Model predictive control (MPC) with learned world models has emerged as a promising paradigm for embodied control, particularly for its ability to generalize zero-shot when deployed in new environments. However, learned world models often struggle with long-horizon control due to the accumulation of prediction errors and the exponentially growing search space. In this work, we address these challenges by learning latent world models at multiple temporal scales and performing hierarchical planning across these scales, enabling long-horizon reasoning while substantially reducing inference-time planning complexity. Our approach serves as a modular planning abstraction that applies across diverse latent world-model architectures and domains. We demonstrate that this hierarchical approach enables zero-shot control on real-world non-greedy robotic tasks, achieving a 70% success rate on pick-&-place using only a final goal specification, compared to 0% for a single-level world model. In addition, across physics-based simulated environments including push manipulation and maze navigation, hierarchical planning achieves higher success while requiring up to 4x less planning-time compute.
Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modifications, typically requiring manual prompt tuning to achieve acceptable results. We propose \textbf{CAMEO}, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process rather than a one-shot generation task. CAMEO decomposes editing into coordinated stages of planning, structured prompting, hypothesis generation, and adaptive reference grounding, where external guidance is invoked only when task complexity requires it. To overcome the lack of intrinsic quality control in existing methods, evaluation is embedded directly within the editing loop. Intermediate results are iteratively refined through structured feedback, forming a closed-loop process that progressively corrects structural and contextual inconsistencies. We evaluate CAMEO on anomaly insertion and human pose switching tasks. Across multiple strong editing backbones and independent evaluation models, CAMEO consistently achieves 20\% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic security assessment of six representative OpenClaw-series agent frameworks, namely OpenClaw, AutoClaw, QClaw, KimiClaw, MaxClaw, and ArkClaw, under multiple backbone models. To support this study, we construct a benchmark of 205 test cases covering representative attack behaviors across the full agent execution lifecycle, enabling unified evaluation of risk exposure at both the framework and model levels. Our results show that all evaluated agents exhibit substantial security vulnerabilities, and that agentized systems are significantly riskier than their underlying models used in isolation. In particular, reconnaissance and discovery behaviors emerge as the most common weaknesses, while different frameworks expose distinct high-risk profiles, including credential leakage, lateral movement, privilege escalation, and resource development. These findings indicate that the security of modern agent systems is shaped not only by the safety properties of the backbone model, but also by the coupling among model capability, tool use, multi-step planning, and runtime orchestration. We further show that once an agent is granted execution capability and persistent runtime context, weaknesses arising in early stages can be amplified into concrete system-level failures. Overall, our study highlights the need to move beyond prompt-level safeguards toward lifecycle-wide security governance for intelligent agent frameworks.
In this paper, we study how a budget-constrained bidder should learn to bid adaptively in repeated first-price auctions to maximize cumulative payoff. This problem arises from the recent industry-wide shift from second-price auctions to first-price auctions in display advertising, which renders truthful bidding suboptimal. We propose a simple dual-gradient-descent-based bidding policy that maintains a dual variable for the budget constraint as the bidder consumes the budget. We analyze two settings based on the bidder's knowledge of future private values: (i) an uninformative setting where all distributional knowledge (potentially non-stationary) is entirely unknown, and (ii) an informative setting where a prediction of budget allocation is available in advance. We characterize the performance loss (regret) relative to an optimal policy with complete information. For uninformative setting, we show that the regret is ~O(sqrt(T)) plus a Wasserstein-based variation term capturing non-stationarity, which is order-optimal. In the informative setting, the variation term can be eliminated using predictions, yielding a regret of ~O(sqrt(T)) plus the prediction error. Furthermore, we go beyond the global budget constraint by introducing a refined benchmark based on a per-period budget allocation plan, achieving exactly ~O(sqrt(T)) regret. We also establish robustness guarantees when the baseline policy deviates from the planned allocation, covering both ideal and adversarial deviations.
