Week 4 Update (1/29-2/2)

This week focused on preparing to transition from what stage the project is in, and shifting focus to developing an intelligent path-planning algorithm. With the LiDAR simulation entering a nearly completed phase the team will now begin to start the implementation of planning the best possible path to map a given space that the robot will be placed in. As a result, the focus was mainly on researching what the best route for mapping a room could be -- such as looking at search algorithms like Breadth First Search or Depth First Search; and also discussion on how to implement artificial control onto the simulation model due to it only moving with human input via a keyboard. Lastly, the team met with the Mechanical/Electrical team to discuss when code could get put onto the robot itself. We agreed to work independently for the next 4-6 weeks until the robot is assembled, and then our team will have access to the Arduino/Motors to begin implementing and testing software.

Total hours: 15 hours.

Fig 1. Simulation Test Map and RViz Map recreation

Fig 2. Simulation Controller

Fig 3 Book Recommended for AI implementation

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