{"id":199,"date":"2023-01-23T18:58:48","date_gmt":"2023-01-23T18:58:48","guid":{"rendered":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/?page_id=199"},"modified":"2023-05-04T02:37:25","modified_gmt":"2023-05-04T02:37:25","slug":"issues-log","status":"publish","type":"page","link":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/issues-log\/","title":{"rendered":"Issues Log & Decision Log"},"content":{"rendered":"\n

Decision Log<\/h2>\n\n\n\n
Decision #<\/th>Date<\/th>People Involved<\/th>Topic<\/th>Decision<\/th>Alternative<\/th>Rationale<\/th><\/tr><\/thead>
1<\/td>2\/2\/23<\/td>Alec Trela & Solomon Fenton<\/td>End-Effector Testing<\/td>– Testing End-Effector in a qualitative manner<\/td>– Look to link sensor data to gripping performance (force, torque)<\/td>– Too hard to link sensor data to performance in this setting<\/td><\/tr>
2<\/td>2\/20\/23<\/td>All Team Members<\/td>xArm is broken<\/td>– Move forward with the Sawyer arm for SVD and confirm availability with Kantor
– Simultaneously, get a simulation environment working with an \u201carm-agnostic\u201d planner able to handle both 6 and 7 DOF arms<\/td>		– Entirely Simulation environment for the spring
– Get some to buy an arm
– Reach out to other resources (MFI)<\/td>		– Discussion with sponsor
– Sawyer seems like the only available arm this semester but will not be the arm going to Iowa so we also need to develop an \u201carm-agnostic\u201d simulation<\/td><\/tr>
3<\/td>2\/27\/23<\/td>Alec and Solomon<\/td>Arduino vs Raspberry PI<\/td>Arduino<\/td>Raspberry PI<\/td>– Dynamixel shield compatible with Arduino
– Didn’t have RPi<\/td><\/tr>
4<\/td>3\/11\/23<\/td>Alec and Solomon<\/td>Serial Communication Protocol<\/td>Use Arduino Mega and alternative RX\/TX pins with FTDI serial to usb converter<\/td>Use Arduino Uno and SoftwareSerial to convert digital pins to UART pins<\/td>Arduino Uno route did not work, using the Mega is more reliable. Also leaves additional UART pins for future proofing<\/td><\/tr>
5<\/td>3\/15\/23<\/td>Alec and Solomon<\/td>Dual blades for cutter<\/td>Blades on both sides of the cutting mechanism<\/td>Single blade<\/td>– More effective cutting<\/td><\/tr>
6<\/td>4\/3\/23<\/td>All Team Members<\/td>Switch to Kinova arm<\/td>Use the Kinova Gen3 6 DOF arm in the Tepper AI Makerspace for the SVD<\/td>– Motion planning in simulation
– Sawyer arm <\/td>		– The Sawyer arm is not capable of handling the orientation constraints and obstacles necessary for our SVD<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

