Trustworthy human-AI partnerships

Bioconjugates for Cancer Prevention: Opportunities for Impact

Cancer prevention encompasses both screening strategies to find cancers early when they are likely to be most treatable and prevention and interception strategies to reduce the risk of developing cancers. Bioconjugates, here defined broadly as materials and molecules that have synthetic and biological components, have roles to play across the cancer-prevention spectrum. In particular, bioconjugates may be developed as affordable, accessible, and effective screening strategies or as novel vaccines and drugs to reduce one's risk of developing cancers. Developmental programs are available for taking novel technologies and evaluating them for clinical use in cancer screening and prevention. While a variety of different challenges exist in implementing cancer-prevention interventions, a thoughtful approach to bioconjugates could improve the delivery and acceptability of the interventions.

Reasoning about responsibility in autonomous systems: challenges and opportunities

Ensuring the trustworthiness of autonomous systems and artificial intelligence is an important interdisciplinary endeavour. In this position paper, we argue that this endeavour will benefit from technical advancements in capturing various forms of responsibility, and we present a comprehensive research agenda to achieve this. In particular, we argue that ensuring the reliability of autonomous system can take advantage of technical approaches for quantifying degrees of responsibility and for coordinating tasks based on that. Moreover, we deem that, in certifying the legality of an AI system, formal and computationally implementable notions of responsibility, blame, accountability, and liability are applicable for addressing potential responsibility gaps (i.e. situations in which a group is responsible, but individuals’ responsibility may be unclear). This is a call to enable AI systems themselves, as well as those involved in the design, monitoring, and governance of AI systems, to represent and reason about who can be seen as responsible in prospect (e.g. for completing a task in future) and who can be seen as responsible retrospectively (e.g. for a failure that has already occurred). To that end, in this work, we show that across all stages of the design, development, and deployment of trustworthy autonomous systems (TAS), responsibility reasoning should play a key role. This position paper is the first step towards establishing a road map and research agenda on how the notion of responsibility can provide novel solution concepts for ensuring the reliability and legality of TAS and, as a result, enables an effective embedding of AI technologies into society.

Computational Transcendence: Responsibility and agency

Emergence of responsible behavior is explored in non-cooperative games involving autonomous agents. Rather than imposing constraints or external reinforcements, agents are endowed with an elastic “sense of self” or an elastic identity that they curate based on rational considerations. This approach is called “computational transcendence (CT).” We show that agents using this model make choices for collective welfare instead of individual benefit. First, relevance of this model in game theoretic contexts like Prisoners’ dilemma and collusion is presented. Next, a generic multi-agent framework for simulating dilemmas around responsible agency is also proposed. CT implemented on this framework, is shown to be versatile in acting responsibly to different kinds of circumstances–including modifying their strategy based on their interaction with other agents in the system as well as interacting with adversaries that are rational maximizers, and who have a rationale to exploit responsible behavior from other agents. CT is also shown to outperform reciprocity as a strategy for responsible autonomy. Thus, we present CT as a framework for building autonomous agents which can intrinsically act responsibly in multi-agent systems. The core model for computational ethics presented in this paper can potentially be adapted to the needs of applications in areas like supply chains, traffic management, and autonomous vehicles. This paper hopes to motivate further research on responsible AI, by exploring computational modeling of this elusive concept called the “sense of self” that is a central element of existential inquiry in humans.

From intelligent agents to trustworthy human-centred multiagent systems

The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good.

Human injury-based safety decision of automated vehicles

Automated vehicles (AVs) are anticipated to improve road traffic safety. However, prevailing decision-making algorithms have largely neglected the potential to mitigate injuries when confronting inevitable obstacles. To explore whether, how, and to what extent AVs can enhance human protection, we propose an injury risk mitigation-based decision-making algorithm. The algorithm is guided by a real-time, data-driven human injury prediction model and is assessed using detailed first-hand information collected from real-world crashes. The results demonstrate that integrating injury prediction into decision-making is promising for reducing traffic casualties. Because safety decisions involve harm distribution for different participants, we further analyze the potential ethical issues quantitatively, providing a technically critical step closer to settling such dilemmas. This work demonstrates the feasibility of applying mining tools to identify the underlying mechanisms embedded in crash data accumulated over time and opens the way for future AVs to facilitate optimal road traffic safety.

•

We propose an injury risk mitigation-based decision-making algorithm for AVs

•

A real-time, data-driven human injury prediction model was established

•

We applied mining tools to identify mechanisms embedded in accumulated crash data

•

We analyzed traffic ethical issues quantitatively, closer to feasible solutions

Responsibility of AI Systems

To support the trustworthiness of AI systems, it is essential to have precise methods to determine what or who is to account for the behaviour, or the outcome, of AI systems. The assignment of responsibility to an AI system is closely related to the identification of individuals or elements that have caused the outcome of the AI system. In this work, we present an overview of approaches that aim at modelling responsibility of AI systems, discuss their advantages and shortcomings to deal with various aspects of the notion of responsibility, and present research gaps and ways forward.