Diffusion Policy (DP) enables robots to learn complex behaviors by imitating expert demonstrations through action diffusion. However, in practical applications, hardware limitations often degrade data quality, while real-time constraints restrict model inference to instantaneous state and scene observations. These limitations seriously reduce the efficacy of learning from expert demonstrations, resulting in failures in object localization, grasp planning, and long-horizon task execution. To address these challenges, we propose Causal Diffusion Policy (CDP), a novel transformer-based diffusion model that enhances action prediction by conditioning on historical action sequences, thereby enabling more coherent and context-aware visuomotor policy learning. To further mitigate the computational cost associated with autoregressive inference, a caching mechanism is also introduced to store attention key-value pairs from previous timesteps, substantially reducing redundant computations during execution. Extensive experiments in both simulated and real-world environments, spanning diverse 2D and 3D manipulation tasks, demonstrate that CDP uniquely leverages historical action sequences to achieve significantly higher accuracy than existing methods. Moreover, even when faced with degraded input observation quality, CDP maintains remarkable precision by reasoning through temporal continuity, which highlights its practical robustness for robotic control under realistic, imperfect conditions.
Endowing robots with tool design abilities is critical for enabling them to solve complex manipulation tasks that would otherwise be intractable. While recent generative frameworks can automatically synthesize task settings, such as 3D scenes and reward functions, they have not yet addressed the challenge of tool-use scenarios. Simply retrieving human-designed tools might not be ideal since many tools (e.g., a rolling pin) are difficult for robotic manipulators to handle. Furthermore, existing tool design approaches either rely on predefined templates with limited parameter tuning or apply generic 3D generation methods that are not optimized for tool creation. To address these limitations, we propose RobotSmith, an automated pipeline that leverages the implicit physical knowledge embedded in vision-language models (VLMs) alongside the more accurate physics provided by physics simulations to design and use tools for robotic manipulation. Our system (1) iteratively proposes tool designs using collaborative VLM agents, (2) generates low-level robot trajectories for tool use, and (3) jointly optimizes tool geometry and usage for task performance. We evaluate our approach across a wide range of manipulation tasks involving rigid, deformable, and fluid objects. Experiments show that our method consistently outperforms strong baselines in terms of both task success rate and overall performance. Notably, our approach achieves a 50.0\% average success rate, significantly surpassing other baselines such as 3D generation (21.4%) and tool retrieval (11.1%). Finally, we deploy our system in real-world settings, demonstrating that the generated tools and their usage plans transfer effectively to physical execution, validating the practicality and generalization capabilities of our approach.
In multi-agent systems, signal temporal logic (STL) is widely used for path planning to accomplish complex objectives with formal safety guarantees. However, as the number of agents increases, existing approaches encounter significant computational challenges. Recognizing that many complex tasks require cooperation among multiple agents, we propose swarm STL specifications to describe the collective tasks that need to be achieved by a team of agents. Next, we address the motion planning problem for all the agents in two stages. First, we abstract a group of cooperating agents as a swarm and construct a reduced-dimension state space whose dimension does not increase with the number of agents. The path planning is performed at the swarm level, ensuring the safety and swarm STL specifications are satisfied. Then, we design low-level control strategies for agents within each swarm based on the path synthesized in the first step. The trajectories of agents generated by the two-step policy ensure satisfaction of the STL specifications. We evaluate our two-stage approach in both single-swarm and multi-swarm scenarios. The results demonstrate that all tasks are completed with safety guarantees. Compared to the baseline multi-agent planning approach, our method maintains computational efficiency as the number of agents increases, since the computational time scales with the number of swarms rather than the number of agents.
Several fragments of the satisfiability problem have been studied in the literature. Among these, Linear 3-SAT is a satisfaction problem in which each clause (viewed as a set of literals) intersects with at most one other clause; moreover, any pair of clauses have at most one literal in common. Planar 3-SAT is a fragment which requires that the so-called variable-clause graph is planar. Both fragments are NP-complete and have applications in encoding NP-hard planning problems. In this paper, we investigate the complexity and applications of the fragment obtained combining both features. We define Linear Planar 3-SAT and prove its NP-completeness. We also study the reconfiguration problem of Linear Planar 3-SAT and show that it is PSPACE-complete. As an application, we use these new results to prove the NP-completeness of Bounded Connected Multi-Agent Pathfinding and the PSPACE-completeness of Connected Multi-Agent Pathfinding in two-dimensional grids.
