Breaching the boundaries of safety and intelligence in autonomous systems with risk-based rationality

Introduction

Autonomous systems able to comprehensively assess and model risks would be a scientific breakthrough leading to highly intelligent system behaviors, safe interactions in unstructured environments, and public trust. Currently, risk perception is an important part of human cognition not adequately implemented in the situation awareness, control, and decision-making of autonomous systems.

Project Objectives

Therefore, this project addresses fundamental research challenges related to:

1. Risk-based autonomy
2. Safe and efficient shared control with human supervisors

The aim is to develop powerful risk modeling and built-in risk control solutions, closely connected to risk-based decision support for human supervisors in-the-loop.

Expected Outcomes

The outcomes of the project will allow for new, safe, and advanced types of:

• Transport
• Mapping and monitoring of oceans and land
• Inspections of structures difficult to access

Current State of Research

Although there are a few preliminary concepts coupling risk models with control algorithms and artificial intelligence (AI), a fundamental framework providing risk-based control and decision support for both the autonomous system and human supervisors does not exist.

Proposed Framework

In BREACH, I will establish such a framework constituted by:

• Quantitative risk models merged with data-driven approaches
• Simulation and model-based approaches
• Integration of hardware, software, human, and environmental risk elements

The complexity of the framework will gradually evolve in two parallel tracks along with demonstrations for mission planning and execution for autonomous marine organizations.

Focus on Marine Systems

The focus on marine systems is due to the demanding challenges in that domain, and my knowledge and experience as a researcher in the Centre of Excellence on Autonomous Marine Operations and Systems (NTNU AMOS).

Research Experience

For several years, I have contributed to fundamental research related to risk management of autonomous marine systems, which has convinced me that this project will be a major leap forward with great impact.