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.
Featured Product
Elmo Motion Control - The Platinum Line, a new era in servo control
Significantly enhanced servo performance, higher EtherCAT networking precision, richer servo operation capabilities, more feedback options, and certified smart Functional Safety. Elmo's industry-leading Platinum line of servo drives provides faster and more enhanced servo performance with wider bandwidth, higher resolutions, and advanced control for better results. Platinum drives offer precise EtherCAT networking, faster cycling, high synchronization, negligible jitters, and near-zero latency. They are fully synchronized to the servo loops and feature-rich feedback support, up to three feedbacks simultaneously (with two absolute encoders working simultaneously). The Platinum Line includes one of the world's smallest Functional Safety, and FSoE-certified servo drives with unique SIL capabilities.