Issues Log<\/h2>\n\n\n\n
Issue Number<\/th>Date Found<\/th>Date Fixed<\/th>Change Made By<\/th>Origin<\/th>Issue Description<\/th>Resolution Plan<\/th>Artifact(s)<\/th>Resolved?<\/th><\/tr><\/thead>
1<\/td>1\/29\/2023<\/td>1\/29\/2023<\/td>jiyoonp<\/td>No data on the internet<\/td>Don\u2019t have pepper dataset<\/td>Made them from youtube farm videos<\/td>Dataset<\/td>Yes<\/td><\/tr>
2<\/td>2\/7\/2023<\/td>2\/8\/2023<\/td>jiyoonp<\/td>The format we created\/labeled the datasets were wrong<\/td>AssertionError: Expected target boxes to be a tensor of shape [N, 4], got torch.Size([0])<\/td>I changed the datasets that were being used to train the model. Like reducing the size from 1500 to 500 images. I assume there was something wrong with the datasets. (but when I checked for the images that were throwing errors, they was nothing wrong.)<\/td>Code<\/td>Yes<\/td><\/tr>
3<\/td>2\/8\/2023<\/td>2\/8\/2023<\/td>jiyoonp<\/td>The way imshow takes in arguments<\/td>normalizing the image and doing imshow will show me a black image<\/td>Don\u2019t pass in normalized image \u2192 de-normalize and show an image<\/td>Code<\/td>Postponed as we are not using Faster R-CNN<\/td><\/tr>
4<\/td>2\/9\/2023<\/td>2\/12\/2023<\/td>shriishs<\/td>Colab code was set up but model would not begin the training<\/td>YOLOv7 will not start training<\/td>Speak to seniors and read official documentation to check for potential mistakes in code<\/td>Cleaned code and changed hyperparameters<\/td>Yes<\/td><\/tr>
5<\/td>2\/10\/2023<\/td>2\/19\/2023<\/td>sfenton<\/td>Cutter testing<\/td>Cutting results poorer than expected<\/td>Will need to experiment with other cutting mechanisms and higher torque motors.<\/td>Cutter prototype<\/td>Yes<\/td><\/tr>
6<\/td>2\/13\/2023<\/td>2\/17\/2023<\/td>shriishs<\/td>Model reaches maximum accuracy level and saturates<\/td>YOLOv7 validation accuracy saturates<\/td>Read online about hyperparameter tuning<\/td>Realized that the accuracy being acheived was state-of-the-art values<\/td>Yes<\/td><\/tr>
7<\/td>2\/13\/2023<\/td>2\/15\/2023<\/td>atrela<\/td>Testing of Gear Driven Cutter Design<\/td>Dynamixel SDK wasn\u2019t driving motor<\/td>Ask Jash how to fix it and use the GUI in the meantime<\/td>Replaced Raspberry Pi for Arduino + Dynamixel Shield<\/td>Yes<\/td><\/tr>
8<\/td>2\/16\/2023<\/td>2\/23\/2023<\/td>sridevik<\/td>Meeting with Dominic Guri<\/td>xArm is not going to be easy to fix or is unfixable<\/td>email John Dolan, George Kantor, and Kroemer \u2014 see what they have to say and look for potential replacement arm options<\/td>Manipulator hardware platform, SVD testbed<\/td>Ongoing<\/td><\/tr>
9<\/td>2\/21\/2023<\/td>2\/23\/2023<\/td>atrela<\/td>Testing a Daisy Chain operation of our motors<\/td>Could not operate the AX-12 Dynamixel Motor with the Shield<\/td>Try refactored code, will try to run this past Jash as well if the refactored code does not solve it.<\/td>Swapped the AX-12 for MX-28<\/td>Yes<\/td><\/tr>
10<\/td>4\/1\/23<\/td>4\/3\/23<\/td>sridevik<\/td>Testing with constraints on the Sawyer arm<\/td>The Sawyer arm’s reachability map is not good enough to handle our set of orientation constraints and obstacles<\/td>Switch to the Kinova arm in the Tepper AI Makerspace<\/td>Kinova Gen3 6 DOF Arm<\/td>Yes<\/td><\/tr>
11<\/td>4\/10\/23<\/td>4\/12\/23<\/td>shriishs<\/td>Full system integration led to inaccurate POI computations<\/td>Camera was not properly calibrated<\/td>Created a formalized camera calibration process using an Aruco marker, the Kinova camera, and the RealSense camera<\/td>Aruco marker, Kinova camera, code, calibrated transform values<\/td>Yes<\/td><\/tr>
12<\/td>4\/12\/23<\/td>—<\/td>sridevik<\/td>Switching from Kinova simulation to real arm<\/td>Cartesian moving with Kinova arm<\/td>Set longer durations on the movements so that the acceleration\/velocity limits were not exceeded<\/td>Code<\/td>Ongoing<\/td><\/tr>
13<\/td>4\/26\/23<\/td>—<\/td>sfenton<\/td>SVD Encore<\/td>Dynamixel Motor Failure<\/td>Look into potential reasons for the motor failure over the summer<\/td>Dynamixel motors<\/td>Ongoing<\/td><\/tr><\/tbody><\/table><\/figure>\n","protected":false},"excerpt":{"rendered":"

Decision Log Decision # Date People Involved Topic Decision Alternative Rationale 1 2\/2\/23 Alec Trela & Solomon Fenton End-Effector Testing – Testing End-Effector in a qualitative manner – Look to link sensor data to gripping performance (force, torque) – Too hard to link sensor data to performance in this setting 2 2\/20\/23 All Team Members … Continue Reading<\/strong> <\/i><\/a><\/p>\n","protected":false},"author":314,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-199","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/wp-json\/wp\/v2\/pages\/199","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/wp-json\/wp\/v2\/users\/314"}],"replies":[{"embeddable":true,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/wp-json\/wp\/v2\/comments?post=199"}],"version-history":[{"count":7,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/wp-json\/wp\/v2\/pages\/199\/revisions"}],"predecessor-version":[{"id":672,"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/wp-json\/wp\/v2\/pages\/199\/revisions\/672"}],"wp:attachment":[{"href":"https:\/\/mrsdprojects.ri.cmu.edu\/2023teamd\/wp-json\/wp\/v2\/media?parent=199"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}