A5040721287- Multi-Agent Systems and Negotiation
- Logic, Reasoning, and Knowledge
- Formal Methods in Verification
- Ethics and Social Impacts of AI
- Logic, programming, and type systems
- Semantic Web and Ontologies
- AI-based Problem Solving and Planning
- Adversarial Robustness in Machine Learning
- Model-Driven Software Engineering Techniques
- Software Testing and Debugging Techniques
- Advanced Software Engineering Methodologies
- Mobile Agent-Based Network Management
- Safety Systems Engineering in Autonomy
- Modular Robots and Swarm Intelligence
- Distributed systems and fault tolerance
- Explainable Artificial Intelligence (XAI)
- Service-Oriented Architecture and Web Services
- Natural Language Processing Techniques
- Robotic Path Planning Algorithms
- Reinforcement Learning in Robotics
- Network Security and Intrusion Detection
- Information and Cyber Security
- Software Reliability and Analysis Research
- Artificial Intelligence in Law
- Software Engineering Research
University of Manchester
2020-2024
IEEE Computer Society
2023
Institute of Electrical and Electronics Engineers
2023
Regional Municipality of Niagara
2023
University of Liverpool
2011-2020
University of Freiburg
2018
Merseytravel
2018
University of Nottingham
2002-2007
Information Technology University
2005
University of Edinburgh
1997-2001
Autonomous systems such as unmanned vehicles are beginning to operate within society. All participants in society required follow specific regulations and laws. An autonomous system cannot be an exception. Inevitably will find itself a situation which it needs not only choose obey rule or not, but also make complex ethical decision. However, there exists no obvious way implement the human understanding of behaviour computers. Even if we enable distinguish between more less alternatives, how...
Exploring autonomous systems and the agents that control them.
The coordination of multiple autonomous vehicles into convoys or platoons is expected on our highways in the near future. However, before such can be deployed, behaviours these must certified. This non-trivial and goes beyond current certification requirements, for human-controlled vehicles, that act autonomously. In this paper, we show how formal verification contribute to analysis new, increasingly autonomous, systems. An appropriate overall representation vehicle platooning as a...
This paper describes IEEE P7001, a new draft standard on transparency of autonomous systems 1 . In the paper, we outline development and structure standard. We present rationale for as measurable, testable property. five stakeholder groups: users, general public bystanders, safety certification agencies, incident/accident investigators lawyers/expert witnesses, explain thinking behind normative definitions “levels” each group in P7001. The illustrates application P7001 through worked...
We present a verification methodology for analysing the decision-making component in agent-based hybrid systems. Traditionally automata have been used to both implement and verify such systems, but based modelling, programming techniques scale poorly as complexity of discrete increases making them unattractive situations where complex logical reasoning is required. In systems it has, therefore, become common separate out into separate, discrete, component. However, failed keep pace with this...
Ethics by Design concerns the methods, algorithms and tools needed to endow autonomous agents with capability reason about ethical aspects of their decisions, formalisms guarantee that an agent's behavior remains within given moral bounds. In this context some questions arise: How what extent can understand social reality in which they operate, other intelligences (AI, animals humans) co-exist? What are emerging new forms society, how do we ensure human dimension is upheld interactions...
Previous work on ethical machine reasoning has largely been theoretical, and where such systems have implemented, it has, in general, only initial proofs of principle. Here, we address the question desirable attributes for to improve their real world utility, how controllers with these might be implemented. We propose that ethically critical should proactive, transparent, verifiable. describe an architecture is handled by a separate layer, augmenting typical layered control architecture,...
The advent of sophisticated robotics and AI technology makes sending humans into hazardous distant environments to carry out inspections increasingly avoidable. Being able send a robot, rather than human, nuclear facility or deep space is very appealing. However, building these robotic systems just the start we still need range verification validation tasks ensure that be deployed are as safe reliable possible. Based on our experience across three research innovation hubs within UK’s “Robots...
Exploring autonomous systems and the agents that control them.
Both the ethics of autonomous systems and problems their technical implementation have by now been studied in some detail. Less attention has given to areas which these two separate concerns meet. This paper, written both philosophers engineers systems, addresses a number issues machine that are located at precisely intersection between engineering. We first discuss main challenges which, our view, posses moral philosophy. them consider different approaches towards conceptual design...
This report provides an overview of the workshop titled Autonomy and Safety Assurance in Early Development Robotics Autonomous Systems, hosted by Centre for Robotic Demanding Long-Lasting Environments (CRADLE) on September 2, 2024, at The University Manchester, UK. event brought together representatives from six regulatory assurance bodies across diverse sectors to discuss challenges evidence ensuring safety autonomous robotic systems, particularly inspection robots (AIR). featured invited...
In this article, we describe an approach to autonomous system construction that not only supports self-awareness but also formal verification. This is based on modular where the key decision making captured within a symbolically described "agent." So, article leads us from traditional systems architectures, via agent-based computing, explainability, reconfigurability, and verifiability, applications in robotics, vehicles, machine ethics. Fundamentally, consider perspective. Agents are...
We address the question of how an agent can adapt its behavior to comply with newly adopted norms. This is particularly relevant in case open systems where agents may enter and leave norm-governed social contexts not known at design time. requires norms be explicitly separately stated presented as rules which it then try behavior.We propose a formal semantic framework that specifies execution mechanism for such socially adaptive agents. based on expressing using Linear Temporal Logic. The...
A system of autonomous agents may exhibit undesirable or ineffective behavior if no form regulation is imposed. Norms, describing how should ideally behave, can be used to address this issue are able reason about norms and adapt their comply with them (if they choose do so). Assuming that which will have followed unknown at design time, it not possible pre-program such norm compliant. Instead, we need a generic execution mechanism allows run-time, what propose in paper. The defined on top an...
The continuous integration of software-intensive systems together with the ever-increasing computing power offer a breeding ground for intelligent agents and multi-agent (MAS) more than ever before. Over past two decades, wide variety languages, models, techniques methodologies have been proposed to engineer MAS. Despite this substantial body knowledge expertise, systematic engineering large-scale open MAS still poses many challenges. Researchers engineers face fundamental questions...
Abstract BDI agents act in response to external inputs and their internal plan library. Understanding the root cause of agent action is often difficult, this paper we present a dialogue based approach for explaining behaviour agent. We consider two participants who may have different views regarding beliefs, plans events which drove (encoded via traces). These make utterances incrementally reveal traces each other, allowing them identify divergences traces, or conclude that agree. In...
SUMMARY To understand the evolution of bipedalism among hominoids in an ecological context we need to be able estimate energetic cost locomotion fossil forms. Ideally such would based entirely on morphology since, except for rare instances where footprints are preserved, this is only primary source evidence available. In paper use evolutionary robotics techniques (genetic algorithms, pattern generators and mechanical modeling) produce a biomimetic simulation human body dimensions. The...