*Mar*

For the last week, I was back to Mechanical Logic project and trained Mori for mechanical logic fabrication. For the next few month, I plan to build an integrated robot composed of ML.

*Mar*

All the related codes for Crazyflie project is now on our gitlab: Crazyflie_ros This is a cloned version of whoeing's crazyflie repository with modified launch files compatible with our motion capture system vrpn_client_ros This is the modified version of vrpn_client_ros package that does t...

*Mar*

Attached is a simple demo on one-step update of EM-SLAM algorithm. Note that the robot has only one observation at the begining, and then with an EM algorithm, the landmarks will converge to a certain configuration, but not exact position due to the prior guess of robot state has error. With a corre...

*Mar*

This past week, I have finished writing the draft of the report of the fabrication of a mechanical oscillator with a monostable beam. Then, I started to work on the new project which aims to produce an integrated robot with the system of a mechanical oscillator with Wenzhohng. To begin with, I learn...

*Mar*

This week, while I was writing a python script to generate a trajectory for crazyflie I realized the extrenal position data is not published properly. This command that generates rqt_graph helped me to visualize the published ROS nodes connections and to fix my code. Now applying the optitrack data...

*Mar*

This week I adapted the visualization script for a quadcopter from https://github.com/gibiansky to my single-motor model. The animation helps to determine the tipping point where the drone starts to flip.The blue dot represents the propeller and the line on top represents the general thrust magnitud...

*Mar*

After weeks of adjustments, the ROCO should be able to perform any kinds of multi-faces connection.Part1: How to interpret the angles of connection: When user performs c.addConnection(("B","l"),("A","l"), angle=X), the interpretation is that: (1) Face B (the first argument) is stacked above Face...

*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...