Search research

A novel Learning-by-Education Node Community framework (LENC) for Collaborative Knowledge Distillation (CKD) is presented, which facilitates continual collective learning through effective knowledge exchanges among diverse deployed Deep Neural Network (DNN) peer nodes. These DNNs dynamically and autonomously adopt either the role of a student, seeking knowledge, or that of a teacher, imparting knowledge, fostering a collaborative learning environment. The proposed framework triggers knowledge transfer via autonomous teacher discovery and stream-driven DNN distillation as needed, while enhancing their learning capabilities and promoting their collaboration. LENC addresses the challenges of handling diverse training data distributions and the limitations of individual DNN node learning abilities. \hl{It enables the exploitation of selected peer-teacher knowledge upon learning a new task and mitigates catastrophic forgetting in DNN nodes.} \hl{Additionally, it supports task-boundary-free continual adaptation in distributed settings via autonomous role assignment and modular forgetting mitigation, as DNN nodes receive no explicit task-boundary metadata during deployment.} Experimental evaluation on a proof-of-concept implementation demonstrates the LENC framework's functionalities and benefits across multiple DNN learning and inference scenarios. The conducted experiments showcase its ability to gradually improve the average test accuracy of the community of interacting DNN nodes in image classification problems, by appropriately leveraging the collective knowledge of all node peers. The LENC framework achieves strong performance in on-line unlabelled CKD.

Federated Learning (FL) emerges as a distributed machine learning approach that addresses privacy concerns by training AI models locally on devices. Decentralized Federated Learning (DFL) extends the FL paradigm by eliminating the central server, thereby enhancing scalability and robustness through the avoidance of a single point of failure. However, DFL faces significant challenges in optimizing security, as most Byzantine-robust algorithms proposed in the literature are designed for centralized scenarios. In this paper, we present a novel Byzantine-robust aggregation algorithm to enhance the security of Decentralized Federated Learning environments, coined WFAgg. This proposal handles adverse conditions and strengthens the robustness of dynamic decentralized topologies at the same time by employing multiple filters to identify and mitigate Byzantine attacks. Experimental results demonstrate the effectiveness of the proposed algorithm in maintaining model accuracy and convergence in the presence of various Byzantine attack scenarios, outperforming state-of-the-art centralized Byzantine-robust aggregation schemes (such as Multi-Krum or Clustering). These algorithms are evaluated on an IID image classification problem in both centralized and decentralized scenarios.

Accurate delineation of agricultural field boundaries is essential for effective crop monitoring and resource management. However, competing methodologies often face significant challenges, particularly in their reliance on extensive manual efforts for cloud-free data curation and limited adaptability to diverse global conditions. In this paper, we introduce PTAViT3D, a deep learning architecture specifically designed for processing three-dimensional time series of satellite imagery from either Sentinel-1 (S1) or Sentinel-2 (S2). Additionally, we present PTAViT3D-CA, an extension of the PTAViT3D model incorporating cross-attention mechanisms to fuse S1 and S2 datasets, enhancing robustness in cloud-contaminated scenarios. The proposed methods leverage spatio-temporal correlations through a memory-efficient 3D Vision Transformer architecture, facilitating accurate boundary delineation directly from preprocessed, cloud-affected imagery. We comprehensively validate our models through extensive testing on various datasets, including Australia's ePaddocks - CSIRO's national, continental-scale agricultural field boundary product covering Australia's cropping regions - alongside public benchmarks Fields-of-the-World, PASTIS, and AI4SmallFarms. Our results consistently demonstrate state-of-the-art performance, highlighting excellent global transferability and robustness. Crucially, our approach significantly simplifies data preparation workflows by reliably processing cloud-affected imagery, thereby offering strong adaptability across diverse agricultural environments. Our code and models are publicly available at https://github.com/feevos/tfcl.

