Current practices for designing cluster-randomized trials (cRCTs) typically rely on closed-form formulas for power calculations. For cRCTs using covariate-constrained randomization, the utility of conventional calculations might be limited, particularly when data is nested. We compared simulation-based planning of a nested cRCT using covariate-constrained randomization to conventional power calculations using OptiMAx-Chad as a case study. OptiMAx-Chad will examine the impact of embedding mass distribution of small-quantity lipid-based nutrient supplements within an expanded programme on immunization on first-dose measles-containing vaccine (MCV1) coverage among children aged 12-24 months in rural villages in Ngouri. Within the 12 health areas to be randomized, a random subset of villages will be selected for outcome collection. 1,000,000 assignments of health areas with different possible village selections were generated using covariate-constrained randomization to balance baseline village characteristics. The empirically estimated intracluster correlation coefficient (ICC) and the World Health Organization (WHO) recommended values of 1/3 and 1/6 were considered. The desired operating characteristics were 80% power at 0.05 one-sided type I error rate. Using conventional calculations target power for a realistic treatment effect could not be achieved with the WHO recommended values. Conventional calculations also showed a plateau in power after a certain cluster size. Our simulations matched the design of OptiMAx-Chad with covariate adjustment and random selection, and showed that power did not plateau. Instead, power increased with increasing cluster size. Planning complex cRCTs with covariate constrained randomization and a multi-nested data structure with conventional closed-form formulas can be misleading. Simulations can improve the planning of cRCTs.
As urbanization and climate change progress, urban heat island effects are becoming more frequent and severe. To formulate effective mitigation plans, cities require detailed air temperature data, yet conventional machine learning models with limited data often produce inaccurate predictions, particularly in underserved areas. Geospatial foundation models trained on global unstructured data offer a promising alternative by demonstrating strong generalization and requiring only minimal fine-tuning. In this study, an empirical ground truth of urban heat patterns is established by quantifying cooling effects from green spaces and benchmarking them against model predictions to evaluate the model's accuracy. The foundation model is subsequently fine-tuned to predict land surface temperatures under future climate scenarios, and its practical value is demonstrated through a simulated inpainting that highlights its role for mitigation support. The results indicate that foundation models offer a powerful way for evaluating urban heat island mitigation strategies in data-scarce regions to support more climate-resilient cities.
Missions such as the Ingenuity helicopter have shown the advantages of using novel locomotion modes to increase the scientific return of planetary exploration missions. Legged robots can further expand the reach and capability of future planetary missions by traversing more difficult terrain than wheeled rovers, such as jumping over cracks on the ground or traversing rugged terrain with boulders. To develop and test algorithms for using quadruped robots, the AAPLE project was carried out at DFKI. As part of the project, we conducted a series of field experiments on the Volcano on the Aeolian island of Vulcano, an active stratovolcano near Sicily, Italy. The experiments focused on validating newly developed state-of-the-art adaptive optimal control algorithms for quadrupedal locomotion in a high-fidelity analog environment for Lunar and Martian surfaces. This paper presents the technical approach, test plan, software architecture, field deployment strategy, and evaluation results from the Vulcano campaign.
Accurate annual average daily traffic (AADT) data are vital for transport planning and infrastructure management. However, automatic traffic detectors across national road networks often provide incomplete coverage, leading to underrepresentation of minor roads. While recent machine learning advances have improved AADT estimation at unmeasured locations, most models produce only point predictions and overlook estimation uncertainty. This study addresses that gap by introducing an interval prediction approach that explicitly quantifies predictive uncertainty. We integrate a Quantile Random Forest model with Principal Component Analysis to generate AADT prediction intervals, providing plausible traffic ranges bounded by estimated minima and maxima. Using data from over 2,000 minor roads in England and Wales, and evaluated with specialized interval metrics, the proposed method achieves an interval coverage probability of 88.22%, a normalized average width of 0.23, and a Winkler Score of 7,468.47. By combining machine learning with spatial and high-dimensional analysis, this framework enhances both the accuracy and interpretability of AADT estimation, supporting more robust and informed transport planning.
