Posted on

Akash’s Individual Status Report 27th April

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

I got the communications working last week but this week I had to integrate it with ROS and have it done as a Node so we can use it for communications. As I was traveling for an award ceremony from Thursday to Saturday, I worked really hard before Thursday to get this completely integrated. Challenges were to make it completely fault-tolerant and detect disconnections and new connections on both ends. Taking Distributed Systems helped with this. Moreover, I had previously just sent strings but since we need to send a grid between the hexapods, I had to modify it to be able to send 2d arrays. I also implemented a heartbeat system to detect faults in communication.
|• Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

In terms of communication, I am on schedule. Overall we are behind schedule as we are still integrating right now.

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

At this point, it’s just going to be the 3 of us working very hard to get a demo up on running before the demo day so the deliverable is just to get the final product done.

Didn’t have any flashy photos for communication so here is some debugging output while I was testing the sytem
Posted on

Team Status Report 20th April

•What are the most significant risks that could jeopardize the success of theproject? How are these risks being managed? What contingency plans are ready?

Our most significant risk at this point is not having enough time for us to finish integration. This risk has been managed by having us work on different parts of the project parallel leading us to just need to just integrate and test the search algorithm over the next week. Contingency plans are various simplifications we can make to the search algorithm to complete our final demo.

• Were any changes made to the existing design of the system (requirements,block diagram, system spec, etc)? Why was this change necessary, what costsdoes the change incur, and how will these costs be mitigated going forward?

We switched back to using SLAM cause we got it working and we figured out how to get SLAM and our object detection working together, hence we didn’t need to pivot to a magnetometer which was a great finding. SLAM also gives us accurate heading data which helps our search algorithm. Additionally, we are now no longer running an image publisher node and instead launching a hardware accelerated realsense camera node within our node container alongside yolov8 and VSLAM

• Provide an updated schedule if changes have occurred.
Next week’s sole focus right now is integration and final testings, we have most of the components we need for our project individually but we need to combine them together.

• This is also the place to put some photos of your progress or to brag about athe component you got working.

Slam and Object Detection working

Two hexapods assembled and beginning to test communication and collaborative behavior.

https://docs.google.com/presentation/d/146rbdmwq4HQAA4EFEV7s1tSQf6OJx3z_CFxVmjaCUdc/edit#slide=id.p

Posted on

Akash’s Individual Status Report 20th of April

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


Successfully got inter-hexapod communication working over TCP and worked with Kobe extensively to get the Realsense camera Node in ros working rather than using pyrealsense2 like before. We also got slam and yolov8 finally working simultaneously. Too many hours were spent debugging the above.

Slam and Object Detection working

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

Communications are on schedule, but I’ve just today uncovered a weird bug in our realsense camera node that could derail us, we are remedying it by working around the clock.

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

Since we have the robot physically constructed, hardware setup, and search algorithm implemented we are still mainly bottlenecked by the bug in the camera node. So after getting it resolved, it is mainly completing the integration and demoing it in an actual grid.

• 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?

We recognize that there are quite a few different methods (i.e. learning strategies) for gaining new knowledge — one doesn’t always need to take a class, or read a textbook to learn something new. Informal methods, such as watching an online video or reading a forum post are quite appropriate learning strategies for the acquisition of new knowledge.

I feel like the most important learning strategy I acquired was being able to parse useful information from online forums. Moreover to figure out needed information from poorly written documentation. For example in our project we use Nvidia’s issac ros to facilitate Vslam and object detection, however we had to figure out how to do everything almost from scratch because their examples only work for a particular use case and they don’t explain how to extend it. I also reached out to professors, friends, and others who have worked on similar platforms and their guidance was also essential to our learning.

Posted on

Akash’s Individual Status Report Apr 6th

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

This week was one with a lot of success for our team, Casper, Kobe and I were successfully able to integrate our code to consistently work from Sunday to Wednesday to ultimately be able to be able to be demo something we were proud of. We were able to get one complete robot working detecting a human and maneuvering towards it. After the demo I worked with my teammates to come up with an effective ros architecture and implementing a better state machine. My individual task right now has switched to focusing on communications between the hexapods and getting the other hexapods set up. I’m currently working on the code on of them since we are waiting on more SSD’s to arrive to effectively set up our other 2 Jetsons
• Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

This week we are on track with our modified schedule, we do need to keep the pace up if we need to deliver three robots that are working with each other.
• What deliverables do you hope to complete in the next week?

Deliverables are get the communication done and then setting up our other Jetsons and have them effectively communicate with each other such as heartbeats and messages which can cause state transitions.

Posted on

Akash’s Individual Status Report 3/30

What did you personally accomplish this week on the project? Give files orphotos that demonstrate your progress. Prove to the reader that you put sufficient
A lot of accomplishments got robot controls completely done and integrated, soldered our power connector to power on our hexapod. Our SD card got corrupted so grinded to get our code back to the previous state on an SSD instead. Definitely put like 40+ hours this week lol. Figured out a lot of our previous weird docker container behavior such as aliasing causing us problems.
• 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 barely on track since we finally got our code back to the state it was pre-SD card corruption. So we are barely on track right now. Just need to keep grinding.
• What deliverables do you hope to complete in the next week?
Finish one complete hexapod and get inter hexapod communication code working to an extant.

