Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jane Jean Kiam has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Editorial: AI and robotics for increasing disaster resilience in modern societies

    by Jane Jean Kiam, Anastasios Dimou, Ron Alford, Armin Wedler, Yuichi Ambe

    Several previous publications have highlighted how unmanned systems can be used for disaster management. Erdelj and Natalizio (2016) point out clearly the three stages in disaster management where Unmanned Aerial Vehicles (UAVs) can be of essential support in: 1) early warning through sensorbased remote sensing, 2) disaster assessment with real-time monitoring of the disaster area, and 3) disaster response by being the communication nodes in a Wireless Sensor Network (WSN) or by transporting first aid to impervious areas. Guibaud et al. (2024) report on a real-world deployment of a remote-controlled ground robot for risk assessment during fire at Notre Dame Cathedral. A more recent scoping review by Mohd Daud et al. (2022) focuses on field reports of real-world deployments of UAVs, analyzing studies and experiments conducted using real-world data. In most scenarios, UAVs were used for disaster assessment by delivering images or by mapping the disaster area, including also three-dimensional mapping. Damage assessment in impervious areas was identified as the main advantage of UAVs in disaster management. Besides, UAVs can locate missing person(s) in Search and Rescue (SAR) operations faster, especially in snow-covered terrains.Alongside the increasing risks associated with disasters, advances in artificial intelligence (AI) are creating new opportunities to enhance disaster resilience. Beyond enabling robots to act as sensor payload carriers for situational awareness (Verykokou et al., 2018), the integration of AI facilitates increased autonomy in decision-making. For example, prior work has demonstrated automated planning for complex rescue missions using unmanned autonomous platforms (Patra et al., 2019;Bit-Monnot et al., 2018). Such capabilities enable more effective operations, thereby improving operational efficiency without requiring additional human involvement in the decision-making loop.Recent advancements in Large Language Models (LLMs) have also enable automated context extractions for disaster management (Xu et al., 2025;Chen et al., 2026), but also for seamless disaster response, in which operators command unmanned assets in natural language through LLM-powered interfaces (Döschl and Kiam, 2025).While robotics and AI were often topics of scientific publications, targeted applications often vary. Often, the application in disaster relief plays only a marginal role, for example being one of many example use cases for performance benchmarking. This special session addresses exactly recent advancements in robotics and AI in view of their use for increasing disaster resilience. Topics of interest include 1. Novel sensor techniques and sensor fusion algorithms to be integrated on unmanned vehicles deployed for disaster response;2. AI algorithms, frameworks, and systems for automated planning, sequential decision-making, multiagent coordination etc. of unmanned vehicles in disaster areas;3. Algorithms and methods for motion control of robots to be deployed in disaster areas (to overcome the physically challenging environment at a disaster site, e.g. uneven grounds due to debris for ground vehicles, stormy weather for aerial vehicles, etc.); 4. Collaborative capabilities for improved interaction of humans and unmanned vehicles in shared spaces; 5. Reporting on field validation tests for unmanned technologies in realistic environments and review articles.Accepted publications cover a wide spectrum of topics. Yamauchi et al. (2023) focus on the design and development of an innovative robot demonstrator, namely the 3.6 m long Dragon Firefighter (DFF), capable of extinguishing fire with onboard nozzles. The DFF has achieved stable manual flight, at the time the publication was submitted. In contrast, Tamura and Kamegawa (2023) addresses the control of snake robots on soft surfaces, which are highly relevant in disaster scenarios where terrain surface can vary significantly with respect to hardness. The developed control loop considers tactile feedback from different surface conditions, and uses a Central Pattern Generator (CPG) network to optimize coordination of the joints during locomotion.Focusing on a more conventional UGV platform, Zafar et al. (2024) extend beyond isolated control loop by integrating hand-gesture-based tele-operation and YOLO-based victim detection for more intuitive human-robot interaction in the operational pipeline for search-and-rescue missions. Additionally, Moosavi et al. (2024) and Döschl et al. (2025) address multi-robot operations. Moosavi et al. (2024) investigate path planning for multiple snake robots in rescue scenarios and demonstrates a functional coordination in a simulation environment. Meanwhile, Döschl et al. (2025) focus on symbolic planning for multiple aerial robots, providing validation in photorealistic simulation environments and outlining a pathway toward integration with real robotic hardware.This special session brings together a collection of recent state-of-the-art research contributions aimed at enhancing disaster resilience through the integration of AI and unmanned platforms. With the rapid advancement of AI, particularly in LLM-driven applications enabling increasingly sophisticated reasoning and decision-making capabilities (Webb et al., 2025), as well as recent progress in humanoid robotics (Han et al., 2025), the field is entering a phase of accelerated innovation. These developments are expected to continuously unlock new opportunities and research breakthroughs in the application of intelligent systems for disaster resilience.

