This paper tackles open-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and one-shot generation paradigms that easily suffer from long-context failure issues like "loss in the middle" and hallucinations. To address these challenges, we introduce WebWeaver, a novel dual-agent framework that emulates the human research process. The planner operates in a dynamic cycle, iteratively interleaving evidence acquisition with outline optimization to produce a comprehensive, source-grounded outline linking to a memory bank of evidence. The writer then executes a hierarchical retrieval and writing process, composing the report section by section. By performing targeted retrieval of only the necessary evidence from the memory bank for each part, it effectively mitigates long-context issues. Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym. These results validate our human-centric, iterative methodology, demonstrating that adaptive planning and focused synthesis are crucial for producing high-quality, reliable, and well-structured reports.
As a fundamental problem in transportation and operations research, the bilevel capacity expansion problem (BCEP) has been extensively studied for decades. In practice, BCEPs are commonly addressed in two stages: first, pre-select a small set of links for expansion; then, optimize their capacities. However, this sequential and separable approach can lead to suboptimal solutions as it neglects the critical interdependence between link selection and capacity allocation. In this paper, we propose to introduce a cardinality constraint into the BCEP to limit the number of expansion locations rather than fixing such locations beforehand. This allows us to search over all possible link combinations within the prescribed limit, thereby enabling the joint optimization of both expansion locations and capacity levels. The resulting cardinality-constrained BCEP (CCBCEP) is computationally challenging due to the combination of a nonconvex equilibrium constraint and a nonconvex and discontinuous cardinality constraint. To address this challenge, we develop a penalized difference-of-convex (DC) approach that transforms the original problem into a sequence of tractable subproblems by exploiting its inherent DC structure and the special properties of the cardinality constraint. We prove that the method converges to approximate Karush-Kuhn-Tucker (KKT) solutions with arbitrarily prescribed accuracy. Numerical experiments further show that the proposed approach consistently outperforms alternative methods for identifying practically feasible expansion plans investing only a few links, both in solution quality and computational efficiency.
High-energy heavy-ion particle accelerators have long served as a proxy for the harsh space radiation environment, enabling both fundamental life-science research and applied testing of flight components. Typically, monoenergetic high-energy heavy-ion beams are used to mimic the complex mixed radiation field encountered in low Earth orbit and beyond. However, synergistic effects arising from the spatial or temporal proximity of interactions of different radiation qualities in a mixed field cannot be fully assessed with such beams. Therefore, spearheaded by developments at the NASA Space Radiation Laboratory, the GSI Helmholtzzentrum fuer Schwerionenforschung, supported by ESA, has developed advanced space radiation simulation capabilities to support space radiation studies in Europe. Here, we report the design, optimization, and in-silico benchmarking of GSI's hybrid active-passive GCR simulator. Additionally, a computationally optimized phase-space particle source for Geant4 is presented, which will be made available to external users to support their own in-silico studies and experimental planning.
The CUbesat Solar Polarimeter (CUSP) project is a CubeSat mission planned for a launch in low-Earth orbit and aimed to measure the linear polarization of solar flares in the hard X-ray band by means of a Compton scattering polarimeter. CUSP will allow us to study the magnetic reconnection and particle acceleration in the flaring magnetic structures of our star. CUSP is a project in the framework of the Alcor Program of the Italian Space Agency aimed at developing new CubeSat missions. It is undergoing a 12-month Phase B that started in December 2024. The Compton polarimeter on board CUSP is composed of two acquisition chains based on plastic scintillators read out by Multi-Anode PhotoMultiplier Tubes for the scatterer part and GAGG crystals coupled to Avalanche PhotoDiodes for the absorbers. An event coincident between the two readout schemes will lead to a measurement of the incoming X-ray's azimuthal scattering angle, linked to the polarization of the solar flare in a statistical manner. The current status of the CUSP mission design, mission analysis, and payload scientific performance will be reported. The latter will be discussed based on preliminary laboratory results obtained in parallel with Geant4 simulations.
