{"id":20455558,"url":"https://github.com/banaankiamanesh/dl-for-navigation","last_synced_at":"2025-04-13T03:42:04.769Z","repository":{"id":37463765,"uuid":"463449195","full_name":"BanaanKiamanesh/DL-for-Navigation","owner":"BanaanKiamanesh","description":"Implementation of Regression Models on Navigation with IMUs.","archived":false,"fork":false,"pushed_at":"2022-08-23T14:22:13.000Z","size":14983,"stargazers_count":15,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-26T20:51:29.495Z","etag":null,"topics":["9-axis-imu","ahrs","bno055","bosch","cpp","datacollection","deeplearning","imu","knn-regression","navigation","neural-networks","python","python3","raspberry-pi","recurrent-neural-network","recurrent-neural-networks","regression-models","support-vector-regression","tensorflow2"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/BanaanKiamanesh.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-02-25T08:07:16.000Z","updated_at":"2024-10-15T13:18:41.000Z","dependencies_parsed_at":"2022-08-08T20:30:22.034Z","dependency_job_id":null,"html_url":"https://github.com/BanaanKiamanesh/DL-for-Navigation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BanaanKiamanesh%2FDL-for-Navigation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BanaanKiamanesh%2FDL-for-Navigation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BanaanKiamanesh%2FDL-for-Navigation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BanaanKiamanesh%2FDL-for-Navigation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BanaanKiamanesh","download_url":"https://codeload.github.com/BanaanKiamanesh/DL-for-Navigation/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248660985,"owners_count":21141381,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["9-axis-imu","ahrs","bno055","bosch","cpp","datacollection","deeplearning","imu","knn-regression","navigation","neural-networks","python","python3","raspberry-pi","recurrent-neural-network","recurrent-neural-networks","regression-models","support-vector-regression","tensorflow2"],"created_at":"2024-11-15T11:19:12.838Z","updated_at":"2025-04-13T03:42:04.740Z","avatar_url":"https://github.com/BanaanKiamanesh.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# **Implementation of Regression Models(DRNN + SVR + KNR) Against Kalman Filters for the Calculation of Quaternions and Euler Angles**\n\n### This Repo Contains 2 Main Parts:\n\n* [Dataset](https://github.com/BanaanKiamanesh/DL_for_Navigation/tree/main/DataSet)\n*   1. [DRNN Model](https://github.com/BanaanKiamanesh/DL_for_Navigation/tree/main/RNN%20Model)\n    2. [SVR+KNR Model](https://github.com/BanaanKiamanesh/DL_for_Navigation/tree/main/SVR%20Model)\n\n## DataSet Collection\n\n#### Data Contains\n\n    1. Gyroscope Data 3DoF\n    2. Accelerometer Data 3DoF\n    3. Magnetometer Data 3DoF\n    4. Euler Angles Data 3DoF\n    5. Quaternions Data 4DoF\n\nTo collect the data, I made a small setup using a Raspberry pi and BNO055 IMU. So simple but it works wonderfully.\n\n### 1. Hardware Setup\n\n    1. Raspberry pi 4\n    2. BNO055 9DoF IMU\n    3. Lithium Polymer Battery\n    4. Buck Converter\n    5. USB-C to USB-A Adapter\n    6. Breadboard\n    7. Bunch of Jumper Wires\n    **Note:** It should be portable, So the data collection is not constrained to a specific location and angle.\n\n![Best Data Logger in the Whole World!](images/Hardware_Setup.jpeg)\n\n---\n\n### 2. Software Setup\n\n[Here](https://github.com/BanaanKiamanesh/DL_for_Navigation/tree/main/Data_Collection) is the code for the data collection.\nFirst, the code is written in C++. The code contains a loop with a constant frequency of 100Hz. The loop reads the IMU data for 5 minutes and writes it to a \".csv\" file at each iteration.\n\nThere is a Executable file for the Code in the same folder.\nBut in case you want to run the code, you need to install the WiringPi library from [here](http://wiringpi.com/download-and-install/).\n\nThere is another prerequisite for the code to run.\nHigh speed I2C (400kHz) in the used Raspberry pi 4 have to be anabled.\nFor the purpose use the procedure described in the [here](https://www.raspberrypi-spy.co.uk/2018/02/change-raspberry-pi-i2c-bus-speed/).\n\nAfter handling all, the code is ready to be compiled.\n\nSo, Navigate to the folder where the code is and ***run*** the following ***bash*** command:\n\n    $ g++ -o CollectorApp *.cpp -lwiringPi -lm -std=c++11\n\n***Now the executable file is ready to be run like this***:\n\n    $ ./CollectorApp\n\n---\n\n#### **There are 8 Available Files Containing Data in the *\"DataSet\"* Folder.**\n\n\u003e **Note:** The files having \"(No Mag)\" in there names, don't contain magnetometer data.\n---\n\n## **Models**\nFor the purpose of this project, I used the following models:\n* Deep-RNN Model\n* Support-Vector-Regression Model\n* K-Neighbours-Regression Model\n\nSeems Like the Complexity of the data is so much that the ***RNN Model*** is not able to handle it.\n\nAnd it had a huge RMS of ***0.5*** in it's predictions and also the model stopped learning after a few epochs. Although the learning rate was adaptively adjusted. \n\nSo, I decided to use the ***Multi Output Support Vector Regression*** model.\nWhich seemed to handle the data better.\nBut, also the Model didn't perform well enough!\n\nSo, as a last resort, I used the ***K-Neighbours Regression*** model. Which turned out to be the finest model for this data...\n\nAnd with a bit of tuning, it was able to perform the best on the data.\nwith a mean absolute error of ***0.0043*** for Quaternions and ***3.3*** for Euler Angles.\n\n \u003e (**Note:** The mean absolute error is the average of the absolute errors of the predictions)\n---\n#### Logs for all the models are saved in a file named \"Logs.txt\" in the specific folder of each model.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbanaankiamanesh%2Fdl-for-navigation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbanaankiamanesh%2Fdl-for-navigation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbanaankiamanesh%2Fdl-for-navigation/lists"}