The idea of soccer playing robots is not new. In fact, there are annual competitions that allow various teams to test their soccer bots. Hybrid Robotics have programmed a quadrupedal robot with deep learning for goalkeeping. Their framework enables robots to intercept balls flying to different regions of the goal.
For this project, a Mini Cheetah robot was used. As the researchers explain:
The first component of the framework contains multiple control policies for distinct locomotion skills, which can be used to cover different regions of the goal. Each control policy enables the robot to track random parametric end-effector trajectories while performing one specific locomotion skill, such as jump, dive, and sidestep. These skills are then utilized by the second part of the framework which is a high-level planner to determine a desired skill and end-effector trajectory in order to intercept a ball flying to different regions of the goal.
As you can see in the above video, the robot is capable of making some spectacular saves.
[HT]
