This paper addresses a motion planning problem to achieve spatio-temporal-logical tasks, expressed by syntactically co-safe linear temporal logic specifications (scLTL\next), in uncertain environments. Here, the uncertainty is modeled as some probabilistic knowledge on the semantic labels of the environment. For example, the task is "first go to region 1, then go to region 2"; however, the exact locations of regions 1 and 2 are not known a priori, instead a probabilistic belief is available. We propose a novel automata-theoretic approach, where a special product automaton is constructed to capture the uncertainty related to semantic labels, and a reward function is designed for each edge of this product automaton. The proposed algorithm utilizes value iteration for online replanning. We show some theoretical results and present some simulations/experiments to demonstrate the efficacy of the proposed approach.
This paper presents the innovative design and successful deployment of a pioneering autonomous unmanned aerial system developed for executing the world's largest mural painted by a drone. Addressing the dual challenges of maintaining artistic precision and operational reliability under adverse outdoor conditions such as wind and direct sunlight, our work introduces a robust system capable of navigating and painting outdoors with unprecedented accuracy. Key to our approach is a novel navigation system that combines an infrared (IR) motion capture camera and LiDAR technology, enabling precise location tracking tailored specifically for largescale artistic applications. We employ a unique control architecture that uses different regulation in tangential and normal directions relative to the planned path, enabling precise trajectory tracking and stable line rendering. We also present algorithms for trajectory planning and path optimization, allowing for complex curve drawing and area filling. The system includes a custom-designed paint spraying mechanism, specifically engineered to function effectively amidst the turbulent airflow generated by the drone's propellers, which also protects the drone's critical components from paint-related damage, ensuring longevity and consistent performance. Experimental results demonstrate the system's robustness and precision in varied conditions, showcasing its potential for autonomous large-scale art creation and expanding the functional applications of robotics in creative fields.
This paper introduces a novel $k$-cell decomposition method for pursuit-evasion problems in polygonal environments, where a searcher is equipped with a $k$-modem: a device capable of seeing through up to $k$ walls. The proposed decomposition ensures that as the searcher moves within a cell, the structure of unseen regions (shadows) remains unchanged, thereby preventing any geometric events between or on invisible regions, that is, preventing the appearance, disappearance, merge, or split of shadow regions. The method extends existing work on $0$- and $2$-visibility by incorporating m-visibility polygons for all even $0 \le m \le k$, constructing partition lines that enable robust environment division. The correctness of the decomposition is proved via three theorems. The decomposition enables reliable path planning for intruder detection in simulated environments and opens new avenues for visibility-based robotic surveillance. The difficulty in constructing the cells of the decomposition consists in computing the $k$-visibility polygon from each vertex and finding the intersection points of the partition lines to create the cells.
Huntington disease (HD) is a genetically inherited neurodegenerative disease with progressively worsening symptoms. Accurately modeling time to HD diagnosis is essential for clinical trial design and treatment planning. Langbehn's model, the CAG-Age Product (CAP) model, the Prognostic Index Normed (PIN) model, and the Multivariate Risk Score (MRS) model have all been proposed for this task. However, differing in methodology, assumptions, and accuracy, these models may yield conflicting predictions. Few studies have systematically compared these models' performance, and those that have could be misleading due to (i) testing the models on the same data used to train them and (ii) failing to account for high rates of right censoring (80%+) in performance metrics. We discuss the theoretical foundations of the four most common models of time to HD diagnosis, offering intuitive comparisons about their practical feasibility. Further, we externally validate their risk stratification abilities using data from the ENROLL-HD study and performance metrics that adjust for censoring. Our findings guide the selection of a model for HD clinical trial design. The MRS model, which incorporates the most covariates, performed the best. However, the simpler CAP and PIN models were not far behind and may be logistically simpler to adopt. We also show how these models can be used to estimate sample sizes for an HD clinical trial, emphasizing that previous estimates would lead to underpowered trials.
India achieved a significant milestone on August $23^{\text{rd}}$ 2023, becoming the fourth country to accomplish a soft landing on the Moon. This paper presents the powered descent trajectory design for the Chandrayaan-3 mission. The optimization framework is based on pseudospectral Radau collocation, and controllability-based waypoint refinement is employed to further enhance the robustness of the trajectory against state and control perturbations. Furthermore, the trade-off between fuel consumption and robustness is explicitly quantified, providing insights into the practical considerations of mission planning.