There is a need for experimental data in conditions representative injection in rocket engines to validate or initiate droplet formation models used in numerical simulations. A new cryogenic vessel was built upon the MASCOTTE test bench to study the atomization of a single oxygen liquid jet, under non-reactive conditions, with simultaneous optical diagnostics. A test plan was built to explore the fiber-type regime occurring in liquid rocket injection systems, with a fixed Reynolds number and a large range of Weber number and momentum flux ratio, compared to existing studies. High-speed images are used to describe qualitatively the fiber-type regime and to visualize were droplets are present, in order to prepare the drop-size measurements. A Phase Doppler Interferometer is used to measure the size and velocity of droplets produced by atomization of a liquid oxygen jet by a co-flowing gas. Droplet size and velocity measurements were performed with a PDI close to the nozzle exit in order to provide data on droplets produced by the primary atomization process, which can be useful for numerical simulations initialisation. The radial evolutions of the axial velocity and of the drop size distribution show similar trends as observed in the literature. The axial velocity is investigated for different operating conditions with helium or nitrogen as atomizing gas, showing an increase on the side of the spray. The radial evolution of the droplet size shows a translation of the drop size distribution on the edge of the spray towards the smaller sizes, indicating that the biggest liquid elements stay close to the LOX jet.
This search introduces the Multimodal Socialized Learning Framework (M-S2L), designed to foster emergent social intelligence in AI agents by integrating Multimodal Large Language Models (M-LLMs) with social learning mechanisms. The framework equips agents with multimodal perception (vision and text) and structured action capabilities, enabling physical manipulation and grounded multimodal communication (e.g., text with visual pointers). M-S2L combines direct reinforcement learning with two novel social learning pathways: multimodal observational learning and communication-driven learning from feedback, augmented by an episodic memory system for long-term social context. We evaluate M-S2L in a Collaborative Assembly Environment (CAE), where agent teams must construct complex devices from ambiguous blueprints under informational asymmetry. Across tasks of increasing complexity, M-S2L agents consistently outperform Text-Only and No-Social-Learning baselines in Task Completion Rate and Time to Completion, particularly in dynamic problem-solving scenarios. Ablation studies confirm the necessity of both multimodality and socialized learning. Our analysis reveals the emergence of efficient communication protocols integrating visual pointers with concise text, alongside rapid role specialization leading to stable labor division. Qualitative case studies demonstrate agents' abilities for shared awareness, dynamic re-planning, and adaptive problem-solving, suggesting a nascent form of machine social cognition. These findings indicate that integrating multimodal perception with explicit social learning is critical for developing human-like collaborative intelligence in multi-agent systems.
Reliable navigation in safety-critical environments requires both accurate hazard perception and principled uncertainty handling to strengthen downstream safety handling. Despite the effectiveness of existing approaches, they assume perfect hazard detection capabilities, while uncertainty-aware perception approaches lack finite-sample guarantees. We present COPPOL, a conformal-driven perception-to-policy learning approach that integrates distribution-free, finite-sample safety guarantees into semantic segmentation, yielding calibrated hazard maps with rigorous bounds for missed detections. These maps induce risk-aware cost fields for downstream RL planning. Across two satellite-derived benchmarks, COPPOL increases hazard coverage (up to 6x) compared to comparative baselines, achieving near-complete detection of unsafe regions while reducing hazardous violations during navigation (up to approx 50%). More importantly, our approach remains robust to distributional shift, preserving both safety and efficiency.
Motivated by the application of using model predictive control (MPC) for motion planning of autonomous mobile robots, a form of output tracking MPC for non-holonomic systems and with non-convex constraints is studied. Although the advantages of using MPC for motion planning have been demonstrated in several papers, in most of the available fundamental literature on output tracking MPC it is assumed, often implicitly, that the model is holonomic and generally the state or output constraints must be convex. Thus, in application-oriented publications, empirical results dominate and the topic of proving completeness, in particular under which assumptions the target is always reached, has received comparatively little attention. To address this gap, we present a novel MPC formulation that guarantees convergence to the desired target under realistic assumptions, which can be verified in relevant real-world scenarios.
