Category: Uncategorized

In conclusion we were able to combine the parts of our robot system to effectively sort boxes at a rate of 8/min at 95% accuracy. After prototyping a precise and strong robot arm from scratch, we used a camera and ML to locate and track QR’s on a moving treadmill then feed this data to a python kinematics engine. We wrote Arduino code to control the arm using motor controllers and angle sensors utilizing position moves and realtime averaged angle feedback.

Here is a video of our system in action
System Video

Here is our Design Presentation Slides
Design Slides

Here is our Final Presentation
Final Presentation

Here is our Final Video
Final Video

Here is our Final Report
Final Report

This week we worked on the design report and planning out the connection of our algorithms. We discussed using pixel differences in the qr to judge the height of the box on the treadmill. We are working to test the camera and the rest of our electrical components. When we get the robot arm to work were are going to feed it live position control calculate from camera data.

Here is about halfway finished soldering and wiring of the robot arm motor control box. 

 

These weeks I worked on the report and wiring the robot. I was able to wire about half of the robot and do tests on one of motors and angle sensors. I was able to create a preliminary Arduino angle feedback control system for 1 motor. One setback is that the “360” angle sensors were actually 250, and I think the overall cause was ESP32 only supporting 3.3v and not 5. This problem might require a switch to Arduino. Otherwise everything going smooth, next week I am going to finish wiring the robot arm and do full movement tests.

 

This week I moved a treadmill to a stable location and ran speed tests. Additionally I took it apart to see the motor and pulley setup. Planning on ordering electronic components in the next week. I need to ask for where to get bulk 18-22 awg wire. I also made a 3d kinematics visualizer and move solver

This week we worked on finalizing out design, and camera setup. We have received the treadmill and camera, and are going to run tests accordingly. We ran the treadmill to see what speed settings it had and .5 mph is the lowest we can go without modifying the treadmill. This speed is fast relative to the robot arm so we are going to do some calculations on required move kinematics.

This week I finished designing and printing the robot arm. My biggest challenges next week will be wiring the motors sensors and controllers. I will then need to connect the ESP32 to a computer and see if I can get position feedback, and do PWM motor control. Ive made a wiring diagram but will need to order many components. The suction gripper has proved effective on lifting packages > 4 lbs.

I set up coordinate frame transform and made an algorithm for setting the positions of robot moves .

This week we worked on planning out our kinematic flow. We also looked into camera options and purchased a camera for computer vision. We are working on developing kinematic planning algorithms for the robot. We decided on how we are going to set up the camera in relation to the conveyor belt: 1m above. We decided to change the scope of our project to include boxes of different heights, which will greatly increase our project’s overall usefulness. We decided to use OpenCV modules to determine the size of the QR code on each box, from which we should be able to extrapolate the height of the box.

A was written by Marcus, B was written by __, C was written by Matt:

A: In response to safety, we want a strict perimeter around the robot that puts people our of arm range. Additionally a full stop control should be established. In response to public welfare, back strain and warehouse related injuries are the main aches that our product aims to sooth. In regards to public health, fast packages will help people get their meds and happiness faster.

B:

C: Our project directly addresses the growing need for efficient and cost-effective package sorting in warehouses and distribution centers. As commercialization and e-commerce shipments continue to boom, the number of packages that need to be sorted will eventually reach unsustainable levels. This is especially true due to human inefficiencies, rising labor costs, and the physical toll of the work itself. Our robotic arm would significantly reduce labor dependency, which would allow businesses to minimize sorting errors, optimize workflow, and improve overall operational efficiency. This would affect the entire supply chain and improve the overall production, distribution, and consumption of goods.

By using our robotic arm to reduce labor costs and standardize sorting speed/accuracy, warehouses would be able to increase their package volumes, leading to greater profitability. Additionally, our robotic arm would streamline logistics and reduce bottlenecks, which would ultimately enable faster order fulfillment. Ideally, consumers would benefit from quicker delivery times, which would also increase their consumption. Another interesting effect of automating package sorting is that it allows companies to reallocate funds for human labor towards higher-value roles, which would potentially improve overall productivity and economic growth.