Safe multi-agent motion planning (MAMP) under task-induced constraints is a critical challenge in robotics. Many real-world scenarios require robots to navigate dynamic environments while adhering to manifold constraints imposed by tasks. For example, service robots must carry cups upright while avoiding collisions with humans or other robots. Despite recent advances in decentralized MAMP for high-dimensional systems, incorporating manifold constraints remains difficult. To address this, we propose a manifold-constrained Hamilton-Jacobi reachability (HJR) learning framework for decentralized MAMP. Our method solves HJR problems under manifold constraints to capture task-aware safety conditions, which are then integrated into a decentralized trajectory optimization planner. This enables robots to generate motion plans that are both safe and task-feasible without requiring assumptions about other agents' policies. Our approach generalizes across diverse manifold-constrained tasks and scales effectively to high-dimensional multi-agent manipulation problems. Experiments show that our method outperforms existing constrained motion planners and operates at speeds suitable for real-world applications. Video demonstrations are available at https://youtu.be/RYcEHMnPTH8 .
Large multimodal models (LMMs) are increasingly capable of interpreting visualizations, yet they continue to struggle with spatial reasoning. One proposed strategy is decomposition, which breaks down complex visualizations into structured components. In this work, we examine the efficacy of scalable vector graphics (SVGs) as a decomposition strategy for improving LMMs' performance on floor plans comprehension. Floor plans serve as a valuable testbed because they combine geometry, topology, and semantics, and their reliable comprehension has real-world applications, such as accessibility for blind and low-vision individuals. We conducted an exploratory study with three LMMs (GPT-4o, Claude 3.7 Sonnet, and Llama 3.2 11B Vision Instruct) across 75 floor plans. Results show that combining SVG with raster input (SVG+PNG) improves performance on spatial understanding tasks but often hinders spatial reasoning, particularly in pathfinding. These findings highlight both the promise and limitations of decomposition as a strategy for advancing spatial visualization comprehension.
Efficient production planning is essential in modern manufacturing to improve performance indicators such as lead time and to reduce reliance on human intuition. While mathematical optimization approaches, formulated as job shop scheduling problems, have been applied to automate this process, solving large-scale production planning problems remains computationally demanding. Moreover, many practical scenarios involve conflicting objectives, making traditional scalarization techniques ineffective in finding diverse and useful Pareto-optimal solutions. To address these challenges, we developed a quantum-classical hybrid algorithm that decomposes the problem into two subproblems: resource allocation and task scheduling. Resource allocation is formulated as a quadratic unconstrained binary optimization problem and solved using annealing-based methods that efficiently explore complex solutions. Task scheduling is modeled as a mixed-integer linear programming problem and solved using conventional solvers to satisfy detailed scheduling constraints. We validated the proposed method using benchmark instances based on foundry production scenarios. Experimental results demonstrate that our hybrid approach achieves superior solution quality and computational efficiency compared to traditional monolithic methods. This work offers a promising direction for high-speed, multi-objective scheduling in industrial applications.
Island endemism is shaped by complex interactions among environmental, ecological, and evolutionary factors, yet the relative contributions of topography, climate, and land cover remain incompletely quantified. We investigated the drivers of endemic plant richness across Crete, a Mediterranean biodiversity hotspot, using spatially explicit data on species distributions, topographic complexity, climatic variability, land cover, and soil characteristics. Artificial Neural Network models, a machine learning tool, were employed to assess the relative importance of these predictors and to identify hotspots of endemism. We found that total species richness, elevation range, and climatic variability were the strongest predictors of endemic richness, reflecting the role of biodiversity, topographic heterogeneity, and climatic gradients in generating diverse habitats and micro-refugia that promote speciation and buffer extinction risk. Endemic hotspots only partially overlapped with areas of high total species richness, indicating that total species richness was the optimal from the ones examined, yet an imperfect surrogate. These environmentally heterogeneous areas also provide critical ecosystem services, including soil stabilization, pollination, and cultural value, which are increasingly threatened by tourism, renewable energy development, land-use change, and climate impacts. Our findings underscore the importance of prioritizing mountainous and climatically variable regions in conservation planning, integrating ecosystem service considerations, and accounting for within-island spatial heterogeneity. By explicitly linking the environmental drivers of endemism to both biodiversity patterns and ecosystem function, this study provides a framework for evidence-based conservation planning in Crete and other Mediterranean islands with similar geological and biogeographic contexts.
