The primary risks associated with our project right now are final integration and the robot’s ease of access when collecting a trash component while moving. During testing, we found that the robot has difficulty picking up the components while moving Read more…
This week, I prepared the final presentation and gave speech. Also, I tried to debug the github issues we were having with Ritu and wired the ultrasonic sensors to count the number of items we are collecting. Finally, I installed Read more…
I did not get much done this week since I was sick. I did participate in final presentations and peer review. I also participated in build once with working through a problem we had with GitHub, helping test the ultrasonic Read more…
This past week, I sent in our final parts requests for motor mounts (for the two motors we have been using for the roller and conveyor belt) and power banks (as previously we noticed that our current power bank can Read more…
The most significant risk we are encountering right now is not being able to integrate all the components (from Jetson Orin to ultrasonic sensors) until the final demo. However, we are managing to mitigate this risk by committing more time Read more…
For two weeks, I have been mostly working on motion control. First, as our original motors had low torque for our robot base, we switched to motors with higher torques (6.5 kg*s/m). As soon as it came, Hirani and I Read more…
Last week, I focused on making sure the camera could detect trash items at the robot’s rather high height and reliably communicate information to the Pi with a basic path planning algorithm. Unfortunately, since the images the camera were trained Read more…
This week, our revised motors, for both the wheels and conveyor belt & roller, came in. Ella and I tested the motors and found that these work much better – we were able to get the robot moving and have Read more…
This week, I have mostly spent my time trying to debug dc motors. On Monday’s interim demo, we found out that the robot cannot move when it is on the ground. Plus, some of the motors would not run at Read more…
This week, I was successfully able to generate bounding boxes using the optimized tensorrt (trt) model. As seen in the below screenshot, inferencing runs at an average rate of 115 FPS (~8.7ms) on a live camera feed when jetson_clocks is Read more…