As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination. Within the AI research community, this topic remains less familiar to many researchers. In this paper, we complement existing surveys, which largely focused on the psychological, social and legal discussions of the topic, with an analysis of recent advances in technical solutions for AI governance. By reviewing publications in leading AI conferences including AAAI, AAMAS, ECAI and IJCAI, we propose a taxonomy which divides the field into four areas: 1) exploring ethical dilemmas; 2) individual ethical decision frameworks; 3) collective ethical decision frameworks; and 4) ethics in human-AI interactions. We highlight the intuitions and key techniques used in each approach, and discuss promising future research directions towards successful integration of ethical AI systems into human societies.

Trust is an important mechanism enabling agents to self-police open and dynamic multi-agent systems (ODMASs). Trusters evaluate the reputation of trustees based on their past observed performance, and use this information to guide their future interaction decisions. Existing trust models tend to concentrate trusters’ interactions on a small number of highly reputable trustees to minimize risk exposure. When a trustee’s servicing capacity is limited, such an approach may cause long delays for trusters and subsequently damage the reputation of trustees. To mitigate this problem, we propose a reputation management approach for trustee agents based on distributed constraint optimization. It helps a trustee to make situation-aware decisions on which incoming requests to serve and prevent the resulting reputation score from being affected by factors out of the trustee’s control. The approach is evaluated through theoretical analysis and within a simulated, highly dynamic multi-agent environment. The results show that it can achieve close to optimally efficient utilization of the trustee agents’ collective capacity in an ODMAS, promotes fair treatment of trustee agents based on their behavior, and significantly outperforms related work in enhancing social welfare.

We propose an approach for meeting real-time constraints in AI systems that views (1) time as a resource that should be considered when making control decisions, (2) plans as ways of expressing control decisions, and (3) approximate processing as a way of satisfying time constraints that cannot be achieved through normal processing.

We propose an approach for meeting real-time constraints in AI systems that views (1) time as a resource that should be considered when making control decisions, (2) plans as ways of expressing control decisions, and (3) approximate processing as a way of satisfying time constraints that cannot be achieved through normal processing. In this approach, a real-time problem solver estimates the time required to generate solutions and their quality. This estimate permits the system to anticipate whether the current objectives will be met in time. The system can then take corrective actions and form lower-quality solutions within the time constraints. These actions can involve modifying existing plans or forming radically different plans that utilize only rough data characteristics and approximate knowledge to achieve a desired speedup. A decision about how to change processing should be situation dependent, based on the current state of processing and the domain-dependent solution criteria. We present preliminary experiments that show how approximate processing helps a vehicle-monitoring problem solver meet deadlines and outline a framework for flexibly meeting real-time constraints.

Cooperative distributed problem solving networks are distributed networks of semi-autonomous processing nodes that work together to solve a single problem. The Distributed Vehicle Monitoring Testbed is a flexible and fully-instrumented research tool for empirically evaluating alternative designs for these networks. The testbed simulates a class of a distributed knowledge-based problem solving systems operating on an abstracted version of a vehicle monitoring task. it implements a novel generic architecture for distributed problems solving networks that exploits the use of sophisticated local node control and meta-level control to improve global coherence in network problem solving; (2.)

Cooperative distributed problem solving networks are distributed networks of semi-autonomous processing nodes that work together to solve a single problem. The Distributed Vehicle Monitoring Testbed is a flexible and fully-instrumented research tool for empirically evaluating alternative designs for these networks. The testbed simulates a class of a distributed knowledge-based problem solving systems operating on an abstracted version of a vehicle monitoring task. There are two important aspects to the testbed: (1.) it implements a novel generic architecture for distributed problems solving networks that exploits the use of sophisticated local node control and meta-level control to improve global coherence in network problem solving; (2.) it serves as an example of how a testbed can be engineered to permit the empirical exploration of design issues in knowledge AI systems. The testbed is capable of simulating different degrees of sophistication in problem solving knowledge and focus-of attention mechanisms, for varying the distribution and characteristics of error in its (simulated) input data, and for measuring the progress of problem solving. Node configuration and communication channel characteristics can also be independently varied in the simulated network.

Our program in AI is part of the larger departmental focal area of cybernetics which integrates both AI and brain theory (BT). Our research also draws upon a new and expanding interdepartmental program in cognitive science that brings together researchers in cybernetics, linguistics, philosophy, and psychology. This interdisciplinary approach to AI has already led to a number of fruitful collaborations in the areas of cooperative computation, learning, natural language parsing, and vision.

Our program in AI is part of the larger departmental focal area of cybernetics which integrates both AI and brain theory (BT). Our research also draws upon a new and expanding interdepartmental program in cognitive science that brings together researchers in cybernetics, linguistics, philosophy, and psychology. This interdisciplinary approach to AI has already led to a number of fruitful collaborations in the areas of cooperative computation, learning, natural language parsing, and vision.