International audience

Abstract In Ambient Intelligence (AmI), seamless interaction between humans and AI systems is crucial for the effective utilization of smart environments. This paper investigates human–AI interaction in AmI, focusing on the management of uncertainty—situations where the AI is unsure how to choose between multiple possible outputs—within the context of Opportunistic Software Composition. The Opportunistic Composition Engine (OCE) dynamically constructs applications or assemblies from available software components, learning from human feedback to tailor applications to user preferences and context. We design, implement, and evaluate three approaches to uncertainty handling: explicitly asking the user to resolve uncertainty, offering a choice between multiple assemblies, and using a visual gradient to indicate the AI’s confidence. Each approach is implemented in a distinct version of OCE and assessed through a user study ( N = 121) measuring usability and learning performance in a 2D online simulated ambient environment. Our results show that providing clear visual or informational cues about uncertainty improves user satisfaction, while forcing users to resolve uncertainty themselves reduces usability and can hinder learning. Importantly, the other interaction strategies do not impair the system’s learning, suggesting that lightweight, system-guided handling of uncertainty can effectively support both user experience and AI adaptation. Beyond these conclusions, this work demonstrates the utility and general applicability of simulation-based technologies for prototyping and evaluating AmI applications.

International audience

As the vision of Ambient Intelligence (AmI) becomes more feasible, the challenge of designing effective and usable human-machine interaction in this context becomes increasingly important. Interactive Machine Learning (IML) offers a set of techniques and tools to involve end-users in the machine learning process, making it possible to build more trustworthy and adaptable ambient systems. In this paper, our focus is on exploring approaches to effectively integrate and assist human users within ML-based AmI systems. Through a survey of key IML-related contributions, we identify principles for designing effective human-AI interaction in AmI applications. We apply them to the case of Opportunistic Composition, which is an approach to achieve AmI, to enhance collaboration between humans and Artificial Intelligence. Our study highlights the need for user-centered and context-aware design, and provides insights into the challenges and opportunities of integrating IML techniques into AmI systems.

As the vision of Ambient Intelligence (AmI) becomes more feasible, the challenge of designing effective and usable human-machine interaction in this context becomes increasingly important. Interactive Machine Learning (IML) offers a set of techniques and tools to involve end-users in the machine learning process, making it possible to build more trustworthy and adaptable ambient systems. In this paper, our focus is on exploring approaches to effectively integrate and assist human users within ML-based AmI systems. Through a survey of key IML-related contributions, we identify principles for designing effective human-AI interaction in AmI applications. We apply them to the case of Opportunistic Composition, which is an approach to achieve AmI, to enhance collaboration between humans and Artificial Intelligence. Our study highlights the need for user-centered and context-aware design, and provides insights into the challenges and opportunities of integrating IML techniques into AmI systems.

Internet of Things and cyber-physical systems are characterised by openness and an increasing number of devices and their associated services. In a previous work, we have proposed to exploit opportunistically these services in order to automatically make emerge customised applications that suit user preferences. For that, we have developed a generic solution for bottom-up opportunistic service composition, based on reinforcement learning. In this work, it is extended to handle more efficiently the appearance of new components using service annotation and quality attributes in order to generalise and share knowledge with new discovered services. A didactic use case is used for illustration and demonstration purposes.

Cyber-physical and ambient systems surround the human user with applications that should be tailored as possible to her/his preferences and the current situation. We propose to build them automatically and on the fly by composition of software components present at the time in the environment, but without prior expression of the user's needs or process specification or composition model. In order to produce knowledge useful for automatic composition in the absence of an initial guideline, we have developed a generic solution based on lifelong online reinforcement learning. It is decentralized within a multi-agent system where agents learn incrementally from user feedback to satisfy her/him. Different use cases have been experimented in which applications, adapted to the user and the situation, are composed and emerge automatically and continuously.

Ambient environments consist of components surrounding the user and offering services.Applications can here be composed opportunistically and automatically by an intelligent system that puts together available components.Thus, applications that are a priori unknown emerge from the environment.The problem is in the intelligible presentation to an average user of those emerging composite applications.Our approach consists in automatic generation of user-oriented application descriptions from unit descriptions of each component and service.For that, we propose a well-defined language for component description and a method for combining descriptions.A prototype has been developed and used to experiment the generation of different composite application descriptions.Based on these experiments, we assess the degree of fulfillment of the requirements we have identified for the problem.

In this article, optimization of decision support queries is considered in the context of wide-area distributed databases. An original approach based on the “mobile agent” paradigm is proposed and evaluated. Agents’ autonomy and reactivity allow operators of the execution plan to adapt dynamically to estimation errors on relations and to evolutions in the state of the execution system, avoiding time overheads commonly associated with centralized monitoring. We present decentralized self-adaptive algorithms for dynamic optimization of join operators, and their implementations in Java using mobile agents. Then, we evaluate performance depending on error rate on statistical information on database, and on communication bandwidth and CPU frequency. The results show that the agent-based approach can lead to a significant reduction of response time and provide decision criteria for developing an effective migration policy.