18 Apr

The previous design of mechanical logic has rather low fabrication tolerance, though it works. Here, in order to improve its error tolerance, I created a new desgin with switches on the bistable beam. Theoretically, this design also has much high robustness. I will test this design and run debugging...

18 Apr

This paper reviews several implementations in artificial intelligence that have neuroscience correspondence. The most robotics-related one is the neuro-replay. In RL, especially navigation related tasks, the performance will be better if the agent stores a certain amount of raw data. The data will b...

18 Apr

Improved algorithm with direct observation: Debugging on why range-bearing measurements failed: Attempted algorithm with range-bearing (perfect rnb observation, noisy time update): Attempted algorithm with range-bearing (noisy rnb observation, perfect time update): Still, problem...

18 Apr

Current Progress on Offset To date, the offset connection is able to build a multi-level bookshelf with all finger joints properly added on all edges. This bookshelf would be buildable with lazer cutter and wood. The current implementation is based on the original addConnection() function. I add...

11 Apr

Last quarter I finished building the model of the oscillation period of the mechanical logic in one single snap-through motion. This week I studied the periodic motion of the system and found that as the oscillation becomes stable, the oscillation period tends to decrease over time before converging...

11 Apr

For previous two weeks I was building up the framework of EM-SLAM. The framework is showed as following: And as well as the demo by using direct observation (states can be directly observed with gaussian noise): This demo works properly as expected (although there are some discrepency betwee...

10 Apr

Returning to the problem of measuring the cost of different operations for robot localization, I revisited the Spirals research group's PowerAPI toolkit for software power meters. In the time since I had last used PowerAPI, it appeared that the research group had discontinued development of the too...

09 Apr

Here's an additional Figure 8 performance done by adding flow deck to our lovely crazyflie. Crazyflie wishes you a happy demo day :) Link to the demo

13 Mar

I fixed the project to the lemur GitLab folder and added a README file: https://git.uclalemur.com/dongwei95/Single-Motor-Flyer-Simulation The linearizaiton documentation has been updated into a two-column format: LInearization Comparision with Original.pdf

13 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.