Decisions to pursue higher education are not fully explained by economic incentives, with social influence and peer effects playing a crucial, yet dynamically understudied, role. This paper develops a theoretical non-linear dynamics model analysing the interplay between economic returns and social pressure. We model a heterogeneous population of "Followers" who exhibit imitative behaviour, and "Positional Agents" who display counter-adaptive behaviour. Agents' preferences for education evolve endogenously, reacting to both aggregate enrolment and an endogenous wage premium that declines with the supply of educated workers. The aggregate dynamics are governed by a one-dimensional non-linear map. By assuming fixed population structure. we show that the social conflict between pro-cyclical imitative forces and counter-cyclical positional forces can destabilize the steady state, generating a period-doubling route to chaos. These complex, endogenous fluctuations in enrolment emerge only for intermediate, heterogeneous population mixes, while homogeneous populations remain stable. We argue that this instability represents a significant coordination failure, scrambling economic signals and hindering rational long-term planning for both students and institutions, making it a key policy concern. Finally, we also extend the result to the case where the population structure is endogenous.
Off-road autonomous navigation demands reliable 3D perception for robust obstacle detection in challenging unstructured terrain. While LiDAR is accurate, it is costly and power-intensive. Monocular depth estimation using foundation models offers a lightweight alternative, but its integration into outdoor navigation stacks remains underexplored. We present an open-source off-road navigation stack supporting both LiDAR and monocular 3D perception without task-specific training. For the monocular setup, we combine zero-shot depth prediction (Depth Anything V2) with metric depth rescaling using sparse SLAM measurements (VINS-Mono). Two key enhancements improve robustness: edge-masking to reduce obstacle hallucination and temporal smoothing to mitigate the impact of SLAM instability. The resulting point cloud is used to generate a robot-centric 2.5D elevation map for costmap-based planning. Evaluated in photorealistic simulations (Isaac Sim) and real-world unstructured environments, the monocular configuration matches high-resolution LiDAR performance in most scenarios, demonstrating that foundation-model-based monocular depth estimation is a viable LiDAR alternative for robust off-road navigation. By open-sourcing the navigation stack and the simulation environment, we provide a complete pipeline for off-road navigation as well as a reproducible benchmark. Code available at https://github.com/LARIAD/Offroad-Nav.
Remanufacturing is fundamentally more challenging than traditional manufacturing due to the significant uncertainty, variability, and incompleteness inherent in end-of-life (EoL) products. At the same time, it has become increasingly essential and urgent for facilitating a circular economy, driven by the growing volume of discarded electronic products and the escalating scarcity of critical materials. In this paper, we review the existing literature and examine the key challenges as well as emerging opportunities in intelligent automation for EoL electronics remanufacturing, providing a comprehensive overview of how robotics, control, and artificial intelligence (AI) can jointly enable scalable, safe, and intelligent remanufacturing systems. This paper starts with the definition, scope, and motivation of remanufacturing within the context of a circular economy, highlighting its societal and environmental significance. Then it delves into intelligent automation approaches for disassembly, inspection, sorting, and component reprocessing in this domain, covering advanced methods for multimodal perception, decision-making under uncertainty, flexible planning algorithms, and force-aware manipulation. The paper further reviews several emerging techniques, including large foundation models, human-in-the-loop integration, and digital twins that have the potential to support future research in this area. By integrating these topics, we aim to illustrate how next-generation remanufacturing systems can achieve robust, adaptable, and efficient operation in the face of complex real-world challenges.
Given a user's complex information need, a multi-agent Deep Research system iteratively plans, retrieves, and synthesizes evidence across hundreds of documents to produce a high-quality answer. In one possible architecture, an orchestrator agent coordinates the process, while parallel worker agents execute tasks. Current Deep Research systems, however, often rely on hand-engineered prompts and static architectures, making improvement brittle, expensive, and time-consuming. We therefore explore various multi-agent optimization methods to show that enabling agents to self-play and explore different prompt combinations can produce high-quality Deep Research systems that match or outperform expert-crafted prompts.
Vision-Language-Action (VLA) models, as large foundation models for embodied control, have shown strong performance in manipulation tasks. However, their performance comes at high inference cost. To improve efficiency, recent methods adopt action chunking, which predicts a sequence of future actions for open-loop execution. Although effective for reducing computation, open-loop execution is sensitive to environmental changes and prone to error accumulation due to the lack of close-loop feedback. To address this limitation, we propose Speculative Verification for VLA Control (SV-VLA), a framework that combines efficient open-loop long-horizon planning with lightweight closed-loop online verification. Specifically, SV-VLA uses a heavy VLA as a low-frequency macro-planner to generate an action chunk together with a planning context, while a lightweight verifier continuously monitors execution based on the latest observations. Conditioned on both the current observation and the planning context, the verifier compares the planned action against a closed-loop reference action and triggers replanning only when necessary. Experiments demonstrate that SV-VLA combines the efficiency of chunked prediction with the robustness of closed-loop control, enabling efficient and reliable VLA-based control in dynamic environments. Code is available: https://github.com/edsad122/SV-VLA.