Model-based reinforcement learning (MBRL) has shown significant potential in robotics due to its high sample efficiency and planning capability. However, extending MBRL to multi-robot cooperation remains challenging due to the complexity of joint dynamics. To address this, we propose the Sequential World Model (SeqWM), a novel framework that integrates the sequential paradigm into model-based multi-agent reinforcement learning. SeqWM employs independent, sequentially structured agent-wise world models to decompose complex joint dynamics. Latent rollouts and decision-making are performed through sequential communication, where each agent generates its future trajectory and plans its actions based on the predictions of its predecessors. This design enables explicit intention sharing, enhancing cooperative performance, and reduces communication overhead to linear complexity. Results in challenging simulated environments (Bi-DexHands and Multi-Quad) show that SeqWM outperforms existing state-of-the-art model-free and model-based baselines in both overall performance and sample efficiency, while exhibiting advanced cooperative behaviors such as predictive adaptation and role division. Furthermore, SeqWM has been success fully deployed on physical quadruped robots, demonstrating its effectiveness in real-world multi-robot systems. Demos and code are available at: https://github.com/zhaozijie2022/seqwm-marl
We consider the problem of computing aircraft arrival routes in a terminal maneuvering area (TMA) together with an automated scheduling of all the arrivals within a given time interval. The arrival routes are modeled as energy-efficient continuous-descent operations, such that separation based on wake-turbulence categories is guaranteed within the TMA. We propose a new model based on a Dantzig-Wolfe reformulation of a previous model for this problem. As in the previous model, we include tree consistency across consecutive planning intervals. However, the reformulation enables us to further improve the model and also consider aircraft that remain in the TMA from the previous period, a feature critical for operational safety. In computational experiments for Stockholm Arlanda airport, the new model consistently outperforms the previous one: we obtain solutions within 5 seconds to 12.65 minutes compared to 40.9 hours with the old model for instances of half hours with high traffic. In addition, we are able to solve instances of a full hour of arriving aircraft with high traffic (33 aircraft) within 22.22 to 58.57 minutes, whereas the old model could not solve these instances at all. While we schedule all aircraft as continuous-descent arrivals, our model can be applied to any type of speed profiles for the arriving aircraft.
Population estimation is crucial for various applications, from resource allocation to urban planning. Traditional methods such as surveys and censuses are expensive, time-consuming and also heavily dependent on human resources, requiring significant manpower for data collection and processing. In this study a deep learning solution is proposed to estimate population using high resolution (0.3 m) satellite imagery, Digital Elevation Models (DEM) of 0.5m resolution and vector boundaries. Proposed method combines Convolution Neural Network (CNN) architecture for classification task to classify buildings as residential and non-residential and Artificial Neural Network (ANN) architecture to estimate the population. Approx. 48k building footprints over Gandhinagar urban area are utilized containing both residential and non-residential, with residential categories further used for building-level population estimation. Experimental results on a large-scale dataset demonstrate the effectiveness of our model, achieving an impressive overall F1-score of 0.9936. The proposed system employs advanced geospatial analysis with high spatial resolution to estimate Gandhinagar population at 278,954. By integrating real-time data updates, standardized metrics, and infrastructure planning capabilities, this automated approach addresses critical limitations of conventional census-based methodologies. The framework provides municipalities with a scalable and replicable tool for optimized resource management in rapidly urbanizing cities, showcasing the efficiency of AI-driven geospatial analytics in enhancing data-driven urban governance.
Inspired by biological systems, we introduce a general framework for quasi-static shape control of human-scale structures under slowly varying external actions or requirements. In this setting, shape control aims to traverse the stable sub-manifolds of the equilibrium set to meet some predefined requirements or optimization criteria. As finite deformations are allowed, the equilibrium set may have a non-trivial topology. This paper explores the implications of large shape changes and high compliance, such as the emergence of unstable equilibria and equilibrium sets with non-trivial topology. We identify various adaptivity scenarios, ranging from inverse kinematics to optimization and path planning problems, and discuss the role of time-dependent loads and requirements. The applicability of the proposed concepts is demonstrated through the example of a curved Kirchhoff rod that is susceptible to snap-through behavior.
Establishing standardized metrics for Social Robot Navigation (SRN) algorithms for assessing the quality and social compliance of robot behavior around humans is essential for SRN research. Currently, commonly used evaluation metrics lack the ability to quantify how cooperative an agent behaves in interaction with humans. Concretely, in a simple frontal approach scenario, no metric specifically captures if both agents cooperate or if one agent stays on collision course and the other agent is forced to evade. To address this limitation, we propose two new metrics, a conflict intensity metric and the responsibility metric. Together, these metrics are capable of evaluating the quality of human-robot interactions by showing how much a given algorithm has contributed to reducing a conflict and which agent actually took responsibility of the resolution. This work aims to contribute to the development of a comprehensive and standardized evaluation methodology for SRN, ultimately enhancing the safety, efficiency, and social acceptance of robots in human-centric environments.
