Skip to content

This repository acts as a central hub for the code development by TEAM ID 11 for the course "Advanced Deep Learning in Robotics".

Notifications You must be signed in to change notification settings

tabdar-khan/adlr_team_11

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Advanced Deep Learning Robotics (WS21/22)

Instructor: Berthold Bäuml 

Tutor: Johannes Tenhumberg

📦 Tech Stack

Made withJupyter Made withJupyter Made with Docker



🏁 Quick Start

This repository acts as a central hub for the code development by TEAM_ID 11 for the course "Advanced Deep Learning in Robotics".

🎯 Objective of the Project

The main objective of the project is to implement an algorithm to learn from experience for faster(time-efficient) motion planning, for a motion task, with respect to the classical optimization-based planning approach.

🔭 Technical Outline

The general goal of the project is to implement a deep learning solution to generate experiences on known world configurations based on an initial guess, and then using the experiences for faster decision making in motion planning. We ought to investigate multiple models and approaches for the above mentioned task and then experimenting with different tweaks here and there, to find the best solution. After sufficient generation of experiences, we want to test our results in the setup and compare its performance with the previous solution (Only optimized path approach).
If time permits, we want to generate various experiences for the same initial guess and save the best path.

🧑‍🤝‍🧑 Team Members

  • Tabdar Khan Bashir
  • Sabeeh Musharraf
  • Said Anshasi


🔧 Usage

Pre-requisites:

  • Docker and docker-compose must be installed
  • An account on hub.docker.com would save you from unforeseen errors
  • Generate and save your Personal access token with you (This is used as password in the terminal). See this for reference

Steps:

  1. Clone the repository using git clone https://github.com/tabdar-khan/adlr_team_11.git
  2. Go inside the the directory usind cd command.
  3. Copy the db file i.e. SingleSphere02.db inside the repository.
  4. Run docker login inside the terminal and enter your hub.docker.com credentials.
  5. Run docker-compose up in the terminal to pull the images and, create & run a docker container. (This might take some time)
  6. After the container is created, go to your browser and enter http://localhost:8888 into the address bar.


📋 Git Workflow

Note: Please adhere to these rules so that we all are on the same page and there are no hickup in anyone's work

  • Create your own branch using git checkout -b <your_branch_name>. <your_branch_name> should be your github username.
  • Work and commit changes in your own branch and please do not use the main branch.
  • When need be, the branches will be merged inside the master branch.


🥳🎉🎆🎈Happy Coding Folks! 🎈🎆🎉🥳

About

This repository acts as a central hub for the code development by TEAM ID 11 for the course "Advanced Deep Learning in Robotics".

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published