This study aims to develop and evaluate a digital twin (DT) framework to enhance adaptive proton therapy for prostate stereotactic body radiotherapy (SBRT), focusing on improving treatment precision for dominant intraprostatic lesions (DILs) while minimizing organ-at-risk (OAR) toxicity. We propose a decision-theoretic (DT) framework combining deep learning (DL)-based deformable image registration (DIR) with a prior treatment database to generate synthetic CTs (sCTs) for predicting interfractional anatomical changes. Using daily CBCT from five prostate SBRT patients with DILs, the framework precomputes multiple plans with high (DT-H) and low (DT-L) similarity sCTs. Plan optimization is performed in RayStation 2023B, assuming a constant RBE of 1.1 and robustly accounting for positional and range uncertainties. Plan quality is evaluated via a modified ProKnow score across two fractions, with reoptimization limited to 10 minutes. Daily CBCT evaluation showed clinical plans often violated OAR constraints (e.g., bladder V20.8Gy, rectum V23Gy), with DIL V100 < 90% in 2 patients, indicating SIFB failure. DT-H plans, using high-similarity sCTs, achieved better or comparable DIL/CTV coverage and lower OAR doses, with reoptimization completed within 10 min (e.g., DT-H-REopt-A score: 154.3-165.9). DT-L plans showed variable outcomes; lower similarity correlated with reduced DIL coverage (e.g., Patient 4: 84.7%). DT-H consistently outperformed clinical plans within time limits, while extended optimization brought DT-L and clinical plans closer to DT-H quality. This DT framework enables rapid, personalized adaptive proton therapy, improving DIL targeting and reducing toxicity. By addressing geometric uncertainties, it supports outcome gains in ultra-hypofractionated prostate RT and lays groundwork for future multimodal anatomical prediction.
The rapid advancement of vision-language models (VLMs) and their integration into embodied agents have unlocked powerful capabilities for decision-making. However, as these systems are increasingly deployed in real-world environments, they face mounting safety concerns, particularly when responding to hazardous instructions. In this work, we propose AGENTSAFE, the first comprehensive benchmark for evaluating the safety of embodied VLM agents under hazardous instructions. AGENTSAFE simulates realistic agent-environment interactions within a simulation sandbox and incorporates a novel adapter module that bridges the gap between high-level VLM outputs and low-level embodied controls. Specifically, it maps recognized visual entities to manipulable objects and translates abstract planning into executable atomic actions in the environment. Building on this, we construct a risk-aware instruction dataset inspired by Asimovs Three Laws of Robotics, including base risky instructions and mutated jailbroken instructions. The benchmark includes 45 adversarial scenarios, 1,350 hazardous tasks, and 8,100 hazardous instructions, enabling systematic testing under adversarial conditions ranging from perception, planning, and action execution stages.
The ESA/NASA Rosalind Franklin rover, planned for launch in 2028, will carry the first laser desorption ionization mass spectrometer (LDI-MS) to Mars as part of the Mars Organic Molecule Analyzer (MOMA) instrument. MOMA will contribute to the astrobiology goals of the mission through the analysis of potential organic biosignatures. Due to the minimal availability of comparable equipment, laboratory analyses using similar techniques and instrumentation have been limited. In this study, we present a modified commercial benchtop LDI-MS designed to replicate MOMA functionality and to enable rapid testing of samples for MOMA validation experiments. We demonstrate that our instrument can detect organic standards in mineral matrices, with MS/MS enabling structural identification even in complex mixtures. Performance was additionally validated against an existing LDI-MS prototype through the comparison of spectra derived from natural samples from a Mars analog site in the Atacama Desert. Lastly, analysis of Mars analog synthetic mineral mixes highlights the capacity of the instrument to characterize both the mineralogical and organic signals in mission-relevant samples. This modified benchtop instrument will serve as a platform for collaborative research to prepare for MOMA operations, test LDI parameters, and generate pre-flight reference data in support of the mission science and astrobiology specific goals.
