and American engineers has unveiled a unique robot called WHERE-Bot. The robot uses a children's spring toy wrapped in a ring to move. This robot is able to move in all directions and bypass obstacles, relying solely on its mechanical properties. It is completely devoid of any sensors. Instead of traditional navigation methods, the robot uses its own mechanical characteristic

Figure has improved the control system of the Figure 02 humanoid robot to make its gait more human-like. The neural network-based system was fully trained in a simulation using reinforcement learning and then successfully transferred to real robots without additional tuning or retraining. The training process took place in a physical simulator where the walking of a huge number of virtual copi