The simultaneous observation of gamma rays and neutrinos from the same astrophysical source offers a unique opportunity to probe particle acceleration and interaction mechanisms in ultra-high-energy environments. The Cherenkov Telescope Array Observatory (CTAO) is a next-generation ground-based gamma-ray facility, sensitive to energies from 20~GeV to 300~TeV. In this work, we present for the first time a performance study of CTAO based on joint simulations of steady-state sources emitting both neutrinos and gamma rays, under the assumption that neutrino events are detected by the KM3NeT telescope in the Northern Hemisphere. To identify potentially observable sources, we apply a neutrino-based selection filter according to KM3NeT's discovery potential. We then simulate gamma-ray detectability with CTAO, taking into account visibility, sensitivity, and extragalactic background light absorption. The analysis is specifically focused on exploring the detectability of sources at low neutrino luminosities, limited to values below $10^{52}\,\mathrm{erg\,yr^{-1}}$, in order to assess the performance of CTAO and KM3NeT in identifying faint extragalactic emitters. Particular attention is given to the strategic role of KM3NeT's geographic location, which provides access to Southern-sky sources, and to the impact of the planned CTA+ upgrade, which will enhance CTAO-South with Large-Sized Telescopes (LSTs). Our results highlight the importance of coordinated multi-messenger strategies between KM3NeT and CTAO to maximize the discovery potential of astrophysical neutrino sources.
We investigate the task and motion planning problem for Signal Temporal Logic (STL) specifications in robotics. Existing STL methods rely on pre-defined maps or mobility representations, which are ineffective in unstructured real-world environments. We propose the \emph{Structured-MoE STL Planner} (\textbf{S-MSP}), a differentiable framework that maps synchronized multi-view camera observations and an STL specification directly to a feasible trajectory. S-MSP integrates STL constraints within a unified pipeline, trained with a composite loss that combines trajectory reconstruction and STL robustness. A \emph{structure-aware} Mixture-of-Experts (MoE) model enables horizon-aware specialization by projecting sub-tasks into temporally anchored embeddings. We evaluate S-MSP using a high-fidelity simulation of factory-logistics scenarios with temporally constrained tasks. Experiments show that S-MSP outperforms single-expert baselines in STL satisfaction and trajectory feasibility. A rule-based \emph{safety filter} at inference improves physical executability without compromising logical correctness, showcasing the practicality of the approach.
True Digital Orthophoto Map (TDOM) serves as a crucial geospatial product in various fields such as urban management, city planning, land surveying, etc. However, traditional TDOM generation methods generally rely on a complex offline photogrammetric pipeline, resulting in delays that hinder real-time applications. Moreover, the quality of TDOM may degrade due to various challenges, such as inaccurate camera poses or Digital Surface Model (DSM) and scene occlusions. To address these challenges, this work introduces A-TDOM, a near real-time TDOM generation method based on On-the-Fly 3DGS optimization. As each image is acquired, its pose and sparse point cloud are computed via On-the-Fly SfM. Then new Gaussians are integrated and optimized into previously unseen or coarsely reconstructed regions. By integrating with orthogonal splatting, A-TDOM can render just after each update of a new 3DGS field. Initial experiments on multiple benchmarks show that the proposed A-TDOM is capable of actively rendering TDOM in near real-time, with 3DGS optimization for each new image in seconds while maintaining acceptable rendering quality and TDOM geometric accuracy.
Most existing spatial reasoning benchmarks focus on static or globally observable environments, failing to capture the challenges of long-horizon reasoning and memory utilization under partial observability and dynamic changes. We introduce two dynamic spatial benchmarks, locally observable maze navigation and match-2 elimination that systematically evaluate models' abilities in spatial understanding and adaptive planning when local perception, environment feedback, and global objectives are tightly coupled. Each action triggers structural changes in the environment, requiring continuous update of cognition and strategy. We further propose a subjective experience-based memory mechanism for cross-task experience transfer and validation. Experiments show that our benchmarks reveal key limitations of mainstream models in dynamic spatial reasoning and long-term memory, providing a comprehensive platform for future methodological advances. Our code and data are available at https://anonymous.4open.science/r/EvoEmpirBench-143C/.
