ASU Robot learns to shoot hoops

ASU Interactive Robotics Lab:  The video shows a bi-manual robot that learns to throw a ball into the hoop using reinforcement learning. A novel reinforcement learning algorithm "Sparse Latent Space Policy Search" allows the robot to learn the task within only about 2 hours.

The robot repeatedly throws the ball and receives a reward based on the distance of the ball to the center of the hoop. Algorithmic details about the method can be found here: 

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

Schmalz Technology Development - The Right Gripper for Every Task

Schmalz Technology Development - The Right Gripper for Every Task

In order to interact with their environment and perform the tasks, lightweight robots, like all industrial robots, depend on tools - and in many cases these are vacuum grippers. These form the interface to the workpiece and are therefore a decisive part of the overall system. With their help, the robots can pick up, move, position, process, sort, stack and deposit a wide variety of goods and components. Vacuum gripping systems allow particularly gentle handling of workpieces, a compact and space-saving system design and gripping from above. Precisely because the object does not have to be gripped, the vacuum suction cupenables gapless positioning next to each other.