  • Open Access

    AUSPEX: An integrated open-source decision-making framework for UAVs in rescue missions

    by Björn Döschl, Kai Sommer, Jane Jean Kiam

    Unmanned aerial vehicles (UAVs) have become paramount for search and rescue (SAR) missions due to their ability to access hazardous and challenging environments and to rapidly provide cost-effective aerial situational awareness. Nevertheless, current UAV systems are designed for specific tasks, often focusing on benchmarking use cases. Therefore, they offer limited adaptability for the diverse decision-making demands of SAR missions. Furthermore, commercially available integrated UAV systems are non-open-source, preventing further extension with state-of-the-art decision-making algorithms. In this paper, we introduce Automated Unmanned Aerial Swarm System for Planning and EXecution (AUSPEX), which is a holistic, modular, and open-source framework tailored specifically for enhancing the decision-making capabilities of UAV systems. AUSPEX integrates diverse capabilities for knowledge representation, perception, planning, and execution with state-of-the-art decision-making algorithms. Additionally, AUSPEX considers the heterogeneity of available UAV platforms and offers the possibility of including off-the-shelf and generic UAVs, with an open architecture into the AUSPEX ecosystem. The framework relies only on open-source components to ensure transparency, as well as system scalability and extensibility. We demonstrate AUSPEX’s integration with the Unreal Engine-based simulation framework REAP for software-in-the-loop validation and a platform-independent graphical user interface (AUGUR). We demonstrate how AUSPEX can be used for generic scenarios in SAR missions while highlighting its potential for future extensibility.


  • Open Access

    AUSPEX: An Integrated Open-Source Decision-Making Framework for UAVs in Rescue Missions

    by Björn Döschl, Kai Sommer, Jane Jean Kiam

    Unmanned Aerial Vehicles (UAVs) have become paramount for Search and Rescue (SAR) missions, due to their ability to access hazardous and challenging environments, thereby reducing response times significantly by providing cost-effective aerial perspectives for situational awareness. Nevertheless, current UAV systems are designed and optimised for specific tasks, often focusing on benchmarking use cases. Therefore, they bear limited possibility to adapt to diverse decision-making capabilities required for SAR missions. Furthermore, commercially available integrated UAV systems are nonopen source, preventing further extension with state-of-the-art decision-making algorithms. This paper introduces AUSPEX, a holistic modular and open-source framework, tailored specifically for enhancing decision-making capabilities of UAV-systems. AUSPEX integrates diverse capabilities to store and update knowledge, to sense the environment, to compute plans with state-of-the-art decisionmaking algorithms, and to execute the plans. Additionally, AUSPEX considers the heterogeneity of available UAV platforms, and offers the possibility of including off-the-shelf UAVs, as well as generic UAVs with an open architecture into the AUSPEX ecosystem. The framework relies only on open-source components, to ensure transparency, as well as system scalability and extensibility. We demonstrate the possibility of connecting AUSPEX to the Unreal Engine based simulation framework REAP for software-in-the-loop validation, as well as a platform-independent graphical user interface written in Flutter (AUGUR). We demonstrate how AUSPEX can be used for generic scenarios in SAR missions, while highlighting its potential for future extensibility.


