To meet the increasing demand of deep learning (DL) models, AI chips are employing both off-chip memory (e.g., HBM) and high-bandwidth low-latency interconnect for direct inter-core data exchange. However, it is not easy to explore the efficiency of these inter-core connected AI (ICCA) chips, due to a fundamental tussle among compute (per-core execution), communication (inter-core data exchange), and I/O (off-chip data access). In this paper, we develop Elk, a DL compiler framework to maximize the efficiency of ICCA chips by jointly trading off all the three performance factors discussed above. Elk structures these performance factors into configurable parameters and forms a global trade-off space in the DL compiler. To systematically explore this space and maximize overall efficiency, Elk employs a new inductive operator scheduling policy and a cost-aware on-chip memory allocation algorithm. It generates globally optimized execution plans that best overlap off-chip data loading and on-chip execution. To examine the efficiency of Elk, we build a full-fledged emulator based on a real ICCA chip IPU-POD4, and an ICCA chip simulator for sensitivity analysis with different interconnect network topologies. Elk achieves 94% of the ideal roofline performance of ICCA chips on average, showing the benefits of supporting large DL models on ICCA chips. We also show Elk's capability of enabling architecture design space exploration for new ICCA chip development.
This paper introduces a novel approach for jointly solving the periodic Train Timetabling Problem (TTP), train routing, and Vehicle Circulation Problem (VCP) through a unified optimization model. While these planning stages are traditionally addressed sequentially, their interdependencies often lead to suboptimal vehicle usage. We propose the VCR-PESP, an integrated formulation that minimizes fleet size while ensuring feasible and infrastructure-compliant periodic timetables. We present the first Satisfiability Modulo Theories (SMT)-based method for the VCR-PESP to solve the resulting large-scale instances. Unlike the Boolean Satisfiability Problem (SAT), which requires time discretisation, SMT supports continuous time via difference constraints, eliminating the trade-off between temporal precision and encoding size. Our approach avoids rounding artifacts and scales effectively, outperforming both SAT and Mixed Integer Program (MIP) models across non-trivial instances. Using real-world data from the Swiss narrow-gauge operator RhB, we conduct extensive experiments to assess the impact of time discretisation, vehicle circulation strategies, route flexibility, and planning integration. We show that discrete models inflate vehicle requirements and that fully integrated solutions substantially reduce fleet needs compared to sequential approaches. Our framework consistently delivers high-resolution solutions with tractable runtimes, even in large and complex networks. By combining modeling accuracy with scalable solver technology, this work establishes SMT as a powerful tool for integrated railway planning. It demonstrates how relaxing discretisation and solving across planning layers enables more efficient and implementable timetables.
Accurate characterization of vascular geometry is essential for cardiovascular diagnosis and treatment planning. Traditional statistical shape modeling (SSM) methods rely on linear assumptions, limiting their expressivity and scalability to complex topologies such as multi-branch vascular structures. We introduce HUG-VAS, a Hierarchical NURBS Generative model for Vascular geometry Synthesis, which integrates NURBS surface parameterization with diffusion-based generative modeling to synthesize realistic, fine-grained aortic geometries. Trained with 21 patient-specific samples, HUG-VAS generates anatomically faithful aortas with supra-aortic branches, yielding biomarker distributions that closely match those of the original dataset. HUG-VAS adopts a hierarchical architecture comprising a denoising diffusion model that generates centerlines and a guided diffusion model that synthesizes radial profiles conditioned on those centerlines, thereby capturing two layers of anatomical variability. Critically, the framework supports zero-shot conditional generation from image-derived priors, enabling practical applications such as interactive semi-automatic segmentation, robust reconstruction under degraded imaging conditions, and implantable device optimization. To our knowledge, HUG-VAS is the first SSM framework to bridge image-derived priors with generative shape modeling via a unified integration of NURBS parameterization and hierarchical diffusion processes.