Integrating visual-language instructions into visuomotor policies is gaining momentum in robot learning for enhancing open-world generalization. Despite promising advances, existing approaches face two challenges: limited language steerability when no generated reasoning is used as a condition, or significant inference latency when reasoning is incorporated.In this work, we introduce MoTVLA, a mixture-of-transformers (MoT)-based vision-language-action (VLA) model that integrates fast-slow unified reasoning with behavior policy learning. MoTVLA preserves the general intelligence of pre-trained VLMs (serving as the generalist) for tasks such as perception, scene understanding, and semantic planning, while incorporating a domain expert, a second transformer that shares knowledge with the pretrained VLM, to generate domain-specific fast reasoning (e.g., robot motion decomposition), thereby improving policy execution efficiency. By conditioning the action expert on decomposed motion instructions, MoTVLA can learn diverse behaviors and substantially improve language steerability. Extensive evaluations across natural language processing benchmarks, robotic simulation environments, and real-world experiments confirm the superiority of MoTVLA in both fast-slow reasoning and manipulation task performance.
Background: Voxel-based analysis (VBA) is an analytic approach to evaluate correlations between local dose and the development of different toxicities. DVHs are used for toxicity prediction as well. Compared with DVH, no contours are required for VBA technique and results tell specific voxels that may be related to the toxicity instead of the whole contoured area. The VBA has been used on different cancer sites and for different toxicities. Most of these studies included patients treated with photon, all published studies were based on planned dose and VBA tools used were developed in house. In our study, patient cohort were treated with proton, our VBA tool was developed based on RayStation and doses fed to the VBA tool were delivered doses with constant and two variable RBE models.
We propose two novel interaction techniques for visualization-assisted exploration of urban data: Layer Toggling and Visibility-Preserving Lenses. Layer Toggling mitigates visual overload by organizing information into separate layers while enabling comparisons through controlled overlays. This technique supports focused analysis without losing spatial context and allows users to switch layers using a dedicated button. Visibility-Preserving Lenses adapt their size and transparency dynamically, enabling detailed inspection of dense spatial regions and temporal attributes. These techniques facilitate urban data exploration and improve prediction. Understanding complex phenomena related to crime, mobility, and residents' behavior is crucial for informed urban planning. Yet navigating such data often causes cognitive overload and visual clutter due to overlapping layers. We validate our visualization tool through a user study measuring performance, cognitive load, and interaction efficiency. Using real-world data from Sao Paulo, we demonstrate how our approach enhances exploratory and analytical tasks and provides guidelines for future interactive systems.
We describe the design and commissioning tests for the DSA-110 Not-So-Fast
Radio Burst (NSFRB) search pipeline, a 1.4 GHz image-plane single-pulse search
sensitive to 134 ms-160.8 s radio bursts. Extending the pulse width range of
the Fast Radio Burst (FRB) search by 3 orders of magnitude, the NSFRB search is
sensitive to the recently-discovered Galactic Long Period Radio Transients
(LPRTs). The NSFRB search operates in real-time, utilizing a custom
GPU-accelerated search code, \texttt{cerberus}, implemented in Python with JAX.
We summarize successful commissioning sensitivity tests with continuum sources
and pulsar B0329+54, estimating the $6\sigma$ flux (fluence) threshold to be
~290 mJy (~40 Jy ms). Future tests of recovery of longer timescale transients,
e.g. CHIME J1634+44, are planned to supplement injection testing and B0329+54
observations. An offline DSA-110 NSFRB Galactic Plane Survey was conducted to
search for LPRTs, covering $-3.5^\circ
Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has been limited by fragmented evaluation: most existing benchmarks adopt open-loop protocols that emphasize visual quality in isolation, leaving the core issue of embodied utility unresolved, i.e., do WMs actually help agents succeed at embodied tasks? To address this gap, we introduce World-in-World, the first open platform that benchmarks WMs in a closed-loop world that mirrors real agent-environment interactions. World-in-World provides a unified online planning strategy and a standardized action API, enabling heterogeneous WMs for decision making. We curate four closed-loop environments that rigorously evaluate diverse WMs, prioritize task success as the primary metric, and move beyond the common focus on visual quality; we also present the first data scaling law for world models in embodied settings. Our study uncovers three surprises: (1) visual quality alone does not guarantee task success, controllability matters more; (2) scaling post-training with action-observation data is more effective than upgrading the pretrained video generators; and (3) allocating more inference-time compute allows WMs to substantially improve closed-loop performance.
