Related papers: Assuring Increasingly Autonomous Systems in Human-…
The behaviours of a swarm are not explicitly engineered. Instead, they are an emergent consequence of the interactions of individual agents with each other and their environment. This emergent functionality poses a challenge to safety…
Research interest in autonomous agents is on the rise as an emerging topic. The notable achievements of Large Language Models (LLMs) have demonstrated the considerable potential to attain human-like intelligence in autonomous agents.…
Micro aerial vehicles (MAVs) have high potential for information gathering tasks to support situation awareness in search and rescue scenarios. Manually controlling MAVs in such scenarios requires experienced pilots and is error-prone,…
Driving Automation Systems (DAS) are subject to complex road environments and vehicle behaviors and increasingly rely on sophisticated sensors and Artificial Intelligence (AI). These properties give rise to unique safety faults stemming…
Current validation methods often rely on recorded data and basic functional checks, which may not be sufficient to encompass the scenarios an autonomous vehicle might encounter. In addition, there is a growing need for complex scenarios…
Unmanned Aerial Systems (UAS) have a wide variety of applications, and their development in terms of capabilities is continuously evolving. Many missions performed by an Unmanned Aerial Vehicle (UAV) require flying in public airspace. This…
This paper presents an efficient risk management model for unmanned aerial vehicles or UAVs. Our proposed risk management establishes a cyclic model with a continuous and iterative structure that is very adaptable to agile methods and all…
Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of…
This paper describes a technique for the autonomous mission planning of unmanned aerial system swarms. Given a swarm operating in a known area, a central command system generates measurements from the swarm. If those measurements indicate…
Self-adaptive systems (SASs) are capable of adjusting its behavior in response to meaningful changes in the operational con-text and itself. The adaptation needs to be performed automatically through self-managed reactions and…
This study explores integrating large language models (LLMs) with situational awareness-based planning (SAP) to enhance the decision-making capabilities of AI agents in dynamic and uncertain environments. We employ a multi-agent reasoning…
Large language models (LLMs) deployed as agents introduce significant safety risks in clinical settings due to their potential for error and single points of failure. We introduce Tiered Agentic Oversight (TAO), a hierarchical multi-agent…
Autonomous inspection systems are essential for ensuring the performance and longevity of industrial assets. Recently, agentic frameworks have demonstrated significant potential for automating inspection workflows but have been limited to…
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…
As increasingly capable agents are deployed, a central safety challenge is how to retain meaningful human control without modifying the underlying system. We study a minimal control interface in which an agent chooses whether to act…
This paper presents an initial design concept and specification of a civilian Unmanned Aerial Vehicle (UAV) management simulation system that focuses on explainability for the human-in-the-loop control of semi-autonomous UAVs. The goal of…
The emergence of autonomous, high-velocity Agentic AI systems is creating an internal assurance scalability crisis. Point-in-time, document-based audits cannot keep pace with non deterministic behaviour and distributed deployments of agents…
Intelligent autonomous systems are part of a system of systems that interact with other agents to accomplish tasks in complex environments. However, intelligent autonomous systems integrated system of systems add additional layers of…
We study the problem of designing AI agents that can robustly cooperate with people in human-machine partnerships. Our work is inspired by real-life scenarios in which an AI agent, e.g., a virtual assistant, has to cooperate with new users…
This article considers a cooperative vehicle routing problem for an intelligence, surveillance, and reconnaissance mission in the presence of communication constraints between the vehicles. The proposed framework uses a ground vehicle and…