  • Open Access

    Attention-based Conditional Random Field for Financial Fraud Detection

    by Prakash Jamakatel, Rebecca De Venezia, Christian Muise, Jane Jean Kiam

    Financial fraud detection is critical for market transparency and regulatory compliance. Existing methods often ignore the temporal patterns in financial data, which are essential for understanding dynamic financial behaviors and detecting fraud. Moreover, they also treat companies as independent entities, overlooking the valuable interrelationships. To address these issues, we propose ACRF-RNN, a Recurrent Neural Network (RNN) with Attention-based Conditional Random Field (CRF) for fraud detection. Specifically, we use an RNN with a sliding window to capture temporal dependencies from historical data, and an attention-based CRF feature transformer to model inter-company relationships. This transforms raw financial data into optimized features, fed into a multi-layer perceptron for classification. Besides, we also use the focal loss to alleviate the class imbalance problem caused by rare fraudulent cases. This work presents a novel real-world dataset to evaluate the performance of ACRF-RNN. Extensive experiments show that ACRF-RNN outperforms the state-of-the-art methods by 15.28% in KS and 4.04% in Recall. Data and code are available at: https://github.com/XNetLab/ACRF-RNN.git.


  • Open Access

    Towards Intelligent Companion Systems in General Aviation using Hierarchical Plan and Goal Recognition

    by Prakash Jamakatel, Pascal Bercher, Axel Schulte, Jane Jean Kiam

    Modern ultralight aircraft in general aviation are equipped with an onboard Pilot Assistance System (PAS) as a companion system, meant to guide the pilot in decision-making, e.g. with plan suggestions, especially in critical situations. For more meaningful guidance, the PAS must possess a continuous understanding of the context, i.e. the pilot’s intention, so that decision-making support is relevant. However, in realistic settings, the pilot’s intention is not communicated manually, but can only be proactively monitored by the PAS. This paper explores the possibility of embedding domain expertise using Hierarchical Task Network (HTN) planning to track the pilot’s intention, by recognising the pilot’s current goal task judging from the pilot’s actions. Furthermore, by leveraging probability theory for state estimation, we derive belief values to be associated with the recognised goal task, inferred from already executed actions which are in turn inferred from in-cockpit observable measurement data. Statistical evaluation using data collected from human-in-the-loop tests shows that our method for tracking the pilot’s intention is reliable enough to provide the PAS with a contextual understanding in real time.


  • Open Access

    Hierarchical Mission Planning with a GA-Optimizer for Unmanned High Altitude Pseudo-Satellites

    by Jane Jean Kiam, Eva Besada-Portas, Axel Schulte

    Unmanned Aerial Vehicles (UAVs) are gaining preference for mapping and monitoring ground activities, partially due to the cost efficiency and availability of lightweight high-resolution imaging sensors. Recent advances in solar-powered High Altitude Pseudo-Satellites (HAPSs) widen the future use of multiple UAVs of this sort for long-endurance remote sensing, from the lower stratosphere of vast ground areas. However, to increase mission success and safety, the effect of the wind on the platform dynamics and of the cloud coverage on the quality of the images must be considered during mission planning. For this reason, this article presents a new planner that, considering the weather conditions, determines the temporal hierarchical decomposition of the tasks of several HAPSs. This planner is supported by a Multiple Objective Evolutionary Algorithm (MOEA) that determines the best Pareto front of feasible high-level plans according to different objectives carefully defined to consider the uncertainties imposed by the time-varying conditions of the environment. Meanwhile, the feasibility of the plans is assured by integrating constraints handling techniques in the MOEA. Leveraging historical weather data and realistic mission settings, we analyze the performance of the planner for different scenarios and conclude that it is capable of determining overall good solutions under different conditions.