A central challenge in large language model inference is the trade-off between generation speed and output quality. Autoregressive models produce high-quality text but generate tokens sequentially. Diffusion models can generate tokens in parallel but often need many iterations to match the same quality. We propose planned diffusion, a hybrid method that combines the strengths of both paradigms. Planned diffusion works in two stages: first, the model creates a short autoregressive plan that breaks the output into smaller, independent spans. Second, the model generates these spans simultaneously using diffusion. This approach expands the speed-quality Pareto frontier and provides a practical path to faster, high-quality text generation. On AlpacaEval, a suite of 805 instruction-following prompts, planned diffusion achieves Pareto-optimal trade-off between quality and latency, achieving 1.27x to 1.81x speedup over autoregressive generation with only 0.87\% to 5.4\% drop in win rate, respectively. Our sensitivity analysis shows that the planning mechanism of planned diffusion is minimal and reliable, and simple runtime knobs exist to provide flexible control of the quality-latency trade-off.
Developing autonomous vehicles (AVs) requires not only safety and efficiency, but also realistic, human-like behaviors that are socially aware and predictable. Achieving this requires sim agent policies that are human-like, fast, and scalable in multi-agent settings. Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data, producing realistic policies. However, these models are computationally expensive, slow during inference, and struggle to adapt in reactive, closed-loop scenarios. In contrast, self-play reinforcement learning (RL) scales efficiently and naturally captures multi-agent interactions, but it often relies on heuristics and reward shaping, and the resulting policies can diverge from human norms. We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a centralized reference policy to guide decentralized self-play. The reference model provides likelihood rewards and KL divergence, anchoring policies to the human driving distribution while preserving RL scalability. Evaluated on the Waymo Sim Agents Challenge, our method achieves competitive performance with imitation-learned policies while being up to 10x faster at inference and 50x smaller in parameter size than large generative models. In addition, we demonstrate in closed-loop ego planning evaluation tasks that our sim agents can effectively measure planner quality with fast and scalable traffic simulation, establishing a new paradigm for testing autonomous driving policies.
Deep subspace clustering models are vital for applications such as snowmelt detection, sea ice tracking, crop health monitoring, infectious disease modeling, network load prediction, and land-use planning, where multivariate spatiotemporal data exhibit complex temporal dependencies and reside on multiple nonlinear manifolds beyond the capability of traditional clustering methods. These models project data into a latent space where samples lie in linear subspaces and exploit the self-expressiveness property to uncover intrinsic relationships. Despite their success, existing methods face major limitations: they use shallow autoencoders that ignore clustering errors, emphasize global features while neglecting local structure, fail to model long-range dependencies and positional information, and are rarely applied to 4D spatiotemporal data. To address these issues, we propose A-DATSC (Attention-Guided Deep Adversarial Temporal Subspace Clustering), a model combining a deep subspace clustering generator and a quality-verifying discriminator. The generator, inspired by U-Net, preserves spatial and temporal integrity through stacked TimeDistributed ConvLSTM2D layers, reducing parameters and enhancing generalization. A graph attention transformer based self-expressive network captures local spatial relationships, global dependencies, and both short- and long-range correlations. Experiments on three real-world multivariate spatiotemporal datasets show that A-DATSC achieves substantially superior clustering performance compared to state-of-the-art deep subspace clustering models.
Building robots that can perceive, reason, and act in dynamic, unstructured environments remains a core challenge. Recent embodied systems often adopt a dual-system paradigm, where System 2 handles high-level reasoning while System 1 executes low-level control. In this work, we refer to System 2 as the embodied brain, emphasizing its role as the cognitive core for reasoning and decision-making in manipulation tasks. Given this role, systematic evaluation of the embodied brain is essential. Yet existing benchmarks emphasize execution success, or when targeting high-level reasoning, suffer from incomplete dimensions and limited task realism, offering only a partial picture of cognitive capability. To bridge this gap, we introduce RoboBench, a benchmark that systematically evaluates multimodal large language models (MLLMs) as embodied brains. Motivated by the critical roles across the full manipulation pipeline, RoboBench defines five dimensions-instruction comprehension, perception reasoning, generalized planning, affordance prediction, and failure analysis-spanning 14 capabilities, 25 tasks, and 6092 QA pairs. To ensure realism, we curate datasets across diverse embodiments, attribute-rich objects, and multi-view scenes, drawing from large-scale real robotic data. For planning, RoboBench introduces an evaluation framework, MLLM-as-world-simulator. It evaluate embodied feasibility by simulating whether predicted plans can achieve critical object-state changes. Experiments on 14 MLLMs reveal fundamental limitations: difficulties with implicit instruction comprehension, spatiotemporal reasoning, cross-scenario planning, fine-grained affordance understanding, and execution failure diagnosis. RoboBench provides a comprehensive scaffold to quantify high-level cognition, and guide the development of next-generation embodied MLLMs. The project page is in https://robo-bench.github.io.