Machine Learning (ML) has become central to Autonomous Vehicles (AVs), supporting perception, prediction, planning, control, and decision-making in dynamic environments. However, achieving full autonomy in cluttered and complex scenarios, such as intricate intersections, diverse scenes, varied trajectories, and complex missions, remains challenging; moreover, data labeling is still a major bottleneck. These limitations motivate Human-in-the-Loop Machine Learning (HITL-ML), in which human input is incorporated through validation, annotation, task organization, reward design, action correction, preference feedback, and supervisory intervention. To advance safe and ethical autonomy, this paper presents a tutorial survey of HITL-ML for AVs, focusing on Curriculum Learning (CL), Human-in-the-Loop Reinforcement Learning (HITL-RL), Human-in-the-Loop Large Language Models (HITL-LLMs), Active Learning (AL), and ethical principles. We first review CL methods that structure training from simple to complex tasks, covering navigation, path planning, obstacle avoidance, data collection, landing, intersection handling, motion planning, and UAV swarm coordination. We then examine HITL-RL through reward shaping, action injection, demonstrations, preference-based feedback, and interactive learning, emphasizing improved learning efficiency, safer policy exploration, and real-time intervention. Next, we review HITL-LLM through collaboration and oversight and specify key challenges. After that, we discuss AL for perception, anomaly detection, semantic mapping, object detection, vehicle recognition, and security-related classification. Ethical principles are reviewed as technical requirements for transparency, accountability, human oversight, safety, security, regulatory compliance, and reliability of human input.

Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental to human cognition. However, mainstream model-free Reinforcement Learning (RL) methods lack the ability to proactively envision future scenarios, plan, and guide strategies. These methods typically rely on trial and error to adjust policy functions, aiming to maximize cumulative rewards or long-term value, even if such high-reward decisions place the environment in extremely dangerous states. To address this, we propose the Prospective (ProSpec) RL method, which makes higher-value, lower-risk optimal decisions by imagining future n-stream trajectories. Specifically, ProSpec employs a dynamic model to predict future states (termed "imagined states") based on the current state and a series of sampled actions. Furthermore, we integrate the concept of Model Predictive Control and introduce a cycle consistency constraint that allows the agent to evaluate and select the optimal actions from these trajectories. Moreover, ProSpec employs cycle consistency to mitigate two fundamental issues in RL: augmenting state reversibility to avoid irreversible events (low risk) and augmenting actions to generate numerous virtual trajectories, thereby improving data efficiency. We validated the effectiveness of our method on the DMControl benchmarks, where our approach achieved significant performance improvements. Code will be open-sourced upon acceptance.

Industry is moving toward autonomous, network-connected machines that detect and adapt to changing conditions, including hardware faults. Conventional fault-tolerant design duplicates hardware and reroutes control logic; reinforcement learning (RL) offers a learning-based alternative. This paper presents the first systematic comparison of two RL algorithms -- Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) -- for integrating fault tolerance into control. Beyond algorithm choice, we investigate four knowledge-transfer strategies: retaining or discarding model parameters, and retaining or discarding storage contents. Performance is evaluated in two Gymnasium environments: Ant-v5 and FetchReachDense-v3. Results show rapid, fault-specific recovery with clear trade-offs. In Ant-v5, retaining PPO's parameters boosts early returns and remains the safest choice across all faults, while retaining SAC's parameters yields mixed outcomes. SAC's early performance further depends on whether the replay buffer is retained: beneficial when prior experiences match current dynamics, but harmful when they diverge. In FetchReachDense-v3, discarding both PPO's and SAC's parameters was most effective under sensor corruption. Across tasks, both algorithms recover near-normal performance within minutes in low-dimensional settings and within days in high-dimensional settings, highlighting a clear trade-off between adaptation speed and asymptotic performance. These findings demonstrate that RL can deliver robust fault tolerance and offer practical guidelines.

