Artificial Ethical Agent
  • Introduction of AMA Project
    • Annual Development Plan
      • First year
      • Second year
      • Third year
      • Fourth year
      • Fifth year
  • Published thesis
  • main_banner02.png

    AMA task introduction
    Development of artificial moral agent

    In order for humans and robots to communicate with each other truly, artificial intelligence should be developed by combining moral factors together. 

  • main_banner02.png

    AMA Source code
    AMA Meta package download

    ownload AMA version 1.0 meta package for an OP 

Second year (2017)
1. Objective

* Dong-A University (host organization): Implement top-down and bottom-up ethical decision layers in ROS-Soar architecture.

* Seoul National University of Education (participation organization): Develop bottom-up moral principle system and moral judgment test tool for AMA.

2. Content and Scope of Development
* Dong-A Univ

- Development of Soar agent with ethical components (top-down and bottom-up ethical layers) that enable basic ethical decision-making

- Top-down ethical decision-making layer in ROS-Soar package
ㆍ Implement Soar top-down ethical layer combining the utilitarian theory and Kant's deontological theory.

- Bottom-up moral learning layer in ROS-Soar package (pre-convention level of Kohlberg)
ㆍ Develop obedience-oriented ethics module by developing a punishment algorithm for behavior using Soar's reinforcement learning function.
ㆍ Develop individualism, instrumental purpose and deal-oriented ethics module using Soar's chunking function and episodic, semantic, and procedural memories.
* Seoul National Univ. of Education
- Extract ethical judgment elements to be used for moral judgment test of various social and care robots and construct hierarchical structure between ethical elements.

- Establish a limited sense of operative moral concept applicable to artificial intelligence.

- Develop bottom-up ethical platform and scenario.