Related papers: Human Control: Definitions and Algorithms
Balancing user agency and system automation is essential for effective human-AI interactions. Fully automated systems can deliver efficiency but risk undermining usability and user autonomy, while purely manual tools are often inefficient…
Human-AI shared control allows human to interact and collaborate with AI to accomplish control tasks in complex environments. Previous Reinforcement Learning (RL) methods attempt the goal-conditioned design to achieve human-controllable…
The article discusses development of autonomous artificial intelligence systems for corporate management. The function of a corporate director is still one of the few that are legislated for execution by a "natural" rather than an…
To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some…
The paper faces the problem of scheduling from a new perspective, trying to bridge the gap between classical heuristic approaches and system identification and control strategies. To this aim, a complete mathematical formulation of a…
Decision-making is increasingly supported by machine recommendations. In healthcare, for example, a clinical decision support system is used by the physician to find a treatment option for a patient. In doing so, people can rely too much on…
The ability to accurately predict human behavior is central to the safety and efficiency of robot autonomy in interactive settings. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as…
This paper develops a control-theoretic framework for analyzing agentic systems embedded within feedback control loops, where an AI agent may adapt controller parameters, select among control strategies, invoke external tools, reconfigure…
Every AI system is deployed by a human organization. In high risk applications, the combined human plus AI system must function as a high-reliability organization in order to avoid catastrophic errors. This short note reviews the properties…
As AI systems are increasingly incorporated into domains where human behavior has set the norm, a challenge for AI governance and AI alignment research is to regulate their behavior in a way that is useful and constructive for society. One…
Real-time collaboration with humans poses challenges due to the different behavior patterns of humans resulting from diverse physical constraints. Existing works typically focus on learning safety constraints for collaboration, or how to…
Shared autonomy refers to approaches for enabling an autonomous agent to collaborate with a human with the aim of improving human performance. However, besides improving performance, it may often also be beneficial that the agent…
We study the problem of controlling a general complex network towards an assigned synchronous evolution, by means of a pinning control strategy. We define the pinning-controllability of the network in terms of the spectral properties of an…
This position paper argues that AI agents should be regulated by the extent to which they operate autonomously. AI agents with long-term planning and strategic capabilities can pose significant risks of human extinction and irreversible…
A core part of human intelligence is the ability to work flexibly with others to achieve goals. The incorporation of artificial agents into human spaces is making increasing demands on artificial intelligence (AI) to demonstrate and…
This paper proposes a control method to address the physical Human-Robot Interaction (pHRI) challenge in the context of hierarchical tasks. A common approach to managing hierarchical tasks is Hierarchical Quadratic Programming (HQP), which,…
A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we…
We address the problem of stability of motor actions implemented by the central nervous system based on simple algorithms potentially reflecting physical (including physiological) processes within the body. A number of conceptually simple…
As learned control policies become increasingly common in autonomous systems, there is increasing need to ensure that they are interpretable and can be checked by human stakeholders. Formal specifications have been proposed as ways to…
We tackle the question of whether an agent can, by suitable choice of prompts, control an AI bot to any state. To that end, we first introduce a formal definition of ``meaning'' that is amenable to analysis. Then, we characterize…