Object-oriented embodied navigation tasks require agents to locate specific objects, either defined by category or images, in unseen environments. While recent methods have made progress in extending closed-set models to open-vocabulary scenarios with foundation models, they typically rely on training-free large language models (LLMs) or finetuning with end-to-end reinforcement learning (RL). However, they face challenges in efficiency (e.g., the overhead and cost of LLM inference) and limited generalization from intensive RL training. In this paper, we propose OVExp, a training-efficient framework for open-vocabulary exploration. We make the first effort to demonstrate the generalization capabilities of semantic map-based goal prediction networks using Dense CLIP models. A major challenge is that preserving both precise point-wise object locations and generalizable visual representations in the semantic map leads to unaffordable training costs. To address this, we design a Cross-Modal Transfer on Semantic Mapping strategy which adapts an intriguing text-only training and transfer to multi-model semantic mapping and goals in test-time. Despite relying on text-based spatial layouts with limited objects, OVExp demonstrates robust generalization to unseentargets on established ObjectNav benchmarks.

Pedestrian detection in conventional frame-based imaging often suffers from limited temporal responsiveness and substantial data redundancy. Inspired by the biological retina, event-based vision sensing (EVS) offers ultra-low latency, high temporal resolution, wide dynamic range, and low power consumption, making it highly attractive for pedestrian perception in complex environments. This paper provides a comprehensive review of EVS and its application to pedestrian detection in intelligent transportation and surveillance scenarios. We first summarize the sensing principles, historical development, and key advantages of event-based vision in comparison with conventional frame-based imaging. We then review the major methodological components of event-based pedestrian detection, including sensing inputs, event representations, preprocessing strategies, feature extraction, detection models, datasets, and evaluation metrics. In addition, representative methods are comparatively analyzed in terms of temporal fidelity, detection accuracy, computational efficiency, and deployment complexity. Finally, we discuss the major open challenges in current EB-PD research, including benchmark standardization, event-native model design, multimodal fusion, and real-world deployment, and outline several promising directions for future development. This review aims to provide a structured and up-to-date reference for researchers working on event-based pedestrian perception and related intelligent vision systems.

Video diffusion models can enable embodied agents to anticipate plausible futures from the recent past, but they are typically trained offline on curated datasets--a mismatch with the agents' learning setup at deployment: online, from a single video stream that sequentially outputs one frame at a time. We bridge this training gap and demonstrate that training autoregressive video diffusion models from such a stream, resembling the experience of embodied agents, is not only possible but can also perform comparably to standard offline training given the same number of gradient steps. We find that this robustness to video stream autocorrelation and nonstationarity can be achieved using experience replay methods that retain a subset of the video stream. To support training and evaluation in this setting, we introduce five new datasets for streaming lifelong generative video modeling: Lifelong Bouncing Balls (O), Lifelong Bouncing Balls (C), Lifelong 3D Maze, Lifelong Drive, and Lifelong PLAICraft, each consisting of one million consecutive frames from environments of increasing complexity. Together, our datasets and experiments lay the groundwork for video generative models and world models that continuously learn from single-sensor video streams rather than fixed datasets.

We pose uncertainty quantification and exploration in online decision-making as a problem of training and generation from an autoregressive sequence model, an area experiencing rapid innovation. Our approach rests on viewing uncertainty as arising from missing future outcomes that could be revealed through action choices, rather than from unobservable latent parameters of the environment. This reformulation aligns naturally with modern machine learning capabilities: we can i) train generative models through next-outcome prediction rather than fit explicit priors, ii) assess uncertainty through autoregressive generation rather than sampling latent parameters from posteriors, and iii) adapt to new information by extending the sequence model's context rather than explicit posterior updating. Our main theoretical result establishes a reduction from online decision-making to offline next-outcome prediction: Bayesian regret is controlled directly by the sequence model's offline prediction loss, without requiring an explicit latent-variable posterior. Experiments, including a semi-synthetic news recommendation task, show that autoregressive generation produces calibrated epistemic uncertainty and enables effective exploration by using article text as prior information to focus exploration on resolving remaining uncertainties.

