Mixed reality systems for space exploration integrating telemetry data, artificial intelligence, three dimensional modeling, and hardware interfaces

Advancing Spaceflight through a Digital Mirror and Artificial Intelligence

Human spaceflight represents a vital part of modern space exploration. The Artemis program and planned Gateway space station will soon push the boundaries of classical space exploration, necessitating innovative solutions to overcome the novel challenges of Life Support System (LSS) operation in extraterrestrial environments. Advanced simulation tools can facilitate the development and testing of LSSs within an environment that closely resembles actual mission conditions. This work presents the current development progress on a virtual model of the Columbus Science Laboratory onboard the International Space Station, specifically focusing on the Environmental Control and Life Support System as well as the Thermal Control System. The model was created using the simulation tool V-HAB (Virtual Habitat) and by performing a parameter identification study for the Condensing Heat Exchanger configuration. An initial test successfully demonstrated the methodology and enabled future development of a high-fidelity model. Additionally, the potential of integrating Machine Learning (ML) models for time series prediction was explored. The application of ML methods enables predictive maintenance, optimized resource allocation and enhanced system resilience, ultimately supporting the development of more efficient and reliable technologies.

MMUSV-Sim: A Perception-Oriented Simulation and Data-Generation Platform for Multi-USV Cooperative Perception

Cooperative perception among multiple unmanned surface vehicles (USVs) combines complementary observations to extend maritime target sensing beyond the view range and field of a single platform. Developing such systems at scale calls for a unified workflow for configurable multi-USV scenarios, multimodal acquisition, and shared annotations. We present MMUSV-Sim, a perception-oriented maritime simulation and data-generation platform built on Unreal Engine 5 and Project AirSim. It provides island, open-sea, and port environments; configurable weather, time of day, and wave conditions; a diverse vessel asset library; and spline-based multi-vessel motion. MMUSV-Sim acquires RGB, depth, semantic, LiDAR, and radar observations across multiple USVs and captures a common world state for per-agent annotation export. Experiments verify that the configured wave settings produce the intended changes in vessel heave, roll, and pitch, and evaluate the geometric consistency between projected annotations and semantic renderings. In LiDAR-based cooperative BEV vessel detection experiments on the generated multi-USV dataset, Early Fusion achieves an AP@0.5 of 72.74, compared with 45.54 using a single USV.

AI Sensor Fusion Technology for Self-Driving Intelligent Systems

A conceptual framework is proposed that interprets sensor fusion as a reconstructive process, transforming diverse sensory inputs into a coherent environmental model, and connects fusion strategies to key autonomous driving tasks, including object detection, tracking, localisation, and planning.

Future Generation Computer Systems

AI-Driven Distributed Multi-Sensor Fusion for Real-Time Drone Detection in Urban Airspace

The increasing density of unmanned aerial systems (UAS) in urban low-altitude airspace introduces significant safety and security challenges, particularly for detecting non-cooperative drones in environments where RADAR (Radio Detection and Ranging) deployment is impractical. This paper presents a distributed, artificial intelligence (AI)-enabled multi-sensor surveillance framework integrating visual, acoustic, and radio frequency (RF) sensing through weighted decision-level fusion.Each sensing modality is processed using dedicated deep learning models, while a decision-level fusion mechanism combines predictions based on confidence scores and reliability weights. The modular architecture enables asynchronous communication through a publisher–subscriber paradigm, supporting distributed deployment and resilience under partial sensor degradation.The system is evaluated through both laboratory experiments and simulated urban environments with varying complexity. Results demonstrate that the proposed framework achieves over 90% detection precision, maintains false positive rates below 10%, and supports real-time processing exceeding 50 Hz. Furthermore, the fusion strategy effectively mitigates performance degradation in individual sensing modalities, particularly under noisy or obstructed conditions.These results highlight the potential of AI-based distributed sensor fusion systems as a scalable and cost-effective solution for real-time drone surveillance in smart urban airspace, contributing to resilient monitoring within emerging U-space ecosystems.

Connected Radar: A New Paradigm for Atmospheric Observation and Experimentation

Advancing atmospheric science increasingly depends on how effectively we design, execute, and adapt observational experiments. While major progress has been made in numerical modeling and artificial intelligence (AI), observational experimentation has not kept pace. Most observing systems—including radars—still operate as largely stand-alone instruments, using fixed or heuristically-defined strategies that limit our ability to capture fast-evolving phenomena and fully exploit emerging analytical tools. Here, we argue for a shift from static, hardware-centric observations toward connected, outcome-driven experimentation. Drawing on lessons from the Multisensor Agile Adaptive Sampling (MAAS) project, we introduce the concept of Connected Radar, in which radars operate as part of an integrated, cloud-based experimental infrastructure that incorporates satellite data, lightning observations, cameras, drones, and AI-driven data fusion. In this paradigm, radar operation is treated as part of a controlled experiment, where sensing decisions are guided by scientific intent and information gain rather than predefined scan strategies. Artificial intelligence plays a central role by linking sensing actions to experimental outcomes through self-supervised learning, uncertainty estimation, and active sampling. This reframes radar agility as information (or cognitive) agility, not just physical beam steering. We show how this framework provides a natural pathway for fully exploiting phased-array radar capabilities and for rethinking future radar facilities as autonomous laboratories for atmospheric research—where scientific value is defined by insight gained, not hardware alone.