Robot Learning Project: Beer pong
نویسنده
چکیده
In this paper we describe how a robotic arm can acquire new skills, and specifically how to play beer pong. We used two different optimization algorithms are described and applied to teach a robot how to play the game beer pong. The first algorithm is the gradient based finite difference method. The second one is the expectation maximization algorithm PoWER. Their performance, consisting of both running time and quality of the result, is compared. Both algorithms are used to determine the necessary parameters of a spline interpolation used to control the ball throwing movement.
منابع مشابه
The Experience of using Micromouse and Robot Ping Pong for Teaching Mechatronics
Micromouse and robotic ping pong have been interesting mechatronic applications for the past decade or more. Recently a number of educational institutions around the world have started using these two ‘fun’ robotic ideas as a basis for a more structured approach to robotic engineering education. At City Polytechnic of Hong Kong regular project work using micromouse has been going on for a numbe...
متن کاملReal-time accurate ball trajectory estimation with "asynchronous" stereo camera system for humanoid Ping-Pong robot
— Temporal asynchrony between two cameras in the vision system is a usual problem in practice. In some vision task such as estimating fast moving targets, the estimation error caused by the tiny temporal asynchrony will become non-ignorable essentials. This paper will address on the asynchrony in the stereo vision system of humanoid Ping-Pong robot, and present a real-time accurate Ping-Pong ba...
متن کاملStroke Motion Learning for a Humanoid Robotic Ping-Pong Player Using a Novel Motion Capture System
Problem statement: Human ping-pong players determine the stroke trajectory according to their experience before the ball enters their court. However, to enable a humanoid robot to select the appropriate stroke motion based on skills learned from 3D motion, important patterns must be generated to simplify the complex 3D motion. Approach: This study developed an effective strategy for teaching pi...
متن کاملA Toolkit for Learning: Technology of the MIT LEGO Robot Design Competition
The LEGO Robot Design Competition at the Massachusetts Institute of Technology is a hands-on, project-based workshop class for undergraduates developed to excite students about robotic technology as they build a competitive autonomous robot of their own design. This paper analyzes two aspects of the technology created for the workshop: the robotic contest specifications and the hardware and sof...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2013