Urban flooding is expected to increase in frequency and severity as a consequence of climate change, causing wide-ranging impacts that include a decrease in urban Quality of Life (QoL). Meanwhile, policymakers must devise adaptation strategies that can cope with the uncertain nature of climate change and the complex and dynamic nature of urban flooding. Reinforcement Learning (RL) holds significant promise in tackling such complex, dynamic, and uncertain problems. Because of this, we use RL to identify which climate adaptation pathways lead to a higher QoL in the long term. We do this using an Integrated Assessment Model (IAM) which combines a rainfall projection model, a flood model, a transport accessibility model, and a quality of life index. Our preliminary results suggest that this approach can be used to learn optimal adaptation measures and it outperforms other realistic and real-world planning strategies. Our framework is publicly available: https://github.com/MLSM-at-DTU/maat_qol_framework.
We introduce SENT-Map, a semantically enhanced topological map for representing indoor environments, designed to support autonomous navigation and manipulation by leveraging advancements in foundational models (FMs). Through representing the environment in a JSON text format, we enable semantic information to be added and edited in a format that both humans and FMs understand, while grounding the robot to existing nodes during planning to avoid infeasible states during deployment. Our proposed framework employs a two stage approach, first mapping the environment alongside an operator with a Vision-FM, then using the SENT-Map representation alongside a natural-language query within an FM for planning. Our experimental results show that semantic-enhancement enables even small locally-deployable FMs to successfully plan over indoor environments.
Objective: To validate a newly proposed stochastic differential equation (SDE)-based model for proton beam energy deposition by comparing its predictions with those from Geant4 in simplified phantom scenarios. Approach: Building on previous work in Crossley et al. (2025), where energy deposition from a proton beam was modelled using an SDE framework, we implemented the model with standard approximations to interaction cross sections and mean excitation energies, which makes simulations easily adaptable to new materials and configurations. The model was benchmarked against Geant4 in homogeneous and heterogeneous phantoms. Main results: The SDE-based dose distributions agreed well with Geant4, showing range differences within 0.4 mm and 3D gamma pass rates exceeding 98% under 3%/2 mm criteria with a 1% dose threshold. The model achieved a computational speed-up of approximately fivefold relative to Geant4, consistent across different Geant4 physics lists. Significance: These results demonstrate that the SDE approach can reproduce accuracy comparable to high-fidelity Monte Carlo for proton therapy at a fraction of the computational cost, highlighting its potential for accelerating dose calculations and treatment planning.
Robots must understand their environment from raw sensory inputs and reason about the consequences of their actions in it to solve complex tasks. Behavior Cloning (BC) leverages task-specific human demonstrations to learn this knowledge as end-to-end policies. However, these policies are difficult to transfer to new tasks, and generating training data is challenging because it requires careful demonstrations and frequent environment resets. In contrast to such policy-based view, in this paper we take a model-based approach where we collect a few hours of unstructured easy-to-collect play data to learn an action-conditioned visual world model, a diffusion-based action sampler, and optionally a reward model. The world model -- in combination with the action sampler and a reward model -- is then used to optimize long sequences of actions with a Monte Carlo Tree Search (MCTS) planner. The resulting plans are executed on the robot via a zeroth-order Model Predictive Controller (MPC). We show that the action sampler mitigates hallucinations of the world model during planning and validate our approach on 3 real-world robotic tasks with varying levels of planning and modeling complexity. Our experiments support the hypothesis that planning leads to a significant improvement over BC baselines on a standard manipulation test environment.