We propose a multi-robot control paradigm to solve point-to-point navigation tasks for a team of holonomic robots with access to the full environment information. The framework invokes two processes asynchronously at high frequency: (i) a centralized, discrete, and full-horizon planner for computing collision- and deadlock-free paths rapidly, leveraging recent advances in multi-agent pathfinding (MAPF), and (ii) dynamics-aware, robot-wise optimal trajectory controllers that ensure all robots independently follow their assigned paths reliably. This hierarchical shift in planning representation from (i) discrete and coupled to (ii) continuous and decoupled domains enables the framework to maintain long-term scalable motion synthesis. As an instantiation of this idea, we present LF, which combines a fast state-of-the-art MAPF solver (LaCAM), and a robust feedback control stack (Freyja) for executing agile robot maneuvers. LF provides a robust and versatile mechanism for lifelong multi-robot navigation even under asynchronous and partial goal updates, and adapts to dynamic workspaces simply by quick replanning. We present various multirotor and ground robot demonstrations, including the deployment of 15 real multirotors with random, consecutive target updates while a person walks through the operational workspace.
The RoboCup Logistics League is a RoboCup competition in a smart factory scenario that has focused on task planning, job scheduling, and multi-agent coordination. The focus on production logistics allowed teams to develop highly competitive strategies, but also meant that some recent developments in the context of smart manufacturing are not reflected in the competition, weakening its relevance over the years. In this paper, we describe the vision for the RoboCup Smart Manufacturing League, a new competition designed as a larger smart manufacturing scenario, reflecting all the major aspects of a modern factory. It will consist of several tracks that are initially independent but gradually combined into one smart manufacturing scenario. The new tracks will cover industrial robotics challenges such as assembly, human-robot collaboration, and humanoid robotics, but also retain a focus on production logistics. We expect the reenvisioned competition to be more attractive to newcomers and well-tried teams, while also shifting the focus to current and future challenges of industrial robotics.
SNOLAB hosts a biannual Future Projects Workshop (FPW) with the goal of encouraging future project stakeholders to present ideas, concepts, and needs for experiments or programs that could one day be hosted at SNOLAB. The 2025 FPW was held in the larger context of a 15-year planning exercise requested by the Canada Foundation for Innovation. This report collects input from the community, including both contributions to the workshop and contributions that could not be scheduled in the workshop but nonetheless are important to the community.
This study develops a capacity expansion model for a fully decarbonized European electricity system using an Adaptive Robust Optimization (ARO) framework. The model endogenously identifies the worst regional Dunkelflaute events, prolonged periods of low wind and solar availability, and incorporates multiple extreme weather realizations within a single optimization run. Results show that system costs rise nonlinearly with the geographic extent of these events: a single worst-case regional disruption increases costs by 9%, but broader disruptions across multiple regions lead to much sharper increases, up to 51%. As Dunkelflaute conditions extend across most of Europe, additional cost impacts level off, with a maximum increase of 71%. The optimal technology mix evolves with the severity of weather stress: while renewables, batteries, and interregional transmission are sufficient to manage localized events, large-scale disruptions require long-term hydrogen storage and load shedding to maintain system resilience. Central European regions, especially Germany and France, emerge as systemic bottlenecks, while peripheral regions bear the cost of compensatory overbuilding. These findings underscore the need for a coordinated European policy strategy that goes beyond national planning to support cross-border infrastructure investment, scale up flexible technologies such as long-duration storage, and promote a geographically balanced deployment of renewables to mitigate systemic risks associated with Dunkelflaute events.
Robotic task execution faces challenges due to the inconsistency between symbolic planner models and the rich control structures actually running on the robot. In this paper, we present the first physical deployment of an integrated actor-planner system that shares hierarchical operational models for both acting and planning, interleaving the Reactive Acting Engine (RAE) with an anytime UCT-like Monte Carlo planner (UPOM). We implement RAE+UPOM on a mobile manipulator in a real-world deployment for an object collection task. Our experiments demonstrate robust task execution under action failures and sensor noise, and provide empirical insights into the interleaved acting-and-planning decision making process.