We present SentiAvatar, a framework for building expressive interactive 3D digital humans, and use it to create SuSu, a virtual character that speaks, gestures, and emotes in real time. Achieving such a system remains challenging, as it requires jointly addressing three key problems: the lack of large-scale, high-quality multimodal data, robust semantic-to-motion mapping, and fine-grained frame-level motion-prosody synchronization. To solve these problems, first, we build SuSuInterActs (21K clips, 37 hours), a dialogue corpus captured via optical motion capture around a single character with synchronized speech, full-body motion, and facial expressions. Second, we pre-train a Motion Foundation Model on 200K+ motion sequences, equipping it with rich action priors that go well beyond the conversation. We then propose an audio-aware plan-then-infill architecture that decouples sentence-level semantic planning from frame-level prosody-driven interpolation, so that generated motions are both semantically appropriate and rhythmically aligned with speech. Experiments show that SentiAvatar achieves state-of-the-art on both SuSuInterActs (R@1 43.64%, nearly 2 times the best baseline) and BEATv2 (FGD 4.941, BC 8.078), producing 6s of output in 0.3s with unlimited multi-turn streaming. The source code, model, and dataset are available at https://sentiavatar.github.io.
The paper presents an approach for learning antenna Radiation Patterns (RPs) of a pair of heterogeneous quadrotor Uncrewed Aerial Vehicles (UAVs) by calibration flight data. RPs are modeled either as a Spherical Harmonics series or as a weighted average over inducing samples. Linear regression of polynomial coefficients simultaneously decouples the two independent UAVs' RPs. A joint calibration trajectory exploits available flight time in an obstacle-free anechoic altitude. Evaluation on a real-world dataset demonstrates the feasibility of learning both radiation patterns, achieving 3.6 dB RMS error, the measurement noise level. The proposed RP learning and decoupling can be exploited in rapid recalibration upon payload changes, thereby enabling precise autonomous path planning and swarm control in real-world applications where setup changes are expected.
This paper presents a learning-based approach for all-pairs motion planning, where the initial and goal states are allowed to be arbitrary points in a safe set. We construct smooth goal-conditioned neural ordinary differential equations (neural ODEs) via bi-Lipschitz diffeomorphisms. Theoretical results show that the proposed model can provide guarantees of global exponential stability and safety (safe set forward invariance) regardless of goal location. Moreover, explicit bounds on convergence rate, tracking error, and vector field magnitude are established. Our approach admits a tractable learning implementation using bi-Lipschitz neural networks and can incorporate demonstration data. We illustrate the effectiveness of the proposed method on a 2D corridor navigation task.
Controllable 3D human avatars have found widespread applications in 3D games, the metaverse, and AR/VR scenarios. The conventional approach to creating such a 3D avatar requires a lengthy, intricate pipeline encompassing appearance modeling, motion planning, rigging, and physical simulation. In this paper, we introduce UNICA (UNIfied neural Controllable Avatar), a skeleton-free generative model that unifies all avatar control components into a single neural framework. Given keyboard inputs akin to video game controls, UNICA generates the next frame of a 3D avatar's geometry through an action-conditioned diffusion model operating on 2D position maps. A point transformer then maps the resulting geometry to 3D Gaussian Splatting for high-fidelity free-view rendering. Our approach naturally captures hair and loose clothing dynamics without manually designed physical simulation, and supports extra-long autoregressive generation. To the best of our knowledge, UNICA is the first model to unify the workflow of "motion planning, rigging, physical simulation, and rendering". Code is released at https://github.com/zjh21/UNICA.
-Navigation through narrow and irregular gaps is an essential skill in autonomous drones for applications such as inspection, search-and-rescue, and disaster response. However, traditional planning and control methods rely on explicit gap extraction and measurement, while recent end-to-end approaches often assume regularly shaped gaps, leading to poor generalization and limited practicality. In this work, we present a fully vision-based, end-to-end framework that maps depth images directly to control commands, enabling drones to traverse complex gaps within unseen environments. Operating in the Special Euclidean group SE(3), where position and orientation are tightly coupled, the framework leverages differentiable simulation, a Stop-Gradient operator, and a Bimodal Initialization Distribution to achieve stable traversal through consecutive gaps. Two auxiliary prediction modules-a gap-crossing success classifier and a traversability predictor-further enhance continuous navigation and safety. Extensive simulation and real-world experiments demonstrate the approach's effectiveness, generalization capability, and practical robustness.