This paper deals with the effect of errors in the B and V magnitudes, or measurements in any other color system, on the width of the main sequence in a color-magnitude (Hertzsprung-Russell) diagram. The width is defined as the dispersion in apparent (or absolute) magnitude at a fixed, measured photometric color. I find that the dispersion is larger than might be thought, a priori. A statistical analysis is presented which demonstrates that the error in the magnitude residual from a linear approximation to the main sequence is Gaussian, but with a standard deviation which is much larger, in general, than the errors in the individual B and V magnitudes. This result is confirmed by a Monte Carlo simulation of a main sequence population with specified errors in B and V magnitudes, and can be explained on the basis of simple algebraic arguments.
Capturing human mobility is essential for modeling how people interact with and move through physical spaces, reflecting social behavior, access to resources, and dynamic spatial patterns. To support scalable and transferable analysis across diverse geographies and contexts, there is a need for a generalizable foundation model for spatiotemporal data. While foundation models have transformed language and vision, they remain limited in handling the unique challenges posed by the spatial, temporal, and semantic complexity of mobility data. This vision paper advocates for a new class of spatial foundation models that integrate geolocation semantics with human mobility across multiple scales. Central to our vision is a shift from modeling discrete points of interest to understanding places: dynamic, context-rich regions shaped by human behavior and mobility that may comprise many places of interest. We identify key gaps in adaptability, scalability, and multi-granular reasoning, and propose research directions focused on modeling places and enabling efficient learning. Our goal is to guide the development of scalable, context-aware models for next-generation geospatial intelligence. These models unlock powerful applications ranging from personalized place discovery and logistics optimization to urban planning, ultimately enabling smarter and more responsive spatial decision-making.
As AI's energy demand continues to grow, it is critical to enhance the understanding of characteristics of this demand, to improve grid infrastructure planning and environmental assessment. By combining empirical measurements from Brookhaven National Laboratory during AI training on 8-GPU H100 systems with open-source benchmarking data, we develop statistical models relating computational intensity to node-level power consumption. We measure the gap between manufacturer-rated thermal design power (TDP) and actual power demand during AI training. Our analysis reveals that even computationally intensive workloads operate at only 76% of the 10.2 kW TDP rating. Our architecture-specific model, calibrated to floating-point operations, predicts energy consumption with 11.4% mean absolute percentage error, significantly outperforming TDP-based approaches (27-37% error). We identified distinct power signatures between transformer and CNN architectures, with transformers showing characteristic fluctuations that may impact grid stability.
The convergence of robotics and virtual reality (VR) has enabled safer and more efficient workflows in high-risk laboratory settings, particularly virology labs. As biohazard complexity increases, minimizing direct human exposure while maintaining precision becomes essential. We propose GAMORA (Gesture Articulated Meta Operative Robotic Arm), a novel VR-guided robotic system that enables remote execution of hazardous tasks using natural hand gestures. Unlike existing scripted automation or traditional teleoperation, GAMORA integrates the Oculus Quest 2, NVIDIA Jetson Nano, and Robot Operating System (ROS) to provide real-time immersive control, digital twin simulation, and inverse kinematics-based articulation. The system supports VR-based training and simulation while executing precision tasks in physical environments via a 3D-printed robotic arm. Inverse kinematics ensure accurate manipulation for delicate operations such as specimen handling and pipetting. The pipeline includes Unity-based 3D environment construction, real-time motion planning, and hardware-in-the-loop testing. GAMORA achieved a mean positional discrepancy of 2.2 mm (improved from 4 mm), pipetting accuracy within 0.2 mL, and repeatability of 1.2 mm across 50 trials. Integrated object detection via YOLOv8 enhances spatial awareness, while energy-efficient operation (50% reduced power output) ensures sustainable deployment. The system's digital-physical feedback loop enables safe, precise, and repeatable automation of high-risk lab tasks. GAMORA offers a scalable, immersive solution for robotic control and biosafety in biomedical research environments.