As information grows exponentially, enterprises face increasing pressure to transform unstructured data into coherent, actionable insights. While autonomous agents show promise, they often struggle with domain-specific nuances, intent alignment, and enterprise integration. We present Enterprise Deep Research (EDR), a multi-agent system that integrates (1) a Master Planning Agent for adaptive query decomposition, (2) four specialized search agents (General, Academic, GitHub, LinkedIn), (3) an extensible MCP-based tool ecosystem supporting NL2SQL, file analysis, and enterprise workflows, (4) a Visualization Agent for data-driven insights, and (5) a reflection mechanism that detects knowledge gaps and updates research direction with optional human-in-the-loop steering guidance. These components enable automated report generation, real-time streaming, and seamless enterprise deployment, as validated on internal datasets. On open-ended benchmarks including DeepResearch Bench and DeepConsult, EDR outperforms state-of-the-art agentic systems without any human steering. We release the EDR framework and benchmark trajectories to advance research on multi-agent reasoning applications. Code at https://github.com/SalesforceAIResearch/enterprise-deep-research and Dataset at https://huggingface.co/datasets/Salesforce/EDR-200
The current Timing System at Fermilab has been around for 40 years and currently relies on 7 CAMAC crates and over 100 CAMAC cards to produce the Tevatron Clock (TCLK). Thanks to the ingenuity of those before us, this has allowed Fermilab the flexibility to change the timing and Events for its accelerator as beamlines and projects have changed over the years. With the advent of the Proton Improvement Plan-II (PIP-II), the Timing System at Fermilab is being reimagined into a single chassis with even greater flexibility and functionality for decades to come while tackling the ever-challenging task of maintaining backwards compatibility.
Novel Markov Chain Monte Carlo (MCMC) methods have enabled the generation of large ensembles of redistricting plans through graph partitioning. However, existing algorithms such as Reversible Recombination (RevReCom) and Metropolized Forest Recombination (MFR) are constrained to sampling from distributions related to spanning trees. We introduce the marked edge walk (MEW), a novel MCMC algorithm for sampling from the space of graph partitions under a tunable distribution. The walk operates on the space of spanning trees with marked edges, allowing for calculable transition probabilities for use in the Metropolis-Hastings algorithm. Empirical results on real-world dual graphs show convergence under target distributions unrelated to spanning trees. For this reason, MEW represents an advancement in flexible ensemble generation.
This paper presents a formal framework for sequencing instructions in AI agents, inspired by the Indian philosophical system of Mimamsa. The framework formalizes sequencing mechanisms through action object pairs in three distinct ways: direct assertion (Srutikrama) for temporal precedence, purpose driven sequencing (Arthakrama) for functional dependencies, and iterative procedures (Pravrittikrama) for distinguishing between parallel and sequential execution in repetitive tasks. It introduces the syntax and semantics of an action object imperative logic, extending the MIRA formalism (Srinivasan and Parthasarathi, 2021) with explicit deduction rules for sequencing. The correctness of instruction sequencing is established through a validated theorem, which is based on object dependencies across successive instructions. This is further supported by proofs of soundness and completeness. This formal verification enables reliable instruction sequencing, impacting AI applications across areas like task planning and robotics by addressing temporal reasoning and dependency modeling.
Clinicians need ranking systems that work in real time and still justify their choices. Motivated by the need for a low-latency, decoder-based reranker, we present OG-Rank, a single-decoder approach that pairs a pooled first-token scoring signal with an uncertainty-gated explanation step. The model scores all candidates in one pass and generates a brief, structured rationale only when the list is genuinely ambiguous, keeping latency predictable. Trained with a curriculum that concentrates effort on hard cases, OG-Rank delivers strong effectiveness on encounter-scoped order selection (fast path: Recall@1~0.45, nDCG@20~0.625) and improves further when the gate activates (Recall@1~0.56, nDCG@20~0.699 at a 45\% gate rate), while compact backbones show similar gains under the same policy. Encoder baselines trail in both effectiveness and flexibility. The result is a practical recipe: rank fast by default and explain when it helps, a pattern that applies broadly to decision tasks where selective generation buys accuracy at acceptable cost. The single-policy design simplifies deployment and budget planning, and the curriculum principle (spend more on the hard cases, less on the easy ones) readily transfers beyond clinical order selection.