Continuous-Time Dynamic Graphs (CTDGs) enable fine-grained modeling of evolving relational systems. However, most existing CTDG representation learning methods are tailored to in-distribution settings and exhibit limited robustness under out-of-distribution (OOD) shifts. Although recent causal approaches learn invariant representations via interventions, they are primarily designed for static or discrete-time graphs and become computationally prohibitive for CTDGs due to the combinatorial explosion of structural and temporal variations. To address these challenges, we propose CIR, a framework grounded in a novel structural causal model termed the ICCM. To avoid exhaustive interventions, we leverage the Normalized Weighted Geometric Mean (NWGM) to efficiently approximate interventional predictions. We further instantiate ICCM within a practical deep learning architecture that jointly captures invariant structural and temporal patterns through dedicated subgraph extractors, and maintains an environment memory bank to model distributional shifts across evolving contexts. Extensive experiments demonstrate that CIR consistently outperforms existing methods under diverse OOD scenarios.

Continual learning (CL) evaluates adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forgetting, where models lose proficiency in previously learned tasks as they acquire new ones. While numerous solutions have been proposed, existing experimental setups often rely on idealized class-incremental learning scenarios. We introduce Realistic Continual Learning (RealCL), a novel CL paradigm where class distributions across tasks are random. We also present CLARE (Continual Learning Approach with pRE-trained models for RealCL scenarios), a pre-trained model-based solution designed to integrate new knowledge while preserving past learning. Our contributions include pioneering RealCL as a generalization of traditional CL setups, proposing CLARE as an adaptable approach for RealCL tasks, and conducting extensive experiments demonstrating its effectiveness across various RealCL scenarios. Notably, CLARE outperforms existing models on RealCL benchmarks, highlighting its versatility in unpredictable learning environments. Code to reproduce all our experiments can be found at https://github.com/gramuah/clare.

Federated learning has emerged as a decentralized approach for training high-performance models without accessing user data. Despite its effectiveness, it is vulnerable to poisoning attacks, where malicious users manipulate the global model by uploading poisoned updates. In this paper, we propose FedReview, a review-based mechanism to identify and dispose the potential poisoned updates in federated learning. Under FedReview, the server randomly assigns a subset of clients as reviewers to evaluate model updates on their training datasets in each round. The reviewers rank the updates based on evaluation results and estimate the number of low-quality updates as potential poisoned ones. Based on the review reports, the server applies a majority voting mechanism to aggregate rankings, which tolerates wrong rankings from malicious reviewers and guides the removal of suspicious updates during model aggregation. In contrast to prior works such as FLTrust, FedReview does not require a server-side validation dataset or prior knowledge of clients, allowing flexible client participation. Extensive experiments demonstrate that FedReview enables the server to learn a well-performing global model in adversarial environments.

Retrieval-augmented generation (RAG) has rapidly advanced the language model field, particularly in question-answering (QA) systems. By integrating external documents during the response generation phase, RAG significantly enhances the accuracy and reliability of language models. This method elevates the quality of responses and reduces the frequency of hallucinations, where the model generates incorrect or misleading information. However, these methods exhibit limited retrieval accuracy when faced with numerous indistinguishable documents, presenting notable challenges in their practical application. In response to these emerging challenges, we present HiQA, an advanced multi-document question-answering (MDQA) framework that integrates cascading metadata into content and a multi-route retrieval mechanism. We also release a benchmark called MasQA to evaluate and research in MDQA. Finally, HiQA demonstrates the state-of-the-art performance in multi-document environments.

Identifying the most suitable variables to represent the state is a fundamental challenge in Reinforcement Learning (RL). These variables must efficiently capture the information necessary for making optimal decisions. In order to address this problem, in this paper, we introduce the Transfer Entropy Redundancy Criterion (TERC), an information-theoretic criterion, which determines if there is entropy transferred from observable state variables to actions during training. We define an algorithm based on TERC that provably excludes