Foundation models have revolutionized robotics by providing rich semantic representations without task-specific training. While many approaches integrate pretrained vision-language models (VLMs) with specialized navigation architectures, the fundamental question remains: can these pretrained embeddings alone successfully guide navigation without additional fine-tuning or specialized modules? We present a minimalist framework that decouples this question by training a behavior cloning policy directly on frozen vision-language embeddings from demonstrations collected by a privileged expert. Our approach achieves a 74% success rate in navigation to language-specified targets, compared to 100% for the state-aware expert, though requiring 3.2 times more steps on average. This performance gap reveals that pretrained embeddings effectively support basic language grounding but struggle with long-horizon planning and spatial reasoning. By providing this empirical baseline, we highlight both the capabilities and limitations of using foundation models as drop-in representations for embodied tasks, offering critical insights for robotics researchers facing practical design tradeoffs between system complexity and performance in resource-constrained scenarios. Our code is available at https://github.com/oadamharoon/text2nav
This paper introduces the ROS2 control and the Hardware Interface (HW) integration for the Fanuc CRX- robot family. It explains basic implementation details and communication protocols, and its integration with the Moveit2 motion planning library. We conducted a series of experiments to evaluate relevant performances in the robotics field. We tested the developed ros2_fanuc_interface for four relevant robotics cases: step response, trajectory tracking, collision avoidance integrated with Moveit2, and dynamic velocity scaling, respectively. Results show that, despite a non-negligible delay between command and feedback, the robot can track the defined path with negligible errors (if it complies with joint velocity limits), ensuring collision avoidance. Full code is open source and available at https://github.com/paolofrance/ros2_fanuc_interface.
Digital twins are transforming engineering and applied sciences by enabling real-time monitoring, simulation, and predictive analysis of physical systems and processes. However, conventional digital twins rely primarily on passive data assimilation, which limits their adaptability in uncertain and dynamic environments. This paper introduces the active digital twin paradigm, based on active inference. Active inference is a neuroscience-inspired, Bayesian framework for probabilistic reasoning and predictive modeling that unifies inference, decision-making, and learning under a unique, free energy minimization objective. By formulating the evolution of the active digital twin as a partially observable Markov decision process, the active inference agent continuously refines its generative model through Bayesian updates and forecasts future states and observations. Decision-making emerges from an optimization process that balances pragmatic exploitation (maximizing goal-directed utility) and epistemic exploration or information gain (actively resolving uncertainty). Actions are dynamically planned to minimize expected free energy, which quantifies both the divergence between predicted and preferred future observations, and the epistemic value of expected information gain about hidden states. This approach enables a new level of autonomy and resilience in digital twins, offering superior spontaneous exploration capabilities. The proposed framework is assessed on the health monitoring and predictive maintenance of a railway bridge.
Handheld Augmented Reality (HAR) is revolutionizing the civil infrastructure application domain. The current trend in HAR relies on marker tracking technology. However, marker-based systems have several limitations, such as difficulty in use and installation, sensitivity to light, and marker design. In this paper, we propose a markerless HAR framework with GeoPose-based tracking. We use different gestures for manipulation and achieve 7 DOF (3 DOF each for translation and rotation, and 1 DOF for scaling). The proposed framework, called GHAR, is implemented for architectural building models. It augments virtual CAD models of buildings on the ground, enabling users to manipulate and visualize an architectural model before actual construction. The system offers a quick view of the building infrastructure, playing a vital role in requirement analysis and planning in construction technology. We evaluated the usability, manipulability, and comprehensibility of the proposed system using a standard user study with the System Usability Scale (SUS) and Handheld Augmented Reality User Study (HARUS). We compared our GeoPose-based markerless HAR framework with a marker-based HAR framework, finding significant improvement in the aforementioned three parameters with the markerless framework.
