Hi.

Welcome to Robotik. In this series, I will write about topics that I learn during my graduate studies in robotics and machine learning.

Robotics is “the science of perceiving and manipulating the physical world through computer-controlled devices” (Thrun et al., 2005). Robotics combines the knowledge from different disciplines. People who work on robots may work on different things like the mechanical, electrical, or controls designs. Robots come with various sensors. As roboticists, one of the things that we study is how to process the information we get from these sensors, and use them to do something or to make sense about the world.

I will focus my writing on topics like state estimation, localization, planning, and control algorithms. I will also talk about some of the more recent learning-based techniques that are widely used in robotics. Things like deep learning and reinforcement learning, and how we can apply them to solve robotics tasks. The goal of each post is hopefully to give some intuition on how the method works, and to be able to implement and play with it.

I hope this series will provide useful insights, and inspire others to work in robotics - whether you are high schoolers who are interested to play with robots, undergraduates who are looking to do graduate studies in robotics, or if you are just interested to learn more about robotics.

I also care a lot about improving my writing style, so if you think something is not clear, or perhaps I should write about concept A before explaining concept B, please let me know! If you have any other questions or suggestions, do not hesitate to send me an email to reywiyatno@gmail.com.

References

Sebastian Thrun, Wolfram Burgard, and Dieter Fox. Probabilistic Robotics (Intelligent Robotics and Autonomous Agents). The MIT Press, 2005.

Next: Intro to State Estimation and Bayes Filter