This repository is intended for the lab session of ME336 by the Bionic Design and Learning Lab at Southern University of Science and Technology. This course was also offered during the Spring of 2019 and 2020.

• Course Instructor
  • Prof. Song Chaoyang
  • Dr. Wan Fang
• Teaching Assistant
  • Mr. Jie Yu
  • Mr. Liu Xiaobo
  • Mr. Guo Ning

Basic Training:

• Handeye Calibration: Handeye calibration code including 2D and 3D handeye calibration.
• Data Collection & Labeling: Collect training data of waste sorting.

Sample Projects:

• 2D Picking: Sample project of 2D picking
• 6D Picking: Sample project of 6D picking

Projects related to reinforcement learning:

• MadMario: PyTorch tutorial to build an AI-powered Mario. This example is to learn the Double Q-learning (DDQN) algorithm in reinforcement learning.
• Muzero: The example is to learn the state of the art RL algorithm for board games (Chess, Go, ...) and Atari games. Optional for students who are interested.
• RL-TaxiV3_Tabular_Q_learning.ipynb: train a tabular Q-learning agent on the smart taxi task.
• RL-CartPole_DQN.ipynb: train a Deep Q Learning (DQN) agent on the CartPole-v0 task.
• RL-CartPole_A2C_online.ipynb: train a Advance Actor Critic (A2C) agent on the CartPole-v0 task.

• Project 1: 2D Picking of (x,y)
• Project 2: 3D Picking of (x,y,z)
• Project 3: Your Proposed projects

For the step-by-step instructions on the projects, please refer the doc for Franka and Aubo. Please request for access if you don't have.