Popular posts from this blog
Introduction
Hi! In this blog, I will be demonstrating my progress for the last semester of my final year as a Robotics student at Middlesex University. This blog will solely focus on the project development of creating a robotic system that will allow a serial manipulator play air hockey against a human opponent. Currently, this project can be divided into 3 main tasks: Track the location of the puck within the working space during live demo Implement a trajectory prediction in 2-D Cartesian space to identify where the robot should position itself in relation to the position of the puck Create a graphical user interface (GUI) to allow human opponent to easily set up and play a game of air hockey against the robot. By next week, I will research exiting robotic systems to understand what the creator(s) of the system have done to solve such tasks and their reasoning for it. Note: This blog will not start at Week 1 but at Week 14 to coincide with the university calendar. ...
Linear Regression - Bounce Trajectory 2
Hi, In the previous method, I described a method for handling bounce trajectories using Linear Regression. Below is an image showcasing another way to predict a bounce without swapping the axis and the need of creating new coordinates from the point that the slope intercepts the Y-axis. Code explained: 1. Calculate slope between atleast two points, as soon as the puck changes direction and is moving towards the ABB. 2. Using the slope, I predict the y position of the puck at the centre of the table. 3. If the prediction is greater than the table height,the error is calculated. 4. A new trajectory called Yc is created by reflecting the error from the end of the table. Video of two softbots playing with each other using two different methods Immanuel



Comments
Post a Comment