Week 4 Update (10/16 - 10/20)

This week's progress was a continuation of the previous week's research in preparation for the Midterm Exam. Each member of the team was responsible for research, memorization, and hypothetical application of their algorithm to a specific problem related to the project. ROS2 installation on the PC is still underway, working through issues with Wi-Fi connection.

Due to the nature of the research and the fact that the scheduled Wednesday meeting was set aside for the actual Midterm Exam, the total hours logged for the team this week was: 16 hours.

Below are screenshots and photos documenting what was accomplished this week.

Fig 1-4 document the algorithms chosen by the team to present for their midterms. 


Fig 1. Otsu's Method. This algorithm is used to determine the perceived pixels into  
two categories: foreground and background.

Fig 2. Watershed Algorithm. Similar to Otsu's method, this algorithm is an integral part of   
the image segmentation process, which will come in use towards the end of the project.


Fig 3. Monte Carlo Localization. Given a map of the environment, this algorithm estimates   
the position and orientation of a robot as it moves and senses the environment.



Fig 4. EKF-SLAM (Extended Kalman Filter-Simultaneous Location And Mapping) Algorithm.
This algorithm estimates the trajectory of a robot and builds a surrounding map environment using sensor readings

Comments

Post a Comment

Popular posts from this blog

Week 9 Update (11/27 - 12/1)

Image
This week's progress centered around troubleshooting issues and then starting to alter our existing attempts at Ackermann Steering to work without any additional axles or parts to the simulation. Progress this week could have been minimal as going to the desktop on Wednesday led to the discovery that the Wifi Dongle attached to the monitor was no longer working. After much troubleshooting, we ultimately discovered that an unknown party unplugged the Wifi Dongle we were using and replaced it with a broken one; likely thinking that the broken one was a usb to connect a wireless keyboard and mouse. Solving the issue allowed us to begin reworking the current Ackermann model we created (which accidentally mmade the little robot into a helicopter). We aim to continue development on the reworked Ackermann model -- and hopefully have it done over the break -- so that the next semester can focus on the next phase of the project. The total hours logged for this week: 19 hours. Below are imag
Read more

Week 7 Update (2/19-2/23)

Image
This week showed progress in the development of our existing Move cpp node, and the creation of our new MoveWithLidar.xml behavior tree. We did a bit of restructuring to organize all functionality in our node, and logic in our behavior tree, which is proving much more helpful and efficient. We now have logic implemented in place of a basic loop with repeating hard-coded movement commands. Initially, we used a "go until you see a wall, stop, reverse until you see a wall, repeat" logic tree to test out Lidar scope and limitations. Through many trials, we learned a lot about the 360 scope of the lidar, as well as some errors in the structure of our code (ie. mixing logic between our node and bt). We narrowed the scope of the Lidar to make decisions only on input from an 11-1 o'clock range, so a side parallel wall will not trigger as an obstacle.  Additionally, this Monday we also received access to the actual Lidar sensor, and will being testing and implementation during Wee
Read more

Week 8 Update (11/13 - 11/17)

Image
This week's progress centered around updating our current simulation model to fit the physical models Ackermann Steering method. Progress this week was not major as many attempts to reconfigure the front wheels for more accurate steering were made, with advancements appearing near the end. We are continuing the development of the simulations Ackermann Steering and from there will begin programming a set path for the robot to move, additionally, the controller for the simulation may have to be updated to work with the new steering. The total hours logged for this week: 20 hours. Below are images and videos documenting our progress: Fig 1. Front Axle Testing Fig 2. Applying forces to the robot Fig 3. More forces
Read more