Posted on

Team Status Report 3/30

What are the most significant risks that could jeopardize the success of theproject? How are these risks being managed? What contingency plans are ready?
The most significant risk is not being able to integrate multiple robots in time. The risks are gonna be managed next week after we finish one robot we’ll split into having some of us working on the communication code and some of us building the robot.
• Were any changes made to the existing design of the system (requirements,block diagram, system spec, etc)? Why was this change necessary, what costsdoes the change incur, and how will these costs be mitigated going forward?Yes, for one we added an SSD to the Jetson. This was necessary because our SD card got corrupted and we lost our data :(. We learned the hard way not to have our docker containers running on an SSD. A difference that was a deviation from our previous design is that we keep the raspberry Pi and uses web sockets to command the pi from the Jetson. We have this completely integrated so we can control the robot very effectively.

• Provide an updated schedule if changes have occurred.
A rough change would be getting interhexapod coordination done between two hexapods in 2 weeks. This should be doable as because of our setbacks we have become pretty fast as setting up our Jetson and raspberry pi to work with our code.
Posted on

Akash’s Individual Status Report 03.23.24

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

Got the controls library working and fixed the batteries. Figured out the battery issue was caused by the batteries discharging too much since they are unprotected so created a pseudo-BMS (battery management system). Following a server-client architecture with a client on the jetson that sends commands to the Raspberry Pi using tcp.
• Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

On track right now since we are very close to integrating the controls with the overall functionality. Need to test on campus wifi soon and finish the integration next week.
• What deliverables do you hope to complete in the next week?
Finish integration and get ready for the demo.

 

Posted on

Team Status Report 3/16/24

What are the most significant risks that could jeopardize the success of the project? How are these risks being managed? What contingency plans are ready?

One very significant risk is that our scope might be too large. Getting the controls, object detection and SLAM working on a single robot is a larger feat than we imagined.In particular, it will be difficult to fully implement SLAM in our system. We are managing this risk by talking with our Autonomous robotics professor who is experienced with the Jetson Orin Nano and Issac Ros. For example, he guided us with the setup of the object detection library and told us about the need for using an SSD.  Depending on how much time we have remaining before our final submission, the contingency plan would be to scale down our localization and use April tags in a small defined environment, rather than a generalizable search algorithm that works in any place.

Were any changes made to the existing design of the system (requirements, block diagram, system spec, etc)? Why was this change necessary, what costs does the change incur, and how will these costs be mitigated going forward?

Not a change but we have realized that we need the Raspberry Pi and cannot eliminate it as libraries that could be used to eliminate its need don’t work effectively. This realization occurred after having spent significant time working towards eliminating the Pi and hence was a costly mistake in terms of. time. However, since we already posses 3 pi’s we don’t require any extra expenditure to use them.

 

Posted on

Akash’s Individual Status Report 3/16/23

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

After spending a lot of hours in trying to get the ros control library to work (Too many including working on it throughout spring break) I got it completely working. However, we soon realized that it was not good enough for our control requirements and was jittery and buggy. this is because the library was made as a hobbyist project by a full-time SWE. This was devastating but we came to the conclusion that it would be better to just refactor the existing freenove library and control it as we know that that library works.
• Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?
I would say I am behind because of the weeks lost going behind the faulty Ros library. This week I have to compensate by working hard to get the existing control library with a server-client architecture working and also get working on the SLAM aspect since the demo date is coming up very soon!
• What deliverables do you hope to complete in the next week?
Get the controls library completely functional and work with Casper and setup the SLAM ros library.

Posted on

Team Status Report for Feb 24 2024

Were any changes made to the existing design of the system (requirements, block diagram, system spec, etc)? Why was this change necessary, what costs does the change incur, and how will these costs be mitigated going forward?

One significant change we made was switching from the Jetson Nano to the Jetson Orin Nano. This was necessary as we became cognizant that the Nano’s compute might not have been sufficient to run ROS, Object Detection, and SLAM simultaneously. We also saw that it took the Nano 40 seconds to run YOLOv7. In terms of costs we incur we were lucky that the Orins were available in inventory so we didn’t have the shell money out of them from our budget. An additional cost is that the Orin needs to be supplied with a higher voltage so we have to upgrade a hexapod’s power supplies to meet its demands.

What are the most significant risks that could jeopardize the success of the project? How are these risks being managed? What contingency plans are ready?

Currently, our greatest troubles has been in bringing up the Jetson and Raspberry Pi boards to run all the relevant software that we need (ie. ROS, YOLO, Jetpack, & Python versions meet requirements). This has taken a bit more time than previously planned, though we have learnt many things.

Since we did just swap from Jetson Nano to Jetson Orin Nano, we will also need to make sure that the Jetson Orin Nano does not have any hidden requirements.

Provide an updated schedule if changes have occurred.We will have to extend our scheduled time for setting up Jetsons (since we changed to the Orin). It’s a good thing we have slack!