This paper presents an adaptive air transit network leveraging modular aerial pods and artificial intelligence (AI) to address urban mobility challenges. Passenger demand, forecasted from AI models, serves as input parameters for a Mixed-Integer Nonlinear Programming (MINLP) optimization model that dynamically adjusts pod dispatch schedules and train lengths in response to demand variations. The results reveal a complex interplay of factors, including demand levels, headway bounds, train configurations, and fleet sizes, which collectively influence network performance and service quality. The proposed system demonstrates the importance of dynamic adjustments, where modularity mitigates capacity bottlenecks and improves operational efficiency. Additionally, the framework enhances energy efficiency and optimizes resource utilization through flexible and adaptive scheduling. This framework provides a foundation for a responsive and sustainable urban air mobility solution, supporting the shift from static planning to agile, data-driven operations.
Agentic workflows promise efficiency, but adoption hinges on whether people actually trust systems that act on their behalf. We present DoubleAgents, an agentic planning tool that embeds transparency and control through user intervention, value-reflecting policies, rich state visualizations, and uncertainty flagging for human coordination tasks. A built-in respondent simulation generates realistic scenarios, allowing users to rehearse, refine policies, and calibrate their reliance before live use. We evaluate DoubleAgents in a two-day lab study (n=10), two deployments (n=2), and a technical evaluation. Results show that participants initially hesitated to delegate but grew more reliant as they experienced transparency, control, and adaptive learning during simulated cases. Deployment results demonstrate DoubleAgents' real-world relevance and usefulness, showing that the effort required scaled appropriately with task complexity and contextual data. We contribute trust-by-design patterns and mechanisms for proactive AI -- consistency, controllability, and explainability -- along with simulation as a safe path to build and calibrate trust over time.
Autonomous robots must go from zero prior knowledge to safe control within seconds to operate in unstructured environments. Abrupt terrain changes, such as a sudden transition to ice, create dynamics shifts that can destabilize planners unless the model adapts in real-time. We present a method for online adaptation that combines function encoders with recursive least squares, treating the function encoder coefficients as latent states updated from streaming odometry. This yields constant-time coefficient estimation without gradient-based inner-loop updates, enabling adaptation from only a few seconds of data. We evaluate our approach on a Van der Pol system to highlight algorithmic behavior, in a Unity simulator for high-fidelity off-road navigation, and on a Clearpath Jackal robot, including on a challenging terrain at a local ice rink. Across these settings, our method improves model accuracy and downstream planning, reducing collisions compared to static and meta-learning baselines.
Digital Twin (DT) technology enables real-time monitoring and optimization of complex network infrastructures by creating accurate virtual replicas of physical systems. In millimeter-wave (mmWave) 5G/6G networks, the deployment of Integrated Access and Backhaul (IAB) nodes faces highly dynamic urban environments, necessitating intelligent DT-enabled optimization frameworks. Traditional IAB deployment optimization approaches struggle with the combinatorial complexity of jointly optimizing coverage, connectivity, and resilience, often leading to suboptimal solutions that are vulnerable to network disruptions. With this consideration, we propose a novel Graph Attention Network v2 (GATv2)-based reinforcement learning approach for resilient IAB deployment in urban mmWave networks. Specifically, we formulate the deployment problem as a Markov Decision Process (MDP) with explicit resilience constraints and employ edge-conditioned GATv2 to capture complex spatial dependencies between heterogeneous node types and dynamic connectivity patterns. The attention mechanism enables the model to focus on critical deployment locations to maximize coverage and ensure fault tolerance through redundant backhaul connections. To address the inherent vulnerability of mmWave links, we train the GATv2 policy using Proximal Policy Optimization (PPO) with a carefully designed balance between coverage, cost, and resilience. Comprehensive simulations across three urban scenarios demonstrate that our method achieves 98.5-98.7 percent coverage with 14.3-26.7 percent fewer nodes than baseline approaches, while maintaining 87.1 percent coverage retention under 30 percent link failures, representing 11.3-15.4 percent improvement in fault tolerance compared to state-of-the-art methods.