Accurate crowd simulation is crucial for public safety management, emergency evacuation planning, and intelligent transportation systems. However, existing methods, which typically model crowds as a collection of independent individual trajectories, are limited in their ability to capture macroscopic physical laws. This microscopic approach often leads to error accumulation and compromises simulation stability. Furthermore, deep learning-driven methods tend to suffer from low inference efficiency and high computational overhead, making them impractical for large-scale, efficient simulations. To address these challenges, we propose the Spatio-Temporal Decoupled Differential Equation Network (STDDN), a novel framework that guides microscopic trajectory prediction with macroscopic physics. We innovatively introduce the continuity equation from fluid dynamics as a strong physical constraint. A Neural Ordinary Differential Equation (Neural ODE) is employed to model the macroscopic density evolution driven by individual movements, thereby physically regularizing the microscopic trajectory prediction model. We design a density-velocity coupled dynamic graph learning module to formulate the derivative of the density field within the Neural ODE, effectively mitigating error accumulation. We also propose a differentiable density mapping module to eliminate discontinuous gradients caused by discretization and introduce a cross-grid detection module to accurately model the impact of individual cross-grid movements on local density changes. The proposed STDDN method has demonstrated significantly superior simulation performance compared to state-of-the-art methods on long-term tasks across four real-world datasets, as well as a major reduction in inference latency.
In stroke-based rendering, search methods often get trapped in local minima due to discrete stroke placement, while differentiable optimizers lack structural awareness and produce unstructured layouts. To bridge this gap, we propose a dual representation that couples discrete polylines with continuous Bézier control points via a bidirectional mapping mechanism. This enables collaborative optimization: local gradients refine global stroke structures, while content-aware stroke proposals help escape poor local optima. Our representation further supports Gaussian-splatting-inspired initialization, enabling highly parallel stroke optimization across the image. Experiments show that our approach reduces the number of strokes by 30-50%, achieves more structurally coherent layouts, and improves reconstruction quality, while cutting optimization time by 30-40% compared to existing differentiable vectorization methods.
End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies through behavior cloning on expert demonstrations. However, imitation learning inherently limits the model to replicating observed behaviors without exploring diverse driving strategies, leaving it brittle in novel or out-of-distribution scenarios. Reinforcement learning (RL) offers a natural remedy by enabling policy exploration beyond the expert distribution. Yet VLA models, typically trained on offline datasets, lack directly observable state transitions, necessitating a learned world model to anticipate action consequences. In this work, we propose a unified understanding-and-generation framework that leverages world modeling to simultaneously enable meaningful exploration and provide dense supervision. Specifically, we augment trajectory prediction with future RGB and depth image generation as dense world modeling objectives, requiring the model to learn fine-grained visual and geometric representations that substantially enrich the planning backbone. Beyond serving as a supervisory signal, the world model further acts as a source of intrinsic reward for policy exploration: its image prediction uncertainty naturally measures a trajectory's novelty relative to the training distribution, where high uncertainty indicates out-of-distribution scenarios that, if safe, represent valuable learning opportunities. We incorporate this exploration signal into a safety-gated reward and optimize the policy via Group Relative Policy Optimization (GRPO). Experiments on the NAVSIM and nuScenes benchmarks demonstrate the effectiveness of our approach, achieving a state-of-the-art PDMS score of 93.7 and an EPDMS of 88.8 on NAVSIM. The code and demo will be publicly available at https://zihaosheng.github.io/ExploreVLA/.