We formalise decompression planning as an optimal control problem with gas feasibility windows (ppO$_2$, END), affine ceilings, and convex penalties in normalised oversaturation. We prove existence, a monotone no re-descent structure and bang-bang ascents under a mild monotonicity assumption on inert fraction, and establish dwell time KKT conditions. We give pseudo-polynomial DP and label-setting algorithms with a priori error bounds, derive Lipschitz regularity of the online value function, and discuss multi-species extensions. The efficient frontier is continuous and generally nonconvex. We provide the first formal existence and bang-bang structure proof under mixed gas feasibility windows.
Swarm trajectory optimization problems are a well-recognized class of multi-agent optimal control problems with strong nonlinearity. However, the heuristic nature of needing to set the final time for agents beforehand and the time-consuming limitation of the significant number of iterations prohibit the application of existing methods to large-scale swarm of Unmanned Aerial Vehicles (UAVs) in practice. In this paper, we propose a spatial-temporal trajectory optimization framework that accomplishes multi-UAV consensus based on the Alternating Direction Multiplier Method (ADMM) and uses Differential Dynamic Programming (DDP) for fast local planning of individual UAVs. The introduced framework is a two-level architecture that employs Parameterized DDP (PDDP) as the trajectory optimizer for each UAV, and ADMM to satisfy the local constraints and accomplish the spatial-temporal parameter consensus among all UAVs. This results in a fully distributed algorithm called Distributed Parameterized DDP (D-PDDP). In addition, an adaptive tuning criterion based on the spectral gradient method for the penalty parameter is proposed to reduce the number of algorithmic iterations. Several simulation examples are presented to verify the effectiveness of the proposed algorithm.
Cardiac arrhythmias are a major cause of morbidity and mortality increasing the risk of stroke, heart failure, and sudden cardiac death. Imageless electrocardiographic imaging (ECGI) provides a non invasive alternative to electrical mapping from body surface potentials, but conventional ECGI is confined to epicardial reconstructions and can miss arrhythmias originating in deeper myocardium. We address this by reconstructing three dimensional cardiac activity with a volumetric formulation that solves an inverse source problem via Green's functions, enabling full volume activation mapping and improved localization in anatomically complex regions. We evaluate the approach on simulated premature ventricular beats and on four challenging patient cases, a right ventricular outflow tract premature ventricular contraction, a left bundle branch block, a ventricular tachycardia, and Wolff Parkinson White, and additionally assess performance on an open source myocardial infarction dataset. Results show that volumetric ECGI recovers 3D activation and sharpens arrhythmia origin localization, achieving a 59.3% reduction in geodesic error between estimated and simulated origins relative to surface only methods; in patient cases, activation patterns align with clinical diagnoses. Overall, imageless volumetric ECGI offers accessible, non invasive 3D activation mapping that overcomes a core limitation of surface restricted techniques and may improve preprocedural planning, ablation target guidance, and selection or optimization of cardiac resynchronization therapy.
Safe and efficient robotic navigation among humans is essential for integrating robots into everyday environments. Most existing approaches focus on simplified 2D crowd navigation and fail to account for the full complexity of human body dynamics beyond root motion. We present HumanMPC, a Model Predictive Control (MPC) framework for 3D Micro Air Vehicle (MAV) navigation among humans that combines theoretical safety guarantees with data-driven models for realistic human motion forecasting. Our approach introduces a novel twist to reachability-based safety formulation that constrains only the initial control input for safety while modeling its effects over the entire planning horizon, enabling safe yet efficient navigation. We validate HumanMPC in both simulated experiments using real human trajectories and in the real-world, demonstrating its effectiveness across tasks ranging from goal-directed navigation to visual servoing for human tracking. While we apply our method to MAVs in this work, it is generic and can be adapted by other platforms. Our results show that the method ensures safety without excessive conservatism and outperforms baseline approaches in both efficiency and reliability.