Efficient traffic signal control (TSC) is essential for mitigating urban congestion, yet existing reinforcement learning (RL) methods face challenges in scaling to large networks while maintaining global coordination. Centralized RL suffers from scalability issues, while decentralized approaches often lack unified objectives, resulting in limited network-level efficiency. In this paper, we propose HiLight, a hierarchical reinforcement learning framework with global adversarial guidance for large-scale TSC. HiLight consists of a high-level Meta-Policy, which partitions the traffic network into subregions and generates sub-goals using a Transformer-LSTM architecture, and a low-level Sub-Policy, which controls individual intersections with global awareness. To improve the alignment between global planning and local execution, we introduce an adversarial training mechanism, where the Meta-Policy generates challenging yet informative sub-goals, and the Sub-Policy learns to surpass these targets, leading to more effective coordination. We evaluate HiLight across both synthetic and real-world benchmarks, and additionally construct a large-scale Manhattan network with diverse traffic conditions, including peak transitions, adverse weather, and holiday surges. Experimental results show that HiLight exhibits significant advantages in large-scale scenarios and remains competitive across standard benchmarks of varying sizes.
Remote sensing semantic segmentation is crucial for extracting detailed land surface information, enabling applications such as environmental monitoring, land use planning, and resource assessment. In recent years, advancements in artificial intelligence have spurred the development of automatic remote sensing semantic segmentation methods. However, the existing semantic segmentation methods focus on distinguishing spectral characteristics of different objects while ignoring the differences in the elevation of the different targets. This results in land cover misclassification in complex scenarios involving shadow occlusion and spectral confusion. In this paper, we introduce a depth prompting two-dimensional (2D) remote sensing semantic segmentation framework (DepthSeg). It automatically models depth/height information from 2D remote sensing images and integrates it into the semantic segmentation framework to mitigate the effects of spectral confusion and shadow occlusion. During the feature extraction phase of DepthSeg, we introduce a lightweight adapter to enable cost-effective fine-tuning of the large-parameter vision transformer encoder pre-trained by natural images. In the depth prompting phase, we propose a depth prompter to model depth/height features explicitly. In the semantic prediction phase, we introduce a semantic classification decoder that couples the depth prompts with high-dimensional land-cover features, enabling accurate extraction of land-cover types. Experiments on the LiuZhou dataset validate the advantages of the DepthSeg framework in land cover mapping tasks. Detailed ablation studies further highlight the significance of the depth prompts in remote sensing semantic segmentation.
The cornerstone of cognitive intelligence lies in extracting hidden patterns from observations and leveraging these principles to systematically predict future outcomes. However, current image tokenization methods demonstrate significant limitations in tasks requiring symbolic abstraction and logical reasoning capabilities essential for systematic inference. To address this challenge, we propose Discrete-JEPA, extending the latent predictive coding framework with semantic tokenization and novel complementary objectives to create robust tokenization for symbolic reasoning tasks. Discrete-JEPA dramatically outperforms baselines on visual symbolic prediction tasks, while striking visual evidence reveals the spontaneous emergence of deliberate systematic patterns within the learned semantic token space. Though an initial model, our approach promises a significant impact for advancing Symbolic world modeling and planning capabilities in artificial intelligence systems.
Imitation learning has driven the development of generalist policies capable of autonomously solving multiple tasks. However, when a pretrained policy makes errors during deployment, there are limited mechanisms for users to correct its behavior. While collecting additional data for finetuning can address such issues, doing so for each downstream use case is inefficient at deployment. My research proposes an alternative: keeping pretrained policies frozen as a fixed skill repertoire while allowing user interactions to guide behavior generation toward user preferences at inference time. By making pretrained policies steerable, users can help correct policy errors when the model struggles to generalize-without needing to finetune the policy. Specifically, I propose (1) inference-time steering, which leverages user interactions to switch between discrete skills, and (2) task and motion imitation, which enables user interactions to edit continuous motions while satisfying task constraints defined by discrete symbolic plans. These frameworks correct misaligned policy predictions without requiring additional training, maximizing the utility of pretrained models while achieving inference-time user objectives.
