Paper Predicting Flying Robot Dynamics with Deep Learning

Project by Polygence alum Brian

Paper Predicting Flying Robot Dynamics with Deep Learning

Project's result

Brian compiled his work and findings into a research paper that was published by the Journal of Student Research.

They started it from zero. Are you ready to level up with us?

Summary

With the rising importance of robotics in many industries, a way to quickly and easily test how robots move is required in order to help prevent damage to valuable research prototypes. With this in mind, Brian created an adaptable neural network that accurately predicts the movement of quadcopter robotic agents. It produces results within a very small margin of error, which is essential for accurate robot dynamics simulations. This neural network can also be expanded to encompass many more robots and applications given the requisite data.

Nathan

Nathan

Polygence mentor

PhD Doctor of Philosophy candidate

Subjects

Engineering, Computer Science

Expertise

Robotics; Reinforcement learning; Artificial intelligence; Linear Algebra

Brian

Brian

Student

Brian is a 17 year-old high schooler from Palo Alto, CA.

School

Henry M. Gunn High School

Project review

“The Polygence experience was fantastic. My mentor was extremely interesting and helpful. He taught me a lot about his field of study, which I am very grateful for.”