Network planning seeks to determine base station parameters that maximize coverage and capacity in cellular networks. However, achieving optimal planning remains challenging due to the diversity of deployment scenarios and the significant simulation-to-reality discrepancy. In this paper, we propose \emph{AutoPlan}, a new automatic network planning framework by leveraging digital radio twin (DRT) techniques. We derive the DRT by finetuning the parameters of building materials to reduce the sim-to-real discrepancy based on crowdsource real-world user data. Leveraging the DRT, we design a Bayesian optimization based algorithm to optimize the deployment parameters of base stations efficiently. Using the field measurement from Husker-Net, we extensively evaluate \emph{AutoPlan} under various deployment scenarios, in terms of both coverage and capacity. The evaluation results show that \emph{AutoPlan} flexibly adapts to different scenarios and achieves performance comparable to exhaustive search, while requiring less than 2\% of its computation time.
In a coherent reliability system composed of multiple components configured according to a specific structure function, the distribution of system time to failure, or system lifetime, is often of primary interest. Accurate estimation of system reliability is critical in a wide range of engineering and industrial applications, forming decisions in system design, maintenance planning, and risk assessment. The system lifetime distribution can be estimated directly using the observed system failure times. However, when component-level lifetime data is available, it can yield improved estimates of system reliability. In this work, we demonstrate that under nonparametric assumptions about the component time-to-failure distributions, traditional estimators such as the Product-Limit Estimator (PLE) can be further improved under specific loss functions. We propose a novel methodology that enhances the nonparametric system reliability estimation through a shrinkage transformation applied to component-level estimators. This shrinkage approach leads to improved efficiency in estimating system reliability.
Mitigation of the threat from airbursting asteroids requires an understanding of the potential risk they pose for the ground. How asteroids release their kinetic energy in the atmosphere is not well understood due to the rarity of significant impacts. Ordinary chondrites, in particular L chondrites, represent a frequent type of Earth-impacting asteroids. Here, we present the first comprehensive, space-to-lab characterization of an L chondrite impact. Small asteroid 2023 CX1 was detected in space and predicted to impact over Normandy, France, on 13 February 2023. Observations from multiple independent sensors and reduction techniques revealed an unusual but potentially high-risk fragmentation behavior. The nearly spherical 650 $\pm$ 160 kg (72 $\pm$ 6 cm diameter) asteroid catastrophically fragmented around 28 km altitude, releasing 98% of its total energy in a concentrated region of the atmosphere. The resulting shockwave was spherical, not cylindrical, and released more energy closer to the ground. This type of fragmentation increases the risk of significant damage at ground level. These results warrant consideration for a planetary defense strategy for cases where a >3-4 MPa dynamic pressure is expected, including planning for evacuation of areas beneath anticipated disruption locations.
This paper presents data-driven approaches for integrated assortment planning and inventory allocation that significantly improve fulfillment efficiency at JD.com, a leading E-commerce company. JD.com uses a two-level distribution network that includes regional distribution centers (RDCs) and front distribution centers (FDCs). Selecting products to stock at FDCs and then optimizing daily inventory allocation from RDCs to FDCs is critical to improving fulfillment efficiency, which is crucial for enhancing customer experiences. For assortment planning, we propose efficient algorithms to maximize the number of orders that can be fulfilled by FDCs (local fulfillment). For inventory allocation, we develop a novel end-to-end algorithm that integrates forecasting, optimization, and simulation to minimize lost sales and inventory transfer costs. Numerical experiments demonstrate that our methods outperform existing approaches, increasing local order fulfillment rates by 0.54% and our inventory allocation algorithm increases FDC demand satisfaction rates by 1.05%. Considering the high-volume operations of JD.com, with millions of weekly orders per region, these improvements yield substantial benefits beyond the company's established supply chain system. Implementation across JD.com's network has reduced costs, improved stock availability, and increased local order fulfillment rates for millions of orders annually.
Engineering models created in Model-Based Systems Engineering (MBSE) environments contain detailed information about system structure and behavior. However, they typically lack symbolic planning semantics such as preconditions, effects, and constraints related to resource availability and timing. This limits their ability to evaluate whether a given system variant can fulfill specific tasks and how efficiently it performs compared to alternatives. To address this gap, this paper presents a model-driven method that enables the specification and automated generation of symbolic planning artifacts within SysML-based engineering models. A dedicated SysML profile introduces reusable stereotypes for core planning constructs. These are integrated into existing model structures and processed by an algorithm that generates a valid domain file and a corresponding problem file in Planning Domain Definition Language (PDDL). In contrast to previous approaches that rely on manual transformations or external capability models, the method supports native integration and maintains consistency between engineering and planning artifacts. The applicability of the method is demonstrated through a case study from aircraft assembly. The example illustrates how existing engineering models are enriched with planning semantics and how the proposed workflow is applied to generate consistent planning artifacts from these models. The generated planning artifacts enable the validation of system variants through AI planning.