Accurate liver and tumor segmentation on abdominal CT images is critical for reliable diagnosis and treatment planning, but remains challenging due to complex anatomical structures, variability in tumor appearance, and limited annotated data. To address these issues, we introduce Hyperbolic-convolutions Adaptive-temporal-attention with Neural-representation and Synaptic-plasticity Network (HANS-Net), a novel segmentation framework that synergistically combines hyperbolic convolutions for hierarchical geometric representation, a wavelet-inspired decomposition module for multi-scale texture learning, a biologically motivated synaptic plasticity mechanism for adaptive feature enhancement, and an implicit neural representation branch to model fine-grained and continuous anatomical boundaries. Additionally, we incorporate uncertainty-aware Monte Carlo dropout to quantify prediction confidence and lightweight temporal attention to improve inter-slice consistency without sacrificing efficiency. Extensive evaluations of the LiTS dataset demonstrate that HANS-Net achieves a mean Dice score of 93.26%, an IoU of 88.09%, an average symmetric surface distance (ASSD) of 0.72 mm, and a volume overlap error (VOE) of 11.91%. Furthermore, cross-dataset validation on the 3D-IRCADb-01 dataset obtains an average Dice of 87.45%, IoU of 80.30%, ASSD of 1.525 mm, and VOE of 19.71%, indicating strong generalization across different datasets. These results confirm the effectiveness and robustness of HANS-Net in providing anatomically consistent, accurate, and confident liver and tumor segmentation.
Fluvial erosion is a natural process that can generate significant impacts on soil stability and strategic infrastructures. The detection and monitoring of this phenomenon is traditionally addressed by photogrammetric methods and analysis in geographic information systems. These tasks require specific knowledge and intensive manual processing. This study proposes an artificial intelligence-based approach for automatic identification of eroded zones and estimation of their area. The state-of-the-art computer vision model YOLOv11, adjusted by fine-tuning and trained with photographs and LiDAR images, is used. This combined dataset was segmented and labeled using the Roboflow platform. Experimental results indicate efficient detection of erosion patterns with an accuracy of 70%, precise identification of eroded areas and reliable calculation of their extent in pixels and square meters. As a final product, the EROSCAN system has been developed, an interactive web application that allows users to upload images and obtain automatic segmentations of fluvial erosion, together with the estimated area. This tool optimizes the detection and quantification of the phenomenon, facilitating decision making in risk management and territorial planning.
This paper presents a diffusion-augmented reinforcement learning (RL) approach for robust autonomous underwater vehicle (AUV) control, addressing key challenges in underwater trajectory planning and dynamic environment adaptation. The proposed method integrates three core innovations: (1) A diffusion-based trajectory generation framework that produces physically feasible multi-step trajectories, enhanced by a high-dimensional state encoding mechanism combining current observations with historical states and actions through a novel diffusion U-Net architecture, significantly improving long-horizon planning. (2) A sample-efficient hybrid learning architecture that synergizes diffusion-guided exploration with RL policy optimization, where the diffusion model generates diverse candidate actions and the RL critic selects optimal actions, achieving higher exploration efficiency and policy stability in dynamic underwater environments. Extensive simulation experiments validating the method's superior robustness and flexibility, outperforms conventional control methods in challenging marine conditions, offering enhanced adaptability and reliability for AUV operations in the underwater tasks.
This letter presents a novel coarse-to-fine motion planning framework for robotic manipulation in cluttered, unmodeled environments. The system integrates a dual-camera perception setup with a B-spline-based model predictive control (MPC) scheme. Initially, the planner generates feasible global trajectories from partial and uncertain observations. As new visual data are incrementally fused, both the environment model and motion planning are progressively refined. A vision-based cost function promotes target-driven exploration, while a refined kernel-perceptron collision detector enables efficient constraint updates for real-time planning. The framework accommodates closed-chain kinematics and supports dynamic replanning. Experiments on a multi-arm platform validate its robustness and adaptability under uncertainties and clutter.
Autonomous unmanned aerial vehicles (UAVs) rely on global navigation satellite system (GNSS) pseudorange measurements for accurate real-time localization and navigation. However, this dependence exposes them to sophisticated spoofing threats, where adversaries manipulate pseudoranges to deceive UAV receivers. Among these, drift-evasive spoofing attacks subtly perturb measurements, gradually diverting the UAVs trajectory without triggering conventional signal-level anti-spoofing mechanisms. Traditional distributional shift detection techniques often require accumulating a threshold number of samples, causing delays that impede rapid detection and timely response. Consequently, robust temporal-scale detection methods are essential to identify attack onset and enable contingency planning with alternative sensing modalities, improving resilience against stealthy adversarial manipulations. This study explores a Bayesian online change point detection (BOCPD) approach that monitors temporal shifts in value estimates from a reinforcement learning (RL) critic network to detect subtle behavioural deviations in UAV navigation. Experimental results show that this temporal value-based framework outperforms conventional GNSS spoofing detectors, temporal semi-supervised learning frameworks, and the Page-Hinkley test, achieving higher detection accuracy and lower false-positive and false-negative rates for drift-evasive spoofing attacks.