Semantic occupancy has emerged as a powerful representation in world models for its ability to capture rich spatial semantics. However, most existing occupancy world models rely on static and fixed embeddings or grids, which inherently limit the flexibility of perception. Moreover, their ``in-place classification" over grids exhibits a potential misalignment with the dynamic and continuous nature of real scenarios.In this paper, we propose SparseWorld, a novel 4D occupancy world model that is flexible, adaptive, and efficient, powered by sparse and dynamic queries. We propose a Range-Adaptive Perception module, in which learnable queries are modulated by the ego vehicle states and enriched with temporal-spatial associations to enable extended-range perception. To effectively capture the dynamics of the scene, we design a State-Conditioned Forecasting module, which replaces classification-based forecasting with regression-guided formulation, precisely aligning the dynamic queries with the continuity of the 4D environment. In addition, We specifically devise a Temporal-Aware Self-Scheduling training strategy to enable smooth and efficient training. Extensive experiments demonstrate that SparseWorld achieves state-of-the-art performance across perception, forecasting, and planning tasks. Comprehensive visualizations and ablation studies further validate the advantages of SparseWorld in terms of flexibility, adaptability, and efficiency. The code is available at https://github.com/MSunDYY/SparseWorld.
We develop an active inference route-planning method for the autonomous control of intelligent agents. The aim is to reconnoiter a geographical area to maintain a common operational picture. To achieve this, we construct an evidence map that reflects our current understanding of the situation, incorporating both positive and "negative" sensor observations of possible target objects collected over time, and diffusing the evidence across the map as time progresses. The generative model of active inference uses Dempster-Shafer theory and a Gaussian sensor model, which provides input to the agent. The generative process employs a Bayesian approach to update a posterior probability distribution. We calculate the variational free energy for all positions within the area by assessing the divergence between a pignistic probability distribution of the evidence map and a posterior probability distribution of a target object based on the observations, including the level of surprise associated with receiving new observations. Using the free energy, we direct the agents' movements in a simulation by taking an incremental step toward a position that minimizes the free energy. This approach addresses the challenge of exploration and exploitation, allowing agents to balance searching extensive areas of the geographical map while tracking identified target objects.
Autonomous agents rely on automated planning algorithms to achieve their objectives. Simulation-based planning offers a significant advantage over declarative models in modelling complex environments. However, relying solely on a planner that produces a single plan may not be practical, as the generated plans may not always satisfy the agent's preferences. To address this limitation, we introduce $\texttt{FBI}_\texttt{LTL}$, a diverse planner explicitly designed for simulation-based planning problems. $\texttt{FBI}_\texttt{LTL}$ utilises Linear Temporal Logic (LTL) to define semantic diversity criteria, enabling agents to specify what constitutes meaningfully different plans. By integrating these LTL-based diversity models directly into the search process, $\texttt{FBI}_\texttt{LTL}$ ensures the generation of semantically diverse plans, addressing a critical limitation of existing diverse planning approaches that may produce syntactically different but semantically identical solutions. Extensive evaluations on various benchmarks consistently demonstrate that $\texttt{FBI}_\texttt{LTL}$ generates more diverse plans compared to a baseline approach. This work establishes the feasibility of semantically-guided diverse planning in simulation-based environments, paving the way for innovative approaches in realistic, non-symbolic domains where traditional model-based approaches fail.
This work investigates several aspects related to quantitative stability in optimal transport, as well as uniqueness of the dual transport problem. Our main contributions are as follows. Chapter 1: Observations regarding the quantitative stability of optimal transport plans with respect to Wasserstein distance on the product space. Chapter 2: Extention of strong convexity inequalities for the Kantorovich functional to a larger class of source measures, using glueing arguments recently used for the quantitative stability of optimal transport maps. Chapters 3/4: A qualitative description of the behaviour of the fully discrete transport problem under perturbation of the support positions, as well as quantitative stability under uniqueness assumptions. Chapter 5: Extention of known uniqueness criteria for the dual transport problem. We show that when one marginal measure has Lipschitz-path connected support and the other has bounded support, the values of dual optimisers are unique up to a constant for a large family of costs, including $p$-costs for all $p>1$.