Humanoid robots often face significant balance issues due to the motion of their heavy limbs. These challenges are particularly pronounced when attempting dynamic motion or operating in environments with irregular terrain. To address this challenge, this manuscript proposes a whole-body control framework for humanoid robots with heavy limbs, using a model-based approach that combines a kino-dynamics planner and a hierarchical optimization problem. The kino-dynamics planner is designed as a model predictive control (MPC) scheme to account for the impact of heavy limbs on mass and inertia distribution. By simplifying the robot's system dynamics and constraints, the planner enables real-time planning of motion and contact forces. The hierarchical optimization problem is formulated using Hierarchical Quadratic Programming (HQP) to minimize limb control errors and ensure compliance with the policy generated by the kino-dynamics planner. Experimental validation of the proposed framework demonstrates its effectiveness. The humanoid robot with heavy limbs controlled by the proposed framework can achieve dynamic walking speeds of up to 1.2~m/s, respond to external disturbances of up to 60~N, and maintain balance on challenging terrains such as uneven surfaces, and outdoor environments.
Scene graphs have emerged as a powerful tool for robots, providing a structured representation of spatial and semantic relationships for advanced task planning. Despite their potential, conventional 3D indoor scene graphs face critical limitations, particularly under- and over-segmentation of room layers in structurally complex environments. Under-segmentation misclassifies non-traversable areas as part of a room, often in open spaces, while over-segmentation fragments a single room into overlapping segments in complex environments. These issues stem from naive voxel-based map representations that rely solely on geometric proximity, disregarding the structural constraints of traversable spaces and resulting in inconsistent room layers within scene graphs. To the best of our knowledge, this work is the first to tackle segmentation inconsistency as a challenge and address it with Traversability-Aware Consistent Scene Graphs (TACS-Graphs), a novel framework that integrates ground robot traversability with room segmentation. By leveraging traversability as a key factor in defining room boundaries, the proposed method achieves a more semantically meaningful and topologically coherent segmentation, effectively mitigating the inaccuracies of voxel-based scene graph approaches in complex environments. Furthermore, the enhanced segmentation consistency improves loop closure detection efficiency in the proposed Consistent Scene Graph-leveraging Loop Closure Detection (CoSG-LCD) leading to higher pose estimation accuracy. Experimental results confirm that the proposed approach outperforms state-of-the-art methods in terms of scene graph consistency and pose graph optimization performance.
Every individual carries a unique and personal life story shaped by their memories and experiences. However, these memories are often scattered and difficult to organize into a coherent narrative, a challenge that defines the task of autobiography writing. Existing conversational writing assistants tend to rely on generic user interactions and pre-defined guidelines, making it difficult for these systems to capture personal memories and develop a complete biography over time. We introduce StorySage, a user-driven software system designed to meet the needs of a diverse group of users that supports a flexible conversation and a structured approach to autobiography writing. Powered by a multi-agent framework composed of an Interviewer, Session Scribe, Planner, Section Writer, and Session Coordinator, our system iteratively collects user memories, updates their autobiography, and plans for future conversations. In experimental simulations, StorySage demonstrates its ability to navigate multiple sessions and capture user memories across many conversations. User studies (N=28) highlight how StorySage maintains improved conversational flow, narrative completeness, and higher user satisfaction when compared to a baseline. In summary, StorySage contributes both a novel architecture for autobiography writing and insights into how multi-agent systems can enhance human-AI creative partnerships.
Motion Object Segmentation (MOS) is crucial for autonomous driving, as it enhances localization, path planning, map construction, scene flow estimation, and future state prediction. While existing methods achieve strong performance, balancing accuracy and real-time inference remains a challenge. To address this, we propose a logits-based knowledge distillation framework for MOS, aiming to improve accuracy while maintaining real-time efficiency. Specifically, we adopt a Bird's Eye View (BEV) projection-based model as the student and a non-projection model as the teacher. To handle the severe imbalance between moving and non-moving classes, we decouple them and apply tailored distillation strategies, allowing the teacher model to better learn key motion-related features. This approach significantly reduces false positives and false negatives. Additionally, we introduce dynamic upsampling, optimize the network architecture, and achieve a 7.69% reduction in parameter count, mitigating overfitting. Our method achieves a notable IoU of 78.8% on the hidden test set of the SemanticKITTI-MOS dataset and delivers competitive results on the Apollo dataset. The KDMOS implementation is available at https://github.com/SCNU-RISLAB/KDMOS.
