As we conclude the Fall 2024 semester, the Duke Robotics Club reflects proudly on the progress we’ve made. This semester was filled with milestones, from transitioning our systems to ROS2 and advancing the design of our new minibot to redesigning electrical systems and conducting essential pool tests. Alongside these technical accomplishments, we onboarded the largest …
Today, in our last pool test of the summer, we completed the gate and buoy tasks in one continuous run. We started with the gate task: submerge, correct yaw for the coin flip, move through the gate, and finally barrel roll. We put the gate in the water in the opposite direction from our previous …
Today we resolved the thruster issue and made more progress towards the gate task. Max and I recently improved our detection rate on the DepthAI camera with color correction to 17Hz and also reduced the latency. This was the result of two optimizations At the pool, we first tested our gate model on the DepthAI …
Today we ran into several issues with the thrusters. Over the last few days, Lilly and I swapped the thruster Arduino from a Nano Every to a Nano with the hope that it would fix the disconnect issues we’ve been having. We also swapped the bottom mono camera for a new one. We had to …
We made more progress towards the gate task. Moving Towards the Gate While the robot is able to move towards the gate in most cases, sometimes, the robot would move too far in the Y direction when it first started moving. Its goal would be to align itself with the red image, but it would …
Today we made significant progress towards completing the gate task. As DepthAI color correction is still a work in progress, we temporarily added a YOLOv7 package to onboard to run our gate model on the main computer and perform detections on the front mono camera’s feed. This had a detection rate of 2.66 Hz, which …
We completed the buoy task. We started by first narrowing the range values used for HSV filtering to avoid picking up on gray and orange-red objects and to instead limit it to just saturated red colors. This significantly reduced false positives. The final CV algorithm can detect the buoy when it is within 5 meters …
Today we finished developing a robust buoy detection algorithm, primarily using HSV filtering and contour matching. Here’s the high-level overview of the process: This has been proven to be a robust and reliable way to detect the buoy, whilst filtering out false positives and avoiding false negatives. We also began to write the task planning …
Today we completed the code to accomplish the barrel roll part of the gate task. Here’s the working sequence: The robot drifts a little in X and Y throughout this process. Roughly, a 2m x 2m area around the robot needs to be clear to avoid running into a wall. With this sequence, the robot …
Since the prequal has been completed, our focus has shifted to completing at least one competition task before we leave. This would be either the gate or the buoy. On days that we’re able to get two lanes, we’ll focus on the gate task. Otherwise, we’ll focus on the buoy task. Today, our main goals …
PREQUAL COMPLETE! Today we completed the prequal. We used the same strategy as outlined in the previous update, but with two important changes: Thus, the robot followed the lane line to the marker, dead reckoned around the marker, and followed the lane line on the way back. This proved to be a reliable, repeatable way …
This update covers three pool tests, held on the following dates: These pool tests have been entirely focused on completing the prequal. We initially picked up where we left off with regards to our prequal strategy: This strategy quickly proved to be difficult to execute because of the following issues Given these issues, we switched …
Today we had the first pool test of the summer! Over the past two weeks, we accomplished the following: At the pool test, we adjusted the buoyancy, static power, and performed some basic motion tests. Adjusting buoyancy was a breeze with the new adjustable buoyancy system. However, one of the buoyancy mounts broke during this …
Today our goal was to try to complete the prequal by any means necessary. While we didn’t complete the prequal, we’ve made quite a bit of progress towards this goal. We picked up from where we left off yesterday, which was to try to keep the robot level whilst moving forward, especially when tracking a …
We attached a much wider base to the marker, which allowed it much more stable when standing up in the pool. We setup the prequal course. We’ve put small pieces of tape near the edge of the pool at three points: robot starting position, gate position, and marker position. We adjusted buoyancy and retuned static …
Before the test: Last night, Philip finished wiring the Ping1D. Today morning, we discovered that the epoxy applied to the battery connector had gotten into the connection, causing the connector to be very tightly connected with the wall power connector. We couldn’t separate them with brute force, so Philip cut off part of the insulation. …
8:00 AM – 9:30 AM We got to the pool at 9:50 AM. We were delayed because of an electrical issue causing the computer not to receive power. I had tested the robot last night and today morning and everything was working ok. After we put the capsule on for the first time, the issue …
We got to the pool at 2:45 PM due to issues with the DVL. When we checked the robot in the morning, all sensors worked except the DVL. We wanted to check the LED on top of the DVL to see if it was powered on. To do this, we took the DVL off the …
We got to the pool at 2:30 PM due to delays in resolving issues with the DVL and thrusters. The thrusters issue was fixed after the offset was changed to zero. The DVL however was unreliable when tested on land – it worked sometimes, but not other times. Also, we could initially connect to the …
On Saturday, Max generated a fully synthetic dataset and trained a CV model to detect the buoy. In addition to the four buoy glyphs, it also detected the entire buoy – something which I asked Max to add on Saturday after realizing it would be useful for sonar testing. On Sunday, we tested the new …
Copyright © 2024 Duke Robotics Club. All Rights Reserved.