In the era of large spectroscopic surveys, a vast amount of spectra of massive stars will be gathered and supplemented by the wealth of astrometric and photometric data provided by the Gaia satellite. Released data will mean a major step forward in the study of massive stars, giving us the chance to create statistically significant samples to explore the role of almost any parameter. In this contribution, I introduce to the community the Multi-wavelength Exploration of massIve star-forminG regions and ASsociations project (MEIGAS) and long-term plans for conducting comprehensive studies in the major galactic and near extragalactic star-forming regions and OB associations. Benefiting from current and forthcoming data from large scale spectroscopic surveys such as WEAVE and 4MOST (among others), as well as complementary observations at different wavelength ranges, the project aims to achieve crucial and complementary information to adequately characterize these regions and their stellar content, something imperative to improve our understanding of star formation and poorly known evolutionary pathways of massive stars.
We present a foundation model for brain MRI that can work with different combinations of imaging sequences. The model uses one encoder with learnable modality embeddings, conditional layer normalization, and a masked autoencoding objective that accounts for missing modalities. A variance-covariance regularizer is applied to stabilize feature learning and improve representation diversity. This design removes the need for separate models for each modality and allows the network to adapt when some sequences are missing or unseen. It is trained on about 60,000 multi-center MRIs using self-supervised reconstruction and modality imputation to learn flexible representations. A learnable modality embedding guides feature extraction so the encoder can adjust to different inputs. We describe our planned evaluation on brain tumor and multiple sclerosis segmentation, as well as lesion classification, under various modality settings. Preliminary results show that the method works feasibly, and further experiments are planned to study its performance in more detail. All code and pretrained models are available at https://github.com/BrainFM/brainfm
Using Croatian data and the IMF's Natural Disaster Debt Dynamic Tool, this paper assesses how public debt adjusts to extreme events in a small open economy. We compare debt paths under baseline and stress scenarios, the latter simulating a major earthquake in 2025. Croatia provides a unique setting for evaluating post-disaster recovery in countries recently incorporated into the European Union. Our benchmark projections, which assume moderate economic growth and a broadly neutral fiscal stance, suggest the debt-to-GDP ratio will gradually decline to below 55% by 2040. In contrast, in the disaster scenario, we document a sharp short-term increase and a persistent upward shift in the debt trajectory, reaching 75% of GDP. Deterministic and stochastic simulations allow us to assess the distribution of potential outcomes. It is shown that, in the absence of shocks, public debt is on a sustainable downward path, but a severe natural disaster could reverse this trend and keep it elevated for years. Our findings highlight the importance of fiscal buffers that are critical for creating space to absorb shocks. The paper innovates by integrating natural disaster stress-testing into public debt analysis, with implications for fiscal risk management and policy planning. While we focus on Croatia, the mechanisms we uncover have broader implications for small open economies exposed to extreme events.
Pavement infrastructure monitoring is challenged by complex spatial dependencies, changing environmental conditions, and non-linear deterioration across road networks. Traditional Pavement Management Systems (PMS) remain largely reactive, lacking real-time intelligence for failure prevention and optimal maintenance planning. To address this, we propose a unified Digital Twin (DT) and Graph Neural Network (GNN) framework for scalable, data-driven pavement health monitoring and predictive maintenance. Pavement segments and spatial relations are modeled as graph nodes and edges, while real-time UAV, sensor, and LiDAR data stream into the DT. The inductive GNN learns deterioration patterns from graph-structured inputs to forecast distress and enable proactive interventions. Trained on a real-world-inspired dataset with segment attributes and dynamic connectivity, our model achieves an R2 of 0.3798, outperforming baseline regressors and effectively capturing non-linear degradation. We also develop an interactive dashboard and reinforcement learning module for simulation, visualization, and adaptive maintenance planning. This DT-GNN integration enhances forecasting precision and establishes a closed feedback loop for continuous improvement, positioning the approach as a foundation for proactive, intelligent, and sustainable pavement management, with future extensions toward real-world deployment, multi-agent coordination, and smart-city integration.
Glioma segmentation is critical for diagnosis and treatment planning, yet remains challenging in Sub-Saharan Africa due to limited MRI infrastructure and heterogeneous acquisition protocols that induce severe domain shift. We propose SegFormer3D-plus, a radiomics-guided transformer architecture designed for robust segmentation under domain variability. Our method combines: (1) histogram matching for intensity harmonization across scanners, (2) radiomic feature extraction with PCA-reduced k-means for domain-aware stratified sampling, (3) a dual-pathway encoder with frequency-aware feature extraction and spatial-channel attention, and (4) composite Dice-Cross-Entropy loss for boundary refinement. Pretrained on BraTS 2023 and fine-tuned on BraTS-Africa data, SegFormer3D-plus demonstrates improved tumor subregion delineation and boundary localization across heterogeneous African clinical scans, highlighting the value of radiomics-guided domain adaptation for resource-limited settings.