Multimodal large language models (MLLMs) have shown strong potential for autonomous driving, yet existing benchmarks remain largely ego-centric and therefore cannot systematically assess model performance in infrastructure-centric and cooperative driving conditions. In this work, we introduce V2X-QA, a real-world dataset and benchmark for evaluating MLLMs across vehicle-side, infrastructure-side, and cooperative viewpoints. V2X-QA is built around a view-decoupled evaluation protocol that enables controlled comparison under vehicle-only, infrastructure-only, and cooperative driving conditions within a unified multiple-choice question answering (MCQA) framework. The benchmark is organized into a twelve-task taxonomy spanning perception, prediction, and reasoning and planning, and is constructed through expert-verified MCQA annotation to enable fine-grained diagnosis of viewpoint-dependent capabilities. Benchmark results across ten representative state-of-the-art proprietary and open-source models show that viewpoint accessibility substantially affects performance, and infrastructure-side reasoning supports meaningful macroscopic traffic understanding. Results also indicate that cooperative reasoning remains challenging since it requires cross-view alignment and evidence integration rather than simply additional visual input. To address these challenges, we introduce V2X-MoE, a benchmark-aligned baseline with explicit view routing and viewpoint-specific LoRA experts. The strong performance of V2X-MoE further suggests that explicit viewpoint specialization is a promising direction for multi-view reasoning in autonomous driving. Overall, V2X-QA provides a foundation for studying multi-perspective reasoning, reliability, and cooperative physical intelligence in connected autonomous driving. The dataset and V2X-MoE resources are publicly available at: https://github.com/junwei0001/V2X-QA.
Safe multi-agent coordination in uncertain environments can benefit from learning constraints from other agents. Implicitly communicating safety constraints through actions is a promising approach, allowing agents to coordinate and maintain safety without expensive communication channels. This paper introduces an online method to infer constraints from observing the safety-filtered actions of other agents. We approach the problem by using safety filters to ensure forward safety and exploit their structure to work backwards and infer constraints. We provide sufficient conditions under which we can infer these constraints and prove that our inference method converges. This constraint inference procedure is coupled with a decentralized planning method that ensures safety when the constraint activation distance is sufficiently large. We then empirically validate our method with Monte Carlo simulations and hardware experiments with quadruped robots.
Recently, quantum computing has gained attention in urban studies as a tool for complex transport planning problems, but its role remains unclear. This paper reviews quantum computing research in urban transport planning and highlights major limits in scalability, robustness, constraint handling, and engineering feasibility.Stable and reproducible advantages of quantum optimisation in real urban systems have yet to be shown. By comparing quantum methods with established classical optimisation methods, it is found that decomposition methods, metaheuristics, and reinforcement learning already provide transparent, scalable, and policy-interpretable solutions for medium and large-sized urban transport networks. In contrast, the contribution of quantum methods largely lies in the exploratory analysis of limited, discrete combinatorial subproblems rather than full system-level optimisation. It is argued in this paper for a shift from technology-driven application narrative towards problem-driven method selection. From an urban transport planning perspective, we have identified the specific problem types where the exploratory use of quantum computing may be relevant, including critical link and node vulnerability identification, combinatorial screening of congestion and failure scenarios, disaster-related condition analysis, constrained path option selection, and small-scale facility location and investment option assessment. It is concluded that hybrid frameworks represent a more realistic pathway for integrating quantum computing into urban transport research, in which classical methods ensure systemlevel consistency and policy interpretability while quantum methods support local combinatorial exploration. Until stable engineering advantages are demonstrated, public agencies and researchers should prioritise method validation, scenario suitability, and cross-disciplinary collaboration.
Transport network vulnerability analysis plays a crucial role in safeguarding urban resilience. Traditional vulnerability identification approaches have provided valuable insights, yet they face two major limitations. First, the number of disruption scenarios increases combinatorially with the number of disrupted links considered simultaneously, making classical approaches computationally prohibitive. Second, most studies approximate the impacts of multiple simultaneous link failures through linear aggregation, which fails to capture the nonlinear interaction effects observed in real networks. To address these gaps, we reformulate the bi-level Mixed-Integer Nonlinear Programming (MINLP) model into a quantum-compatible Quadratic Unconstrained Binary Optimisation (QUBO) structure, enabling parallel exploration of complex disruption scenarios while incorporating nonlinear interaction effects. We develop a hybrid optimisation framework that integrates the quantum optimisation algorithm with the Frank-Wolfe method to validate the model's effectiveness on the small-scale network. Then, we further verify the framework through the D-Wave hardware across benchmark networks of different scales, including Sioux Falls, Anaheim, Chicago Sketch, and Berlin Full, to examine scalability and feasibility. The results show that this framework achieves strong solvability and stability. In particular, optimisation for large and larger networks is completed within minutes (Approximately 2.8 minutes for the 914-link, 9.8 minutes for the 2950-link, and 31.2 minutes for the 6018-link on D-Wave), demonstrating a computational efficiency improvement by one to two orders of magnitude compared with classical metaheuristic algorithms. These findings highlight the feasibility and potential of applying quantum computing to network vulnerability identification and open a new avenue for resilience-oriented planning.
