Publication Library
A Modular Energy Aware Framework for Multicopter Modeling in Control and Planning Applications
Description: Unmanned aerial vehicles (UAVs), especially multicopters, have recently gained popularity for use in surveillance, monitoring, inspection, and search and rescue missions. Their maneuverability and ability to operate in confined spaces make them particularly useful in cluttered environments. For advanced control and mission planning applications, accurate and resource-efficient modeling of UAVs and their capabilities is essential. This study presents a modular approach to multicopter modeling that considers vehicle dynamics, energy consumption, and sensor integration. The power train model includes detailed descriptions of key components such as the lithium-ion battery, electronic speed controllers, and brushless DC motors. Their models are validated with real test flight data. In addition, sensor models, including LiDAR and cameras, are integrated to describe the equipment often used in surveillance and monitoring missions. The individual models are combined into an energy-aware multicopter model, which provide the basis for a companion study on path planning for unmanned aircaft system (UAS) swarms performing search and rescue missions in cluttered and dynamic environments. The flexible modeling approach enables easy description of different UAVs in a heterogeneous UAS swarm, allowing for energy-efficient operations and autonomous decision making for a reliable mission performance.
Created At: 07 April 2025
Updated At: 07 April 2025
Which LIME should I trust - Concepts, Challenges, and Solutions
Description: As neural networks become dominant in essential systems, Explainable Artificial Intelligence (XAI) plays a crucial role in fostering trust and detecting potential misbehavior of opaque models. LIME (Local Interpretable Model-agnostic Explanations) is among the most prominent model-agnostic approaches, generating explanations by approximating the behavior of black-box models around specific instances. Despite its popularity, LIME faces challenges related to fidelity, stability, and applicability to domain-specific problems. Numerous adaptations and enhancements have been proposed to address these issues, but the growing number of developments can be overwhelming, complicating efforts to navigate LIME-related research. To the best of our knowledge, this is the first survey to comprehensively explore and collect LIME's foundational concepts and known limitations. We categorize and compare its various enhancements, offering a structured taxonomy based on intermediate steps and key issues. Our analysis provides a holistic overview of advancements in LIME, guiding future research and helping practitioners identify suitable approaches. Additionally, we provide a continuously updated interactive website (this https URL), offering a concise and accessible overview of the survey.
Created At: 07 April 2025
Updated At: 07 April 2025
Decision Trees That Remember - Gradient-Based Learning of Recurrent Decision Trees with Memory
Description: Neural architectures such as Recurrent Neural Networks (RNNs), Transformers, and State-Space Models have shown great success in handling sequential data by learning temporal dependencies. Decision Trees (DTs), on the other hand, remain a widely used class of models for structured tabular data but are typically not designed to capture sequential patterns directly. Instead, DT-based approaches for time-series data often rely on feature engineering, such as manually incorporating lag features, which can be suboptimal for capturing complex temporal dependencies. To address this limitation, we introduce ReMeDe Trees, a novel recurrent DT architecture that integrates an internal memory mechanism, similar to RNNs, to learn long-term dependencies in sequential data. Our model learns hard, axis-aligned decision rules for both output generation and state updates, optimizing them efficiently via gradient descent. We provide a proof-of-concept study on synthetic benchmarks to demonstrate the effectiveness of our approach.
Created At: 07 April 2025
Updated At: 07 April 2025
Virtual Target Trajectory Prediction for Stochastic Targets
Description: Trajectory prediction of other vehicles is crucial for autonomous vehicles, with applications from missile guidance to UAV collision avoidance. Typically, target trajectories are assumed deterministic, but real-world aerial vehicles exhibit stochastic behavior, such as evasive maneuvers or gliders circling in thermals. This paper uses Conditional Normalizing Flows, an unsupervised Machine Learning technique, to learn and predict the stochastic behavior of targets of guided missiles using trajectory data. The trained model predicts the distribution of future target positions based on initial conditions and parameters of the dynamics. Samples from this distribution are clustered using a time series k-means algorithm to generate representative trajectories, termed virtual targets. The method is fast and target-agnostic, requiring only training data in the form of target trajectories. Thus, it serves as a drop-in replacement for deterministic trajectory predictions in guidance laws and path planning. Simulated scenarios demonstrate the approach's effectiveness for aerial vehicles with random maneuvers, bridging the gap between deterministic predictions and stochastic reality, advancing guidance and control algorithms for autonomous vehicles.
Created At: 07 April 2025
Updated At: 07 April 2025
From Deep Learning to LLMs - A survey of AI in Quantitative Investment
Description: Quantitative investment (quant) is an emerging, technology-driven approach in asset management, increasingy shaped by advancements in artificial intelligence. Recent advances in deep learning and large language models (LLMs) for quant finance have improved predictive modeling and enabled agent-based automation, suggesting a potential paradigm shift in this field. In this survey, taking alpha strategy as a representative example, we explore how AI contributes to the quantitative investment pipeline. We first examine the early stage of quant research, centered on human-crafted features and traditional statistical models with an established alpha pipeline. We then discuss the rise of deep learning, which enabled scalable modeling across the entire pipeline from data processing to order execution. Building on this, we highlight the emerging role of LLMs in extending AI beyond prediction, empowering autonomous agents to process unstructured data, generate alphas, and support self-iterative workflows.
Created At: 07 April 2025
Updated At: 07 April 2025