*Mar*

This week I was trying to derive the mathematical formulation of one-step update for recursive EM-SLAM algorith. I was referring to both batch EM-SLAM paper as well as recursive EM paper for reference, and I figured out a coarse representation of Q-function. While I am still doubt on how to get rid...

*Mar*

I found a paper from DeepMind last year on state representation. This paper integrates state representatin learning with deep reinforcement learning. The authors try differnt loss functions related to state representation, and determine which combination of loss function gives the better performance...

*Feb*

The paper of CoLo has just finished revision for ICRA 2019! We have edited the paper in order to explain things more clearly. After submission, we will continue to work on the communication between robots and cost for each robotic operation: measurement, propagation and communication. Special thanks...

*Feb*

After fabricating the first prototype of a monostable beam, I fabricated a bunch of prototypes of monostable beams with different mechanical properties this week. After the fabrication, I tested the monostability of these prototypes of a monostable beam. As a result of experiments, monostability was...

*Feb*

The control frame is changed such that in the control frame, the propeller lies on the xz plane. The resulting linearization matrices are: Now because the model often crashes with singularity points, it is necessary to convert the Simulink model to a MATLAB script for debugging purpose.

*Feb*

This week I compiled my debugging results into a document. There are 4 blocks that need debugging: the production control, position thrust, flyer (dynamics simulation), and the attitude control block. The main goal of the model is to verfiy the control strategy. Therefore, it is important to have th...

*Feb*

Under Dr.Mehta's suggestion, I enhanced my approach to my optimization problem with the use of fmincon in Matlab. The completion of this task marks the start of our writing stage.

*Feb*

Here is a video of my EKF-SLAM code performing with 1 landmark. The red line is the EKF estimate while the blue and black lines are dead reckoning and true trajectory. I adopted my code from https://github.com/AtsushiSakai/PythonRobotics/blob/master/SLAM/EKFSLAM/ekf_slam.py I hope use my code to l...

*Feb*

This week I was mainly surveying on puplications for recursive EM methods (not restricted to SLAM) in various applications, which is listed below: (1) Online EM algorithm for latent model This paper is more like a tutorial on how to use recursive EM algorithm to estimate parameter and update latent...