An official website of the United States government
Cyber-physical systems (CPS) designed in simulators, often consisting of multiple interacting agents (e.g., in multi-agent formations), behave differently in the real-world. We would like to verify these systems during runtime when they are deployed. Thus, we propose robust predictive runtime verification (RPRV) algorithms for: (1) general stochastic CPS under signal temporal logic (STL) tasks, and (2) stochastic multi-agent systems (MAS) under spatio-temporal logic tasks. The RPRV problem presents the following challenges: (1) there may not be sufficient data on the behavior of the deployed CPS, (2) predictive models based on design phase system trajectories may encounter distribution shift during real-world deployment, and (3) the algorithms need to scale to the complexity of MAS and be applicable to spatio-temporal logic tasks. To address these challenges, we assume knowledge of an upper bound on the statistical distance (in terms of anf-divergence) between the trajectory distributions of the system at deployment and design time. We are motivated by our prior work where we proposed an accurate and an interpretable RPRV algorithm for general CPS, which we here extend to the MAS setting and spatio-temporal logic tasks. Specifically, we use a learned predictive model to estimate the system behavior at runtime androbust conformal predictionto obtain probabilistic guarantees by accounting for distribution shifts. Building on our prior work, we perform robust conformal prediction over the robust semantics of spatio-temporal reach and escape logic (STREL) to obtain centralized RPRV algorithms for MAS. We empirically validate our results in a drone swarm simulator, where we show the scalability of our RPRV algorithms to MAS and analyze the impact of different trajectory predictors on the verification result. To the best of our knowledge, these are the first statistically valid algorithms for MAS under distribution shift.
more »
« less
Decision making in open agent systems
Abstract In many real‐world applications of AI, the set of actors and tasks are not constant, but instead change over time. Robots tasked with suppressing wildfires eventually run out of limited suppressant resources and need to temporarily disengage from the collaborative work in order to recharge, or they might become damaged and leave the environment permanently. In a large business organization, objectives and goals change with the market, requiring workers to adapt to perform different sets of tasks across time. We call these multiagent systems (MAS)open agent systems(OASYS), and theopennessof the sets of agents and tasks necessitates new capabilities and modeling for decision making compared to planning and learning inclosedenvironments. In this article, we discuss three notions of openness: agent openness, task openness, and type openness. We also review the past and current research on addressing the novel challenges brought about by openness in OASYS. We share lessons learned from these efforts and suggest directions for promising future work in this area. We also encourage the community to engage and participate in this area of MAS research to address critical real‐world problems in the application of AI to enhance our daily lives.
more »
« less
- PAR ID:
- 10479740
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- AI Magazine
- Volume:
- 44
- Issue:
- 4
- ISSN:
- 0738-4602
- Format(s):
- Medium: X Size: p. 508-523
- Size(s):
- p. 508-523
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Recent work has explored how complementary strengths of humans and artificial intelligence (AI) systems might be productively combined. However, successful forms of human–AI partnership have rarely been demonstrated in real‐world settings. We present the iterative design and evaluation of Lumilo, smart glasses that help teachers help their students in AI‐supported classrooms by presenting real‐time analytics about students’ learning, metacognition, and behavior. Results from a field study conducted in K‐12 classrooms indicate that students learn more when teachers and AI tutors work together during class. We discuss implications of this research for the design of human–AI partnerships. We argue for more participatory approaches to research and design in this area, in which practitioners and other stakeholders are deeply, meaningfully involved throughout the process. Furthermore, we advocate for theory‐building and for principled approaches to the study of human–AI decision‐making in real‐world contexts.more » « less
-
Many domains of AI and its effects are established, which mainly rely on their integration modeling cognition of human and AI agents, collecting and representing knowledge using them at the human level, and maintaining decision-making processes towards physical action eligible to and in cooperation with humans. Especially in human-robot interaction, many AI and robotics technologies are focused on human- robot cognitive modeling, from visual processing to symbolic reasoning and from reactive control to action recognition and learning, which will support human-multi-agent cooperative achieving tasks. However, the main challenge is efficiently combining human motivations and AI agents’ purposes in a sharing architecture and reaching a consensus in complex environments and missions. To fill this gap, this workshop brings together researchers from different communities inter- ested in multi-agent systems (MAS) and human-robot interaction (HRI) to explore potential approaches, future research directions, and domains in human-multi-agent cognitive fusion.more » « less
-
Abstract Recent advances in AI culminate a shift in science and engineering away from strong reliance on algorithmic and symbolic knowledge towards new data-driven approaches. How does the emerging intelligent data-centric world impact research on real-time and embedded computing? We argue for two effects: (1) new challenges in embedded system contexts, and (2) new opportunities for community expansion beyond the embedded domain. First,on the embedded system side, the shifting nature of computing towardsdata-centricityaffects the types of bottlenecks that arise. At training time, the bottlenecks are generallydata-related. Embedded computing relies onscarcesensor data modalities, unlike those commonly addressed in mainstream AI, necessitating solutions forefficient learningfrom scarce sensor data. At inference time, the bottlenecks areresource-related, calling forimproved resource economyandnovel scheduling policies. Further ahead, the convergence of AI around large language models (LLMs) introduces additionalmodel-relatedchallenges in embedded contexts. Second,on the domain expansion side, we argue that community expertise in handling resource bottlenecks is becoming increasingly relevant to a new domain: thecloudenvironment, driven by AI needs. The paper discusses the novel research directions that arise in the data-centric world of AI, covering data-, resource-, and model-related challenges in embedded systems as well as new opportunities in the cloud domain.more » « less
-
Abstract Conformal prediction provides machine learning models with prediction sets that offer theoretical guarantees, but the underlying assumption of exchangeability limits its applicability to time series data. Furthermore, existing approaches struggle to handle multi-step ahead prediction tasks, where uncertainty estimates across multiple future time points are crucial. We propose JANET (JointAdaptive predictioN-regionEstimation forTime-series), a novel framework for constructing conformal prediction regions that are valid for both univariate and multivariate time series. JANET generalises the inductive conformal framework and efficiently produces joint prediction regions with controlledK-familywise error rates, enabling flexible adaptation to specific application needs. Our empirical evaluation demonstrates JANET’s superior performance in multi-step prediction tasks across diverse time series datasets, highlighting its potential for reliable and interpretable uncertainty quantification in sequential data.more » « less
