Responsible Robotics: Ethical Black Box in Human-Robot Dialogue (EBBHRD)
The concept of an ethical black box is critical, especially in the event of an accident, to understand why and how a robot caused an accident and to establish accountability and responsibility. Through the ethical black box, a social robot will be able to explain its behaviour in simple and understandable ways.
The scope of ethical AI and human-robot interaction is very broad, and in this test bed is limited to human-robot dialogue. The first version, EBBHRD-v1.0, is a scalable digital platform running on AWS Cloud Services. EBBHRD-v1.0 detects the type of conversation taking place between human and robot, as well as social factors affecting the human participant, and tracks and stores information relating to the Natural Language Processing (NLP) pipeline.
The Ethical Black Box is being developed and trialled by the RoboTIPS project, a collaboration between Oxford and Bristol Robotics Lab.
PIs: Marina Jirotka, Pericle Salvini, Lars Kunze, Omer Gunes