We explore a functionalist approach to emotion by employing an ansatz -- an initial set of assumptions -- that a hypothetical concept generation model incorporates unproven but biologically plausible traits. From these traits, we mathematically construct a theoretical reinforcement learning framework grounded in functionalist principles and examine how the resulting utility function aligns with emotional valence in biological systems. Our focus is on structuring the functionalist perspective through a conceptual network, particularly emphasizing the construction of the utility function, not to provide an exhaustive explanation of emotions. The primary emphasis is not of planning or action execution, but such factors are addressed when pertinent. Finally, we apply the framework to psychological phenomena such as humor, psychopathy, and advertising, demonstrating its breadth of explanatory power.
This study presents an advanced approach to enhance robotic manipulation in uncertain and challenging environments, with a focus on autonomous operations augmented by human-in-the-loop (HITL) control for lunar missions. By integrating human decision-making with autonomous robotic functions, the research improves task reliability and efficiency for space applications. The key task addressed is the autonomous deployment of flexible solar panels using an extendable ladder-like structure and a robotic manipulator with real-time feedback for precision. The manipulator relays position and force-torque data, enabling dynamic error detection and adaptive control during deployment. To mitigate the effects of sinkage, variable payload, and low-lighting conditions, efficient motion planning strategies are employed, supplemented by human control that allows operators to intervene in ambiguous scenarios. Digital twin simulation enhances system robustness by enabling continuous feedback, iterative task refinement, and seamless integration with the deployment pipeline. The system has been tested to validate its performance in simulated lunar conditions and ensure reliability in extreme lighting, variable terrain, changing payloads, and sensor limitations.
Offset surfaces, defined as the Minkowski sum of a base surface and a rolling ball, play a crucial role in geometry processing, with applications ranging from coverage motion planning to brush modeling. While considerable progress has been made in computing constant-radius offset surfaces, computing variable-radius offset surfaces remains a challenging problem. In this paper, we present OffsetCrust, a novel framework that efficiently addresses the variable-radius offsetting problem by computing a power diagram. Let $R$ denote the radius function defined on the base surface $S$. The power diagram is constructed from contributing sites, consisting of carefully sampled base points on $S$ and their corresponding off-surface points, displaced along $R$-dependent directions. In the constant-radius case only, these displacement directions align exactly with the surface normals of $S$. Moreover, our method mitigates the misalignment issues commonly seen in crust-based approaches through a lightweight fine-tuning procedure. We validate the accuracy and efficiency of OffsetCrust through extensive experiments, and demonstrate its practical utility in applications such as reconstructing original boundary surfaces from medial axis transform (MAT) representations.
We study the problem of forecasting the number of units fulfilled (or ``drained'') from each inventory warehouse to meet customer demand, along with the associated outbound shipping costs. The actual drain and shipping costs are determined by complex production systems that manage the planning and execution of customers' orders fulfillment, i.e. from where and how to ship a unit to be delivered to a customer. Accurately modeling these processes is critical for regional inventory planning, especially when using Reinforcement Learning (RL) to develop control policies. For the RL usecase, a drain model is incorporated into a simulator to produce long rollouts, which we desire to be differentiable. While simulating the calls to the internal software systems can be used to recover this transition, they are non-differentiable and too slow and costly to run within an RL training environment. Accordingly, we frame this as a probabilistic forecasting problem, modeling the joint distribution of outbound drain and shipping costs across all warehouses at each time period, conditioned on inventory positions and exogenous customer demand. To ensure robustness in an RL environment, the model must handle out-of-distribution scenarios that arise from off-policy trajectories. We propose a validation scheme that leverages production systems to evaluate the drain model on counterfactual inventory states induced by RL policies. Preliminary results demonstrate the model's accuracy within the in-distribution setting.