The increasing, high-risk interactions between vehicles and vulnerable micromobility users, such as e-scooter riders, challenge vehicular safety functions and Automated Driving (AD) techniques, often resulting in severe consequences due to the dynamic uncertainty of e-scooter motion. Despite advances in data-driven AD methods, traffic data addressing the e-scooter interaction problem, particularly for safety-critical moments, remains underdeveloped. This paper proposes a pipeline that utilizes collected on-road traffic data and creates configurable synthetic interactions for validating vehicle motion planning algorithms. A Social Force Model (SFM) is applied to offer more dynamic and potentially risky movements for the e-scooter, thereby testing the functionality and reliability of the vehicle collision avoidance systems. A case study based on a real-world interaction scenario was conducted to verify the practicality and effectiveness of the established simulator. Simulation experiments successfully demonstrate the capability of extending the target scenario to more critical interactions that may result in a potential collision.
Path queries are crucial for property graphs, and there is growing interest in queries that combine regular expressions over labels with constraints on property values of vertices and edges. Efficient evaluation of such general path queries requires that intermediate results be eliminated early when there is no possible completion to a full result path. Neither state-of-the-art (SOA) graph DBMS nor relational DBMS currently can do this effectively for a large class of queries. We show that this problem can be addressed by giving a relational optimizer ``a little help'' by specifying early filtering opportunities explicitly in the query. To this end, we propose ReCAP, an abstraction that greatly simplifies the implementation of early filtering techniques for any type of property constraint for which such early filtering can be derived. No matter how complex the constraint, one only needs to implement (1) an NFA-style state transition function and (2) a handful of functions that mirror those needed for user-defined aggregates. We show that when using ReCAP, a standard relational DBMS like DuckDB can effectively push property constraints deep into the query plan, beating the SOA graph and relational DBMS by a factor up to 400,000 over a variety of queries and input graphs.
Electric utilities must make massive capital investments in the coming years to respond to explosive growth in demand, aging assets and rising threats from extreme weather. Utilities today already have rigorous frameworks for capital planning, and there are opportunities to extend this capability to solve multi-objective optimization problems in the face of uncertainty. This work presents a four-part framework that 1) incorporates extreme weather as a source of uncertainty, 2) leverages a digital twin of the grid, 3) uses Monte Carlo simulation to capture variability and 4) applies a multi-objective optimization method for finding the optimal investment portfolio. We use this framework to investigate whether grid-aware optimization methods outperform model-free approaches. We find that, in fact, given the computational complexity of model-based metaheuristic optimization methods, the simpler net present value ranking method was able to find more optimal portfolios with only limited knowledge of the grid.
Two-Stage Vehicle Routing Problems with Stochastic Demands (VRPSDs) form a class of stochastic combinatorial optimization problems where routes are planned in advance, demands are revealed upon vehicle arrival, and recourse actions are triggered whenever capacity is exceeded. Following recent works, we consider VRPSDs where demands are given by an empirical probability distribution of scenarios. Existing approaches rely on integer L-shaped (ILS) cuts, whose coefficients are tailored for specific recourse policies. In contrast, we propose a framework that casts recourse policies as solutions of a higher-dimensional mixed-integer program, and we characterize its convex hull in the original lower-dimensional space via a new class of inequalities called scenario recourse inequalities (SRIs). We show that SRIs are valid for any recourse policy satisfying mild assumptions and are sufficient for formulating the VRPSD under a scenario-optimal recourse policy, where the recourse actions are chosen optimally for each scenario. Under this latter policy, we also show that SRIs dominate several ILS cuts. We conduct computational experiments on the VRPSD with scenarios under both the classical and the scenario-optimal recourse policies. By using the SRIs, our algorithm solves 329 more instances to optimality than the previous state-of-the-art ILS algorithm.
