/phers_framework

Primary LanguagePython

Reproduction Code for PhERS (Pheromone for Every RobotS) Framework

1. Overview:

This repository provides reproduction code for the universal artificial pheromone framework "PhERS (Pheromone for Every RobotS)" designed to facilitate research and applications in pheromone-based communication among robots.

2. Paper Details:

  • Title: Universal Artificial Pheromone Framework with Deep Reinforcement Learning for Robotic Systems
  • Abstract: Pheromone-based communication has been adopted into robotic systems, inspired by social insects. This paper introduces the "PhERS" framework aimed at boosting research and applications in pheromone-based communication among robots.
  • Publication Year: 2021
  • Link: 10.1109/ICCRE51898.2021.9435666
  • Conference/Journal: 2021 6th International Conference on Control and Robotics Engineering (ICCRE)
  • Conference Location: Beijing, China
  • Conference Date: 16-18 April 2021
  • Publisher: IEEE

3. Environment & Dependencies:

  • Python 3.8
  • pytorch
  • OpenAI Gym 0.17.0
  • [Other necessary libraries]

4. Setup:

git clone repository
catkin build

5. Execution:

rosrun phers_framework hand_tune_controlle.py

6. Results:

From our reproduction, we achieved:

  • Static Obstacle Stage , HT-1 : XX% accuracy
  • Task B: XX% accuracy

Comparison with original paper's results:

[Comparison details]

7. Contact:

For questions or feedback, please reach out to [email address].