We study the Shortest-Walk Problem (SWP) in a Graph of Convex Sets (GCS). A GCS is a graph where each vertex is paired with a convex program, and each edge couples adjacent programs via additional costs and constraints. A walk in a GCS is a sequence of vertices connected by edges, where vertices may be repeated. The length of a walk is given by the cumulative optimal value of the corresponding convex programs. To solve the SWP in GCS, we first synthesize a piecewise-quadratic lower bound on the problem's cost-to-go function using semidefinite programming. Then we use this lower bound to guide an incremental-search algorithm that yields an approximate shortest walk. We show that the SWP in GCS is a natural language for many mixed discrete-continuous planning problems in robotics, unifying problems that typically require specialized solutions while delivering high performance and computational efficiency. We demonstrate this through experiments in collision-free motion planning, skill chaining, and optimal control of hybrid systems.
Recent advanced vision-language models(VLMs) have demonstrated strong performance on passive, offline image and video understanding tasks. However, their effectiveness in embodied settings, which require online interaction and active scene understanding remains limited. In such scenarios, an agent perceives the environment from a first-person perspective, with each action dynamically shaping subsequent observations. Even state-of-the-art models such as GPT-4o, Claude 3.5 Sonnet, and Gemini 2.5 Pro struggle in open-environment interactions, exhibiting clear limitations in spatial reasoning and long-horizon planning. To address this gap, we introduce EmRACE-3K, a dataset of over 3,000 language-guided tasks situated in diverse, photorealistic environments constructed using Unreal Engine and the UnrealCV-Zoo framework. The tasks encompass a wide range of embodied challenges, including navigation, object manipulation, and multi-stage goal execution. Each task unfolds as a multi-step trajectory, pairing first-person visual observations with high-level instructions, grounded actions, and natural language rationales that express the agent's intent at every step. Using EmRACE-3K, we establish a benchmark to evaluate the embodied reasoning capabilities of VLMs across three key dimensions: Exploration, Dynamic Spatial-Semantic Reasoning, and Multi-stage Goal Execution. In zero-shot settings, all models achieve success rates below 20%, underscoring the challenge posed by our benchmark and the current limitations of VLMs in interactive environments. To demonstrate the utility of EmRACE-3K, we further fine-tune Qwen2.5-VL-7B using supervised learning followed by reinforcement learning. This approach yields substantial improvements across all three challenge categories, highlighting the dataset's effectiveness in enabling the development of embodied reasoning capabilities.
World models (WMs) demonstrate strong capabilities in prediction, generation, and planning tasks. Existing WMs primarily focus on unstructured data and cannot leverage the ubiquitous structured data, often represented as graphs, in the digital world. While multiple graph foundation models have been proposed, they focus on graph learning tasks and cannot extend to diverse multi-modal data and interdisciplinary tasks. To address these challenges, we propose the Graph World Model (GWM), a world model that supports both unstructured and graph-structured states with multi-modal information and represents diverse tasks as actions. The core of a GWM is a generic message-passing algorithm to aggregate structured information, either over a unified multi-modal token space by converting multi-modal data into text (GWM-T) or a unified multi-modal embedding space by modality-specific encoders (GWM-E). Notably, GWM introduces action nodes to support diverse tasks, where action nodes are linked to other nodes via direct reference or similarity computation. Extensive experiments on six tasks from diverse domains, including multi-modal generation and matching, recommendation, graph prediction, multi-agent, retrieval-augmented generation, and planning and optimization, show that the same GWM outperforms or matches domain-specific baselines' performance, benefits from multi-hop structures, and demonstrates strong zero-shot/few-shot capabilities on unseen new tasks. Our code for GWM is released at https://github.com/ulab-uiuc/GWM.
Strontium-88 is a versatile atomic species often used in quantum optics, precision metrology, and quantum computing. Consolidated atomic data is essential for the planning, execution, and evaluation of experiments. In this reference, we present physical and optical properties of neutral $^{88}$Sr relevant to these applications. Here we focus on experimental results and supplement these with theoretical values. We present equations to convert values and derive important parameters. Tabulated results include key parameters for commonly used transitions in $^{88}$Sr ($^1\mathrm{S}_0 \rightarrow \, ^1\mathrm{P}_1$, $^1\mathrm{S}_0 \rightarrow \, ^3\mathrm{P}_{0,1,2}$, and $^3\mathrm{P}_{0,1,2} \rightarrow \, ^3\mathrm{S}_1$). This dataset serves as an up-to-date reference for studies involving bosonic $^{88}$Sr.