Vision-Language Models (VLMs) have demonstrated notable promise in autonomous driving by offering the potential for multimodal reasoning through pretraining on extensive image-text pairs. However, adapting these models from broad web-scale data to the safety-critical context of driving presents a significant challenge, commonly referred to as domain shift. Existing simulation-based and dataset-driven evaluation methods, although valuable, often fail to capture the full complexity of real-world scenarios and cannot easily accommodate repeatable closed-loop testing with flexible scenario manipulation. In this paper, we introduce a hierarchical real-world test platform specifically designed to evaluate VLM-integrated autonomous driving systems. Our approach includes a modular, low-latency on-vehicle middleware that allows seamless incorporation of various VLMs, a clearly separated perception-planning-control architecture that can accommodate both VLM-based and conventional modules, and a configurable suite of real-world testing scenarios on a closed track that facilitates controlled yet authentic evaluations. We demonstrate the effectiveness of the proposed platform`s testing and evaluation ability with a case study involving a VLM-enabled autonomous vehicle, highlighting how our test framework supports robust experimentation under diverse conditions.
In the current quantum computing ecosystem, building complex and integrated circuits for addressing real-world problems often involves using basic historical components like Bell states to take advantage of superposition, entanglement, and coherence. The availability of the simulator and the IBM quantum computing endeavor through Qiskit further broadens the scope of application based on domain use. In the NISQ era, however, error mitigation is a criterion that is applied when comparing a QPU run result with the simulator. As the real-world scope of application for quantum computing is being broadened, using simulators as a baseline offers confidence; however, concerns about computation resources and availability arise in the high-speed computational regime. As complex problems entail using a larger number of superconducting physical qubits, what should be the basis of framing a quantum circuit for building quantum algorithms in a real-world scenario, given hardware compatibility that should ideally provide confidence baselining with the simulator outcome? This work implements three base circuits for different qubit systems in the simulator and corresponding 127-qubit IBM Sherbrooke superconducting quantum processing units (QPU) to explore the tradeoff between generalizability, sensitivity of circuit design to parameters, noise resilience, resource planning, and efficient qubit usage insights.
Predicting individuals' next locations is a core task in human mobility modelling, with wide-ranging implications for urban planning, transportation, public policy and personalised mobility services. Traditional approaches largely depend on location embeddings learned from historical mobility patterns, limiting their ability to encode explicit spatial information, integrate rich urban semantic context, and accommodate previously unseen locations. To address these challenges, we explore the application of CaLLiPer -- a multimodal representation learning framework that fuses spatial coordinates and semantic features of points of interest through contrastive learning -- for location embedding in individual mobility prediction. CaLLiPer's embeddings are spatially explicit, semantically enriched, and inductive by design, enabling robust prediction performance even in scenarios involving emerging locations. Through extensive experiments on four public mobility datasets under both conventional and inductive settings, we demonstrate that CaLLiPer consistently outperforms strong baselines, particularly excelling in inductive scenarios. Our findings highlight the potential of multimodal, inductive location embeddings to advance the capabilities of human mobility prediction systems. We also release the code and data (https://github.com/xlwang233/Into-the-Unknown) to foster reproducibility and future research.