This tutorial contrasts probabilistic modeling and robust optimization to determine decisions in humanitarian logistics, specifically supply chains subject to adversarial (natural and human) disruptions. Natural disruptions induce dispatch of long-haul relief supply movement as storm forecasts evolve. A two-step workflow: (i) computes an initial pre-staging plan from the most likely forecast, and (ii) evaluates that fixed plan across plausible deviations in the eventual landfall location. In this way, dispatch decisions balance lead time and improved forecast information. For last-mile distribution, we propose deliveries when transportation networks must be protected against the worst case. We apply an iterative robust routing method that detects high-concentration links and increases their effective cost to promote route diversification. A case study based on Typhoon Noru (2022) shows how the combined approach identifies an optimal dispatch time and then protects last-mile delivery from difficult-to-predict network disruptions that could jeopardize the entire supply-chain operation.
As Urban air mobility scales, commercial drone fleets offer a compelling, yet underexplored opportunity to function as mobile sensor networks for real-time urban traffic monitoring. In this paper, we propose a decentralized framework that enables drone fleets to simultaneously execute delivery tasks and observe network traffic conditions. We model the urban environment with dynamic information values associated with road segments, which accumulate traffic condition uncertainty over time and are reset upon drone visitation. This problem is formulated as a mixed-integer linear programming problem where drones maximize the traffic information reward while respecting the maximum detour for each delivery and the battery budget of each drone. Unlike centralized approaches that are computationally heavy for large fleets, our method focuses on dynamic local clustering. When drones enter communication range, they exchange their belief in traffic status and transition from isolated path planning to a local joint optimization mode, resolving coupled constraints to obtain replanned paths for each drone, respectively. Simulation results built on the real city network of Barcelona, Spain, demonstrate that, compared to a shortest-path policy that ignores the traffic monitoring task, our proposed method better utilizes the battery and detour budget to explore the city area and obtain adequate traffic information; and, thanks to its decentralized manner, this ``meet-and-merge" strategy achieves near-global optimality in network coverage with significantly reduced computation overhead compared to the centralized baseline.
Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness and efficiency. However, a systemic challenge remains unresolved, as inherent latency causes generated actions to inevitably lag behind the real-time environment. This issue is particularly exacerbated in dynamic scenarios, where such temporal misalignment severely compromises the policy's ability to interpret and react to rapidly evolving surroundings. In this paper, we propose a novel framework that leverages predicted object flow to synthesize future observations, incorporating a flow-based contrastive learning objective to align the visual feature representations of predicted observations with ground-truth future states. Empowered by this anticipated visual context, our asynchronous policy gains the capacity for proactive planning and motion, enabling it to explicitly compensate for latency and robustly execute manipulation tasks involving actively moving objects. Experimental results demonstrate that our approach significantly enhances responsiveness and success rates in complex dynamic manipulation tasks.
The Earth's Moon presents a uniquely advantageous environment for detecting astrophysical gravitational waves (GWs), particularly in the scientifically interesting deciHz regime. The Laser Interferometer Lunar Antennae (LILA) project plans to perform GW measurements on the lunar surface, using the Moon's unique seismic quietness to access the deciHz regime. Two mission concepts are considered: the initial LILA-Pioneer L-shaped strainmeter and the more advanced LILA-Horizon triangular interferometer. Because the detection frequency is so low, LILA requires only the Moon's precession around the Earth and Sun to triangulate (unlike Earth-based detectors). Thus, the science return of LILA is site-agnostic; however, significant constraints are imposed by practical considerations. These include the need for isolation from anthropogenic noise, protection from the lunar environment, accessibility for lunar terrain vehicles, and line-of-sight. Candidate sites are shown for both LILA-Pioneer and LILA-Horizon, demonstrating that many options exist for deployment of both tools.
Reinforcement learning (RL) agents often struggle with out-of-distribution (OOD) scenarios, leading to high uncertainty and random behavior. While language models (LMs) contain valuable world knowledge, larger ones incur high computational costs, hindering real-time use, and exhibit limitations in autonomous planning. We introduce Adaptive Safety through Knowledge (ASK), which combines smaller LMs with trained RL policies to enhance OOD generalization without retraining. ASK employs Monte Carlo Dropout to assess uncertainty and queries the LM for action suggestions only when uncertainty exceeds a set threshold. This selective use preserves the efficiency of existing policies while leveraging the language model's reasoning in uncertain situations. In experiments on the FrozenLake environment, ASK shows no improvement in-domain, but demonstrates robust navigation in transfer tasks, achieving a reward of 0.95. Our findings indicate that effective neuro-symbolic integration requires careful orchestration rather than simple combination, highlighting the need for sufficient model scale and effective hybridization mechanisms for successful OOD generalization.