Category: Casper’s Individual Status Reports

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

In the past week, I created the majority of slides and wrote the script for our final presentation – this included conducting some validations such as battery life calculations. I also spent a few hours creating cue cards and practicing.

In terms of advancing the project, I spent a lot of time deploying, testing, and tuning the search algorithm on the actual Hexapods. Testing on physical hardware has taken longer than anticipated. Furthermore, I suspect that the performance requirements from running both YoloV8 and VSLAM is causing too much resource depletion and overheating, where the Jetson encounters a “Out of Frame Resources” error after running the program too many times. We will need to find the root cause of this error and fix it, since it might be a bigger issue in our demo.

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

We are still quite behind schedule unfortunately, as we need to finish integrating the robot (though we have performed most of the component-wise validations already). We only need to finish fine tuning the search algorithm and add communications, however there might be many roadbumps (ie. the “Out of Frame Resources” error). Our team is prepared to dedicate the next several days on completing the project before our demo.

What deliverables do you hope to complete in the next week?

We have an early demo on Wednesday, so we are planning to finish our integrated robot by Monday ideally. This will involve solving the error caused by running VSLAM and Yolov8 together. If we are still unable to resolve this by early Monday, we may have to pivot off VSLAM and simply just hardcode turns and movements.

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

Over this past week (and during Carnival), I was able to write the search algorithm for our Hexapod, which can be seen here. I had to make some modifications in behaviour compared to our simulated search algorithm due to some physical constraints that we did not have in the simulation. Furthermore, I was able to assemble and 3D print all the required parts for a second Hexapod, as well as setup the Raspberry Pi for actuation. 

What deliverables do you hope to complete in the next week?

In this next week, I am planning to test and polish up the search algorithm on the Hexapod. This will involve interfacing and calibrating the compass bearings provided from the VSLAM library.

I am also the speaker for our final presentation this week, so I will need to prepare the slide deck and script.

Finally, I will work with the rest of the team in integrating all the Hexapod systems together (ie. image detection, search algorithm communication) then begin validating the whole system.

As you’ve designed, implemented and debugged your project, what new tools or new knowledge did you find it necessary to learn to be able to accomplish these tasks? What learning strategies did you use to acquire this new knowledge?

Being completely new to robotics before this capstone, I learned a lot about ROS throughout this project! I did so through auditing the 18448 class, as well as reading documentation as well as video tutorials.

Although I already knew the fundamentals, I also learned a lot more about 3D printing, as well as all the issues that come with it and how to debug them (ie. bed leveling, nozzle temperature, filament type). A majority of this learning came from simple trial and error, as well as asking others more knowledgeable about the issues that I encountered.

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

I encountered a few blockers this week, which meant I did not get to get as much done as I want unfortunately. Since we are still working on finalizing the controls for the robot, I decided to wait on implementing SLAM. Instead, I have been helping Akash on tuning the Hexapods with the ROS library that we found, but we have decided to pivot as the library does not seem to be super reliable. I have also been doing a lot of learning into Docker containers and ROS, since I am not super knowledgeable, by completing some assignments from relevant robotics courses on my own Jetson Nano.

Additionally, since we are using stereo cameras on our robots now, I designed and printed some retrofit mounts for the camera, which can be seen in the photos.

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

I think we are falling a bit behind schedule, as we will need to implement SLAM fairly soon. However, we have redefined our MVP to be simpler, such that we do not necessarily need SLAM for the product to work – this means that we will not have the Medbot be able to track other bots. However, we will still endeavour to have this done by demo.

What deliverables do you hope to complete in the next week?

This week, I will help Akash in finalizing the controls algorithm, which involves redesigning the Freenove library. Hopefully after that is complete, I can begin working on SLAM.

Once we decide on the power bank / battery pack for the Jetson, I will also design a mount for that.

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

Over the past week(s), I was able to deploy Isaac ROS YOLOv8 on the Jetson Orin Nano – it took a while to setup all the dependencies as well as understand how to use Docker containers. Isaac ROS YOLOv8 is able to run within a second or so on a simple photo, which is significantly faster than YOLOv7 on the Jetson Nano.

I was also able to complete the simulated search algorithm to include and account for multiple Hexapods, and profile the expected speedups we should see through multiple simulated runs. The example below shows that we should expect to see over a 2x speedup with 3 hexapods. The example on the left simulates the Hexapods without optimized behaviour (walk randomly), and the example on the right simulates the Hexapods with optimized behaviour (avoid places that you have previously walked).

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

I think I am more or less on our original schedule. However, since we failed to account for the work we had to do in SLAM and map merging, I think I will need to put in more effort for the second half of the semester.

What deliverables do you hope to complete in the next week?

For this week, I think I will take the initiative and begin implementing the SLAM and map merging algorithms on the robots, which first involves installing the cameras onto the robot and interfacing it with the Jetson Orin Nanos.

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

Over this past week, I have been spending most of my time on creating the simulated search algorithm, which can be found in our Github, and also in the image below.

Currently, the Python software is able to create and visualize a 2D search grid, and the Hexapod is able to take a random step in each time unit.

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

Unfortunately, I had a fever this past week so was unable to do as much in-person work as I would have liked to; hence, I spent most of my time working on the simulation since I could work at home. As a result, we are slightly behind schedule on getting the Jetsons working and on the robot. Now that I am better this week, I hope to spend more time in the lab rooms completing the hardware setup.

What deliverables do you hope to complete in the next week?

Currently, the Hexapod search algorithm is stateless, so I hope to make some simple optimizations so that it has a better baseline search. I will also need to add functionality such that multiple Hexapods can search efficiently. Then, I will profile speedups in search time vs. number of Hexapods.

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

Over this past week, I have spent the majority of my time bringing up the Hexapod. This has involved assembling (which took a surprising amount of hours, calibration of servos, setting up the Raspberry Pi with the relevant software, and testing the control of the robot. In the meanwhile, I also read a lot into SLAM with my team, since we need to consider how the Medbot is able to locate and move to other Hexapods.

The working robot can be seen in action here!

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

I think we are somewhat on schedule. We made a decision to only order one Hexapod rather than all three to give us more budget to pivot in case there was some error. So, we have done everything that we set out on the Gantt chart, but only on one robot rather than 3. We think that the bring up of the remaining Hexapods will be much faster, since we will already have experience and suitable tools.

What deliverables do you hope to complete in the next week?

I am delivering the Design Review presentation in this coming week, so I will be spending a majority of my time working on the slide deck and also script. When

Asides from working on the project proposal presentation this past week, I finalized and made the orders for hardware, such as the Jetson Nanos and camera. I have been doing some readings into distributed search algorithms.

We are currently on schedule, according to our planned Gantt chart. However, we will need to add some additional work to to our current schedule, as we did not factor in SLAM earlier.

We are expecting to receive the Hexapods on Feb 12th, so I hope to assemble the robots in the first few days, then develop and validate the existing controls firmware so that the robots are able to move accurately. I will also do some readings into SLAM along with my other team members.