In robotic fruit picking applications, managing object occlusion in unstructured settings poses a substantial challenge for designing grasping algorithms. Using strawberry harvesting as a case study, we present an end-to-end framework for effective object detection, segmentation, and grasp planning to tackle this issue caused by partially occluded objects. Our strategy begins with point cloud denoising and segmentation to accurately locate fruits. To compensate for incomplete scans due to occlusion, we apply a point cloud completion model to create a dense 3D reconstruction of the strawberries. The target selection focuses on ripe strawberries while categorizing others as obstacles, followed by converting the refined point cloud into an occupancy map for collision-aware motion planning. Our experimental results demonstrate high shape reconstruction accuracy, with the lowest Chamfer Distance compared to state-of-the-art methods with 1.10 mm, and significantly improved grasp success rates of 79.17%, yielding an overall success-to-attempt ratio of 89.58\% in real-world strawberry harvesting. Additionally, our method reduces the obstacle hit rate from 43.33% to 13.95%, highlighting its effectiveness in improving both grasp quality and safety compared to prior approaches. This pipeline substantially improves autonomous strawberry harvesting, advancing more efficient and reliable robotic fruit picking systems.
Quadrotor Morpho-Transition, or the act of transitioning from air to ground through mid-air transformation, involves complex aerodynamic interactions and a need to operate near actuator saturation, complicating controller design. In recent work, morpho-transition has been studied from a model-based control perspective, but these approaches remain limited due to unmodeled dynamics and the requirement for planning through contacts. Here, we train an end-to-end Reinforcement Learning (RL) controller to learn a morpho-transition policy and demonstrate successful transfer to hardware. We find that the RL control policy achieves agile landing, but only transfers to hardware if motor dynamics and observation delays are taken into account. On the other hand, a baseline MPC controller transfers out-of-the-box without knowledge of the actuator dynamics and delays, at the cost of reduced recovery from disturbances in the event of unknown actuator failures. Our work opens the way for more robust control of agile in-flight quadrotor maneuvers that require mid-air transformation.
Effective management of agricultural landscapes is critical for meeting global biodiversity targets, but efforts are hampered by the absence of detailed, large-scale ecological maps. To address this, we introduce Farmscapes, the first large-scale (covering most of England), high-resolution (25cm) map of rural landscape features, including ecologically vital elements like hedgerows, woodlands, and stone walls. This map was generated using a deep learning segmentation model trained on a novel, dataset of 942 manually annotated tiles derived from aerial imagery. Our model accurately identifies key habitats, achieving high f1-scores for woodland (96\%) and farmed land (95\%), and demonstrates strong capability in segmenting linear features, with an F1-score of 72\% for hedgerows. By releasing the England-wide map on Google Earth Engine, we provide a powerful, open-access tool for ecologists and policymakers. This work enables data-driven planning for habitat restoration, supports the monitoring of initiatives like the EU Biodiversity Strategy, and lays the foundation for advanced analysis of landscape connectivity.
We solve the strong CP problem in a broad class of two Higgs doublet theories that will be probed at the Large Hadron Collider and at future colliders.These theories feature CP and Abelian flavor symmetries, both broken softly in the scalar potential, that yield realistic quark masses and mixings. The flavor symmetry charges are chosen so that $\bar{\theta}=0$ at tree level for all values of the Yukawa and quartic couplings of the theory. We prove that in all such theories the 1-loop contribution to $\bar{\theta}$ also vanishes, independently of the mass scale of the second Higgs doublet. We study two illustrative models with flavor group $\mathbb{Z}_3$. The direct contributions to the neutron electric dipole moment are negligible in both models. While the 2-loop contribution to $\bar{\theta}$ is less than $10^{-12}$ in one model, it can be as large as $10^{-10}$ in the other, yielding the prospect of a signal in planned experiments. Even with Abelian flavor symmetries, CP violation in neutral kaon mixing is generally expected to yield naturalness bounds on the masses of additional Higgs doublets of order 20 TeV. We prove that for all models in our class, where the flavor symmetry forces $\bar{\theta}$ to vanish at tree-level, the flavor-changing neutral currents are CP-conserving, yielding model-dependent bounds from neutral meson mixing near 1 TeV. Mixing of the two CP-even scalars gives corrections to the couplings of the 125 GeV Higgs state to $\bar{t}t, \bar{b}b, \bar{c}c, \bar{\tau}\tau$ and $\bar{\mu} \mu$, giving possible signals at high luminosity runs at LHC and at future colliders. Furthermore, distinctive correlations between corrections in the various channels can probe the underlying flavor symmetry.