As AI deployments become more complex and high-stakes, it becomes increasingly important to be able to estimate their risk. AI control is one framework for doing so. However, good control evaluations require eliciting strong attack policies. This can be challenging in complex agentic environments where compute constraints leave us data-poor. In this work, we show how to optimize attack policies in SHADE-Arena, a dataset of diverse realistic control environments. We do this by decomposing attack capability into five constituent skills -- suspicion modeling, attack selection, plan synthesis, execution and subtlety -- and optimizing each component individually. To get around the constraint of limited data, we develop a probabilistic model of attack dynamics, optimize our attack hyperparameters using this simulation, and then show that the results transfer to SHADE-Arena. This results in a substantial improvement in attack strength, reducing safety score from a baseline of 0.87 to 0.41 using our scaffold.
In Major League Baseball, strategy and planning are major factors in determining the outcome of a game. Previous studies have aided this by building machine learning models for predicting the winning team of any given game. We extend this work by training a comprehensive set of machine learning models using a common dataset. In addition, we relate the win probabilities produced by these models to win strength as measured by score differential. In doing so we show that the most common machine learning models do indeed demonstrate a relationship between predicted win probability and the strength of the win. Finally, we analyze the results of using predicted win probabilities as a decision making mechanism on run-line betting. We demonstrate positive returns when utilizing appropriate betting strategies, and show that naive use of machine learning models for betting lead to significant loses.
Medical image segmentation is a critical achievement in modern medical science, developed over decades of research. It allows for the exact delineation of anatomical and pathological features in two- or three-dimensional pictures by utilizing notions like pixel intensity, texture, and anatomical context. With the advent of automated segmentation, physicians and radiologists may now concentrate on diagnosis and treatment planning while intelligent computers perform routine image processing tasks. This study used the BraTS Sub-Saharan Africa dataset, a selected subset of the BraTS dataset that included 60 multimodal MRI cases from patients with glioma. Surprisingly, the nnU Net model trained on the initial 60 instances performed better than the network trained on an offline-augmented dataset of 360 cases. Hypothetically, the offline augmentations introduced artificial anatomical variances or intensity distributions, reducing generalization. In contrast, the original dataset, when paired with nnU Net's robust online augmentation procedures, maintained realistic variability and produced better results. The study achieved a Dice score of 0.84 for whole tumor segmentation. These findings highlight the significance of data quality and proper augmentation approaches in constructing accurate, generalizable medical picture segmentation models, particularly for under-represented locations.
In this paper, we construct an air-sea collaborative system framework based on the Integrated Sensing and Communication (ISAC) techniques, where the Unmanned Aerial Vehicle (UAV) and Unmanned Surface Vehicle (USV) jointly inspect targets of interest while keeping communication with each other simultaneously. First, we demonstrate the unique challenges encountered in this collaborative system, i.e., the coupling and heterogeneity of the UAV/USV's trajectories. Then, we formulate a total energy consumption minimization problem to jointly optimize the trajectories, flying and hovering times, target scheduling, and beamformers under the constraints of water currents, collision avoidance, and Sensing and Communication (S\&C) requirements. To address the strong coupling of the variables, we divide the original problem into two subproblems, namely, the hover point selection and the joint trajectory planning and beamforming design. In the first subproblem, we propose a three-step hierarchical method including: (1) a virtual base station coverage (VBSC) and clustering algorithm to obtain the target scheduling and rough position of hover points; (2) a Bi-traveling salesman problem with neighborhood (Bi-TSPN)-based algorithm to determine the visiting order sequence of the hover points; (3) a hover point refinement and time allocation algorithm to further optimize the time allocation. In the latter subproblem, we complete the remaining trajectory planning and beamforming design in each flying and hovering stage by developing a semi-definite relaxation (SDR) and successive convex approximation (SCA) method. Finally, we conduct a series of simulations to demonstrate the superiority of the proposed scheme over existing sequential access and leader-follower strategies.