One in three women globally experiences intimate partner violence (IPV), yet little is known about how such trauma affects economic decision-making. We provide causal evidence that IPV influences women's time preferences - a key parameter in models of savings, investment, and labor supply. We combine two empirical strategies using four distinct datasets. First, in two randomized recall experiments in Ethiopia, we randomly assigned women to recall specific acts of abuse before eliciting their intertemporal choices. Women with IPV experiences prompted to recall IPV display significantly greater impatience than otherwise similar women who are not prompted. Second, we exploit exogenous reductions in IPV generated by two randomized interventions - one involving cash transfers, the other psychotherapy - and use treatment assignment as an instrument for IPV exposure. Women who experience reduced IPV as a result of treatment exhibit more patient time preferences. Together, these results provide consistent, novel causal evidence that exposure to IPV induces individuals to discount the future more heavily. This evidence suggests a psychological channel through which violence can perpetuate economic disadvantage and constrain women's ability to take actions - such as saving, investing, or exiting abusive relationships - that require planning over time.
Optimization has been widely used to generate smooth trajectories for motion planning. However, existing trajectory optimization methods show weakness when dealing with large-scale long trajectories. Recent advances in parallel computing have accelerated optimization in some fields, but how to efficiently solve trajectory optimization via parallelism remains an open question. In this paper, we propose a novel trajectory optimization framework based on the Consensus Alternating Direction Method of Multipliers (CADMM) algorithm, which decomposes the trajectory into multiple segments and solves the subproblems in parallel. The proposed framework reduces the time complexity to O(1) per iteration to the number of segments, compared to O(N) of the state-of-the-art (SOTA) approaches. Furthermore, we introduce a closed-form solution that integrates convex linear and quadratic constraints to speed up the optimization, and we also present numerical solutions for general inequality constraints. A series of simulations and experiments demonstrate that our approach outperforms the SOTA approach in terms of efficiency and smoothness. Especially for a large-scale trajectory, with one hundred segments, achieving over a tenfold speedup. To fully explore the potential of our algorithm on modern parallel computing architectures, we deploy our framework on a GPU and show high performance with thousands of segments.
TRIDENT is a planned multi-cubic-kilometer deep-sea neutrino telescope to be built in the South China Sea, designed to rapidly discover high-energy astrophysical neutrino sources with sensitivity to all neutrino flavors. Achieving this at scale requires a detector design that balances performance with power, cost, and mechanical simplicity. This study presents a cost-effective optimization of TRIDENT's hybrid Digital Optical Module (hDOM) design, comparing configurations using high-quantum-efficiency (QE) 3-inch PMTs and larger 4-inch PMTs, the latter evaluated with both baseline and enhanced QE assumptions. Using full-chain detector simulations incorporating site-specific seawater optical properties and realistic backgrounds, we assess performance in all-flavor neutrino detection efficiency, directional reconstruction, and tau neutrino flavor identification from 1 TeV to 10 PeV. We find that if 4-inch PMTs can achieve QE comparable to 3-inch PMTs, their performance matches or improves upon that of the 3-inch design, while significantly reducing channel count, power consumption, and cost. These findings support the 4-inch PMT hDOM as a promising and scalable choice for TRIDENT's future instrumentation.
Inspection of complex underwater structures with tethered underwater vehicles is often hindered by the risk of tether entanglement. We propose REACT (real-time entanglement-aware coverage path planning for tethered underwater vehicles), a framework designed to overcome this limitation. REACT comprises a fast geometry-based tether model using the signed distance field (SDF) map for accurate, real-time simulation of taut tether configurations around arbitrary structures in 3D. This model enables an efficient online replanning strategy by enforcing a maximum tether length constraint, thereby actively preventing entanglement. By integrating REACT into a coverage path planning framework, we achieve safe and optimal inspection paths, previously challenging due to tether constraints. The complete REACT framework's efficacy is validated in a pipe inspection scenario, demonstrating safe, entanglement-free navigation and full-coverage inspection. Simulation results show that REACT achieves complete coverage while maintaining tether constraints and completing the total mission 20% faster than conventional planners, despite a longer inspection time due to proactive avoidance of entanglement that eliminates extensive post-mission disentanglement. Real-world experiments confirm these benefits, where REACT completes the full mission, while the baseline planner fails due to physical tether entanglement.