Cone-Beam Computed Tomography (CBCT) is a widely used 3D imaging technique in dentistry, providing volumetric information about the anatomical structures of jaws and teeth. Accurate segmentation of these anatomies is critical for clinical applications such as diagnosis and surgical planning, but remains time-consuming and challenging. In this paper, we present U-Mamba2, a new neural network architecture designed for multi-anatomy CBCT segmentation in the context of the ToothFairy3 challenge. U-Mamba2 integrates the Mamba2 state space models into the U-Net architecture, enforcing stronger structural constraints for higher efficiency without compromising performance. In addition, we integrate interactive click prompts with cross-attention blocks, pre-train U-Mamba2 using self-supervised learning, and incorporate dental domain knowledge into the model design to address key challenges of dental anatomy segmentation in CBCT. Extensive experiments, including independent tests, demonstrate that U-Mamba2 is both effective and efficient, securing top 3 places in both tasks of the Toothfairy3 challenge. In Task 1, U-Mamba2 achieved a mean Dice of 0.792, HD95 of 93.19 with the held-out test data, with an average inference time of XX (TBC during the ODIN workshop). In Task 2, U-Mamba2 achieved the mean Dice of 0.852 and HD95 of 7.39 with the held-out test data. The code is publicly available at https://github.com/zhiqin1998/UMamba2.
The fine-grained surface reconstruction of different organs from 3D medical imaging can provide advanced diagnostic support and improved surgical planning. However, the representation of the organs is often limited by the resolution, with a detailed higher resolution requiring more memory and computing footprint. Implicit representations of objects have been proposed to alleviate this problem in general computer vision by providing compact and differentiable functions to represent the 3D object shapes. However, architectural and data-related differences prevent the direct application of these methods to medical images. This work introduces ImplMORe, an end-to-end deep learning method using implicit surface representations for multi-organ reconstruction from 3D medical images. ImplMORe incorporates local features using a 3D CNN encoder and performs multi-scale interpolation to learn the features in the continuous domain using occupancy functions. We apply our method for single and multiple organ reconstructions using the totalsegmentator dataset. By leveraging the continuous nature of occupancy functions, our approach outperforms the discrete explicit representation based surface reconstruction approaches, providing fine-grained surface details of the organ at a resolution higher than the given input image. The source code will be made publicly available at: https://github.com/CAMMA-public/ImplMORe
We study the problem of generalizing an expert agent's behavior, provided through demonstrations, to new environments and/or additional constraints. Inverse Reinforcement Learning (IRL) offers a promising solution by seeking to recover the expert's underlying reward function, which, if used for planning in the new settings, would reproduce the desired behavior. However, IRL is inherently ill-posed: multiple reward functions, forming the so-called feasible set, can explain the same observed behavior. Since these rewards may induce different policies in the new setting, in the absence of additional information, a decision criterion is needed to select which policy to deploy. In this paper, we propose a novel, principled criterion that selects the "average" policy among those induced by the rewards in a certain bounded subset of the feasible set. Remarkably, we show that this policy can be obtained by planning with the reward centroid of that subset, for which we derive a closed-form expression. We then present a provably efficient algorithm for estimating this centroid using an offline dataset of expert demonstrations only. Finally, we conduct numerical simulations that illustrate the relationship between the expert's behavior and the behavior produced by our method.
Diffusion-based planners have gained significant recent attention for their robustness and performance in long-horizon tasks. However, most existing planners rely on a fixed, pre-specified horizon during both training and inference. This rigidity often produces length-mismatch (trajectories that are too short or too long) and brittle performance across instances with varying geometric or dynamical difficulty. In this paper, we introduce the Variable Horizon Diffuser (VHD) framework, which treats the horizon as a learned variable rather than a fixed hyperparameter. Given a start-goal pair, we first predict an instance-specific horizon using a learned Length Predictor model, which guides a Diffusion Planner to generate a trajectory of the desired length. Our design maintains compatibility with existing diffusion planners by controlling trajectory length through initial noise shaping and training on randomly cropped sub-trajectories, without requiring architectural changes. Empirically, VHD improves success rates and path efficiency in maze-navigation and robot-arm control benchmarks, showing greater robustness to horizon mismatch and unseen lengths, while keeping training simple and offline-only.