We introduce SigmaCollab, a dataset enabling research on physically situated human-AI collaboration. The dataset consists of a set of 85 sessions in which untrained participants were guided by a mixed-reality assistive AI agent in performing procedural tasks in the physical world. SigmaCollab includes a set of rich, multimodal data streams, such as the participant and system audio, egocentric camera views from the head-mounted device, depth maps, head, hand and gaze tracking information, as well as additional annotations performed post-hoc. While the dataset is relatively small in size (~ 14 hours), its application-driven and interactive nature brings to the fore novel research challenges for human-AI collaboration, and provides more realistic testing grounds for various AI models operating in this space. In future work, we plan to use the dataset to construct a set of benchmarks for physically situated collaboration in mixed-reality task assistive scenarios. SigmaCollab is available at https://github.com/microsoft/SigmaCollab.
This work presents a mathematical model to enable rapid prediction of airborne contaminant transport based on scarce sensor measurements. The method is designed for applications in critical infrastructure protection (CIP), such as evacuation planning following contaminant release. In such scenarios, timely and reliable decision-making is essential, despite limited observation data. To identify contaminant sources, we formulate an inverse problem governed by an advection-diffusion equation. Given the problem's underdetermined nature, we further employ a variational regularization ansatz and model the unknown contaminant sources as distribution over the spatial domain. To efficiently solve the arising inverse problem, we employ a problem-specific variant of the Primal-Dual-Active-Point (PDAP) algorithm which efficiently approximates sparse minimizers of the inverse problem by alternating between greedy location updates and source intensity optimization. The approach is demonstrated on two- and three-dimensional test cases involving both instantaneous and continuous contaminant sources and outperforms state-of-the-art techniques with $L^2$-regularization. Its effectiveness is further illustrated in complex domains with real-world building geometries imported from OpenStreetMap.
Agentic AI represents a new paradigm for automating complex systems by using Large AI Models (LAMs) to provide human-level cognitive abilities with multimodal perception, planning, memory, and reasoning capabilities. This will lead to a new generation of AI systems that autonomously decompose goals, retain context over time, learn continuously, operate across tools and environments, and adapt dynamically. The complexity of 5G and upcoming 6G networks renders manual optimization ineffective, pointing to Agentic AI as a method for automating decisions in dynamic RAN environments. However, despite its rapid advances, there is no established framework outlining the foundational components and operational principles of Agentic AI systems nor a universally accepted definition. This paper contributes to ongoing research on Agentic AI in 5G and 6G networks by outlining its core concepts and then proposing a practical use case that applies Agentic principles to RAN optimization. We first introduce Agentic AI, tracing its evolution from classical agents and discussing the progress from workflows and simple AI agents to Agentic AI. Core design patterns-reflection, planning, tool use, and multi-agent collaboration-are then described to illustrate how intelligent behaviors are orchestrated. These theorical concepts are grounded in the context of mobile networks, with a focus on RAN management and optimization. A practical 5G RAN case study shows how time-series analytics and LAM-driven agents collaborate for KPI-based autonomous decision-making.
Intelligent transportation systems (ITS) still have a hard time accurately predicting traffic in cities, especially in big, multimodal settings with complicated spatiotemporal dynamics. This paper presents HybridST, a hybrid architecture that integrates Graph Neural Networks (GNNs), multi-head temporal Transformers, and supervised ensemble learning methods (XGBoost or Random Forest) to collectively capture spatial dependencies, long-range temporal patterns, and exogenous signals, including weather, calendar, or control states. We test our model on the METR-LA, PEMS-BAY, and Seattle Loop tree public benchmark datasets. These datasets include situations ranging from freeway sensor networks to vehicle-infrastructure cooperative perception. Experimental results show that HybridST consistently beats classical baselines (LSTM, GCN, DCRNN, PDFormer) on important metrics like MAE and RMSE, while still being very scalable and easy to understand. The proposed framework presents a promising avenue for real-time urban mobility planning, energy optimization, and congestion alleviation strategies, especially within the framework of smart cities and significant events such as the 2030 FIFA World Cup.