This paper proposes a novel hierarchical model predictive control (MPC) framework, called the Parent-Child MPC architecture, to steer nonlinear systems under uncertainty towards a target set, balancing computational complexity and guaranteeing recursive feasibility and stability without relying on conservative terminal constraints in online decision-making. By coupling a small-horizon Child MPC layer with one or more large-horizon Parent MPC layers, the architecture ensures recursive feasibility and stability through adjustable stage-wise constraints derived from tube-based control. As is demonstrated in our case studies, compared to traditional MPC methods, the proposed Parent-Child MPC architecture enhances performance and computational efficiency, reduces conservativeness, and enables scalable planning for certain nonlinear systems.
Application migration in edge-cloud system enables high QoS and cost effective service delivery. However, automatically orchestrating such migration is typically solved with heuristic approaches. Starting from the Markov Decision Process (MDP), in this paper, we identify, analyze and compare selected state-of-the-art Artificial Intelligence (AI) planning and Reinforcement Learning (RL) approaches for solving the class of edge-cloud application migration problems that can be modeled as Towers of Hanoi (ToH) problems. We introduce a new classification based on state space definition and analyze the compared models also through this lense. The aim is to understand available techniques capable of orchestrating such application migration in emerging computing continuum environments.
This research introduces MP-RBFN, a novel formulation leveraging Radial Basis Function Networks for efficiently learning Motion Primitives derived from optimal control problems for autonomous driving. While traditional motion planning approaches based on optimization are highly accurate, they are often computationally prohibitive. In contrast, sampling-based methods demonstrate high performance but impose constraints on the geometric shape of trajectories. MP-RBFN combines the strengths of both by coupling the high-fidelity trajectory generation of sampling-based methods with an accurate description of vehicle dynamics. Empirical results show compelling performance compared to previous methods, achieving a precise description of motion primitives at low inference times. MP-RBFN yields a seven times higher accuracy in generating optimized motion primitives compared to existing semi-analytic approaches. We demonstrate the practical applicability of MP-RBFN for motion planning by integrating the method into a sampling-based trajectory planner. MP-RBFN is available as open-source software at https://github.com/TUM-AVS/RBFN-Motion-Primitives.
This work presents a vision-based underwater exploration and inspection autonomy solution integrated into Ariel, a custom vision-driven underwater robot. Ariel carries a $5$ camera and IMU based sensing suite, enabling a refraction-aware multi-camera visual-inertial state estimation method aided by a learning-based proprioceptive robot velocity prediction method that enhances robustness against visual degradation. Furthermore, our previously developed and extensively field-verified autonomous exploration and general visual inspection solution is integrated on Ariel, providing aerial drone-level autonomy underwater. The proposed system is field-tested in a submarine dry dock in Trondheim under challenging visual conditions. The field demonstration shows the robustness of the state estimation solution and the generalizability of the path planning techniques across robot embodiments.
Brain tumor segmentation plays a critical role in clinical diagnosis and treatment planning, yet the variability in imaging quality across different MRI scanners presents significant challenges to model generalization. To address this, we propose the Edge Iterative MRI Lesion Localization System (EdgeIMLocSys), which integrates Continuous Learning from Human Feedback to adaptively fine-tune segmentation models based on clinician feedback, thereby enhancing robustness to scanner-specific imaging characteristics. Central to this system is the Graph-based Multi-Modal Interaction Lightweight Network for Brain Tumor Segmentation (GMLN-BTS), which employs a Modality-Aware Adaptive Encoder (M2AE) to extract multi-scale semantic features efficiently, and a Graph-based Multi-Modal Collaborative Interaction Module (G2MCIM) to model complementary cross-modal relationships via graph structures. Additionally, we introduce a novel Voxel Refinement UpSampling Module (VRUM) that synergistically combines linear interpolation and multi-scale transposed convolutions to suppress artifacts while preserving high-frequency details, improving segmentation boundary accuracy. Our proposed GMLN-BTS model achieves a Dice score of 85.1% on the BraTS2017 dataset with only 4.58 million parameters, representing a 98% reduction compared to mainstream 3D Transformer models, and significantly outperforms existing lightweight approaches. This work demonstrates a synergistic breakthrough in achieving high-accuracy, resource-efficient brain tumor segmentation suitable for deployment in resource-constrained clinical environments.