This study develops and evaluates a novel hybridWavelet SARIMA Transformer, WST framework to forecast using monthly rainfall across five meteorological subdivisions of Northeast India over the 1971 to 2023 period. The approach employs the Maximal Overlap Discrete Wavelet Transform, MODWT with four wavelet families such as, Haar, Daubechies, Symlet, Coiflet etc. to achieve shift invariant, multiresolution decomposition of the rainfall series. Linear and seasonal components are modeled using Seasonal ARIMA, SARIMA, while nonlinear components are modeled by a Transformer network, and forecasts are reconstructed via inverse MODWT. Comprehensive validation using an 80 is to 20 train test split and multiple performance indices such as, RMSE, MAE, SMAPE, Willmotts d, Skill Score, Percent Bias, Explained Variance, and Legates McCabes E1 demonstrates the superiority of the Haar-based hybrid model, WHST. Across all subdivisions, WHST consistently achieved lower forecast errors, stronger agreement with observed rainfall, and unbiased predictions compared with stand alone SARIMA, stand-alone Transformer, and two-stage wavelet hybrids. Residual adequacy was confirmed through the Ljung Box test, while Taylor diagrams provided an integrated assessment of correlation, variance fidelity, and RMSE, further reinforcing the robustness of the proposed approach. The results highlight the effectiveness of integrating multiresolution signal decomposition with complementary linear and deep learning models for hydroclimatic forecasting. Beyond rainfall, the proposed WST framework offers a scalable methodology for forecasting complex environmental time series, with direct implications for flood risk management, water resources planning, and climate adaptation strategies in data-sparse and climate-sensitive regions.
We propose an O(100)m Atom Interferometer (AI) experiment - AICE - to be installed against a wall of the PX46 access shaft to the LHC. This experiment would probe unexplored ranges of the possible couplings of bosonic ultralight dark matter (ULDM) to atomic constituents and undertake a pioneering search for gravitational waves (GWs) at frequencies intermediate between those to which existing and planned experiments are sensitive, among other fundamental physics studies. A conceptual feasibility study showed that this AI experiment could be isolated from the LHC by installing a shielding wall in the TX46 gallery, and surveyed issues related to the proximity of the LHC machine, finding no technical obstacles. A detailed technical implementation study has shown that the preparatory civil-engineering work, installation of bespoke radiation shielding, deployment of access-control systems and safety alarms, and installation of an elevator platform could be carried out during LS3, allowing installation and operation of the AICE detector to proceed during Run 4 without impacting HL-LHC operation. These studies have established that PX46 is a uniquely promising location for an AI experiment. We foresee that, if the CERN management encourages this Letter of Intent, a significant fraction of the Terrestrial Very Long Baseline Atom Interferometer (TVLBAI) Proto-Collaboration may wish to contribute to AICE.
This paper presents UniPilot, a compact hardware-software autonomy payload that can be integrated across diverse robot embodiments to enable autonomous operation in GPS-denied environments. The system integrates a multi-modal sensing suite including LiDAR, radar, vision, and inertial sensing for robust operation in conditions where uni-modal approaches may fail. UniPilot runs a complete autonomy software comprising multi-modal perception, exploration and inspection path planning, and learning-based navigation policies. The payload provides robust localization, mapping, planning, and safety and control capabilities in a single unit that can be deployed across a wide range of platforms. A large number of experiments are conducted across diverse environments and on a variety of robot platforms to validate the mapping, planning, and safe navigation capabilities enabled by the payload.
Autonomous stocking in retail environments, particularly supermarkets, presents challenges due to dynamic human interactions, constrained spaces, and diverse product geometries. This paper introduces an efficient end-to-end robotic system for autonomous shelf stocking and fronting, integrating commercially available hardware with a scalable algorithmic architecture. A major contribution of this work is the system integration of off-the-shelf hardware and ROS2-based perception, planning, and control into a single deployable platform for retail environments. Our solution leverages Behavior Trees (BTs) for task planning, fine-tuned vision models for object detection, and a two-step Model Predictive Control (MPC) framework for precise shelf navigation using ArUco markers. Laboratory experiments replicating realistic supermarket conditions demonstrate reliable performance, achieving over 98% success in pick-and-place operations across a total of more than 700 stocking events. However, our comparative benchmarks indicate that the performance and cost-effectiveness of current autonomous systems remain inferior to that of human workers, which we use to highlight key improvement areas and quantify the progress still required before widespread commercial deployment can realistically be achieved.