Moving object segmentation is a crucial task for safe and reliable autonomous mobile systems like self-driving cars, improving the reliability and robustness of subsequent tasks like SLAM or path planning. While the segmentation of camera or LiDAR data is widely researched and achieves great results, it often introduces an increased latency by requiring the accumulation of temporal sequences to gain the necessary temporal context. Radar sensors overcome this problem with their ability to provide a direct measurement of a point's Doppler velocity, which can be exploited for single-scan moving object segmentation. However, radar point clouds are often sparse and noisy, making data annotation for use in supervised learning very tedious, time-consuming, and cost-intensive. To overcome this problem, we address the task of self-supervised moving object segmentation of sparse and noisy radar point clouds. We follow a two-step approach of contrastive self-supervised representation learning with subsequent supervised fine-tuning using limited amounts of annotated data. We propose a novel clustering-based contrastive loss function with cluster refinement based on dynamic points removal to pretrain the network to produce motion-aware representations of the radar data. Our method improves label efficiency after fine-tuning, effectively boosting state-of-the-art performance by self-supervised pretraining.
Aerial manipulation combines the maneuverability of multirotors with the dexterity of robotic arms to perform complex tasks in cluttered spaces. Yet planning safe, dynamically feasible trajectories remains difficult due to whole-body collision avoidance and the conservativeness of common geometric abstractions such as bounding boxes or ellipsoids. We present a whole-body motion planning and safety-critical control framework for aerial manipulators built on superquadrics (SQs). Using an SQ-plus-proxy representation, we model both the vehicle and obstacles with differentiable, geometry-accurate surfaces. Leveraging this representation, we introduce a maximum-clearance planner that fuses Voronoi diagrams with an equilibrium-manifold formulation to generate smooth, collision-aware trajectories. We further design a safety-critical controller that jointly enforces thrust limits and collision avoidance via high-order control barrier functions. In simulation, our approach outperforms sampling-based planners in cluttered environments, producing faster, safer, and smoother trajectories and exceeding ellipsoid-based baselines in geometric fidelity. Actual experiments on a physical aerial-manipulation platform confirm feasibility and robustness, demonstrating consistent performance across simulation and hardware settings. The video can be found at https://youtu.be/hQYKwrWf1Ak.
This paper presents the ZJUNlict team's work over the past year, covering both hardware and software advancements. In the hardware domain, the integration of an IMU into the v2023 robot was completed to enhance posture accuracy and angular velocity planning. On the software side, key modules were optimized, including the strategy and CUDA modules, with significant improvements in decision making efficiency, ball pursuit prediction, and ball possession prediction to adapt to high-tempo game dynamics.
Head-and-neck cancer (HNC) planning is difficult because multiple critical organs-at-risk (OARs) are close to complex targets. Intensity-modulated carbon-ion therapy (IMCT) offers superior dose conformity and OAR sparing but remains slow due to relative biological effectiveness (RBE) modeling, leading to laborious, experience-based, and often suboptimal tuning of many treatment-planning parameters (TPPs). Recent deep learning (DL) methods are limited by data bias and plan feasibility, while reinforcement learning (RL) struggles to efficiently explore the exponentially large TPP search space. We propose a scalable multi-agent RL (MARL) framework for parallel tuning of 45 TPPs in IMCT. It uses a centralized-training decentralized-execution (CTDE) QMIX backbone with Double DQN, Dueling DQN, and recurrent encoding (DRQN) for stable learning in a high-dimensional, non-stationary environment. To enhance efficiency, we (1) use compact historical DVH vectors as state inputs, (2) apply a linear action-to-value transform mapping small discrete actions to uniform parameter adjustments, and (3) design an absolute, clinically informed piecewise reward aligned with plan scores. A synchronous multi-process worker system interfaces with the PHOENIX TPS for parallel optimization and accelerated data collection. On a head-and-neck dataset (10 training, 10 testing), the method tuned 45 parameters simultaneously and produced plans comparable to or better than expert manual ones (relative plan score: RL $85.93\pm7.85%$ vs Manual $85.02\pm6.92%$), with significant (p-value $<$ 0.05) improvements for five OARs. The framework efficiently explores high-dimensional TPP spaces and generates clinically competitive IMCT plans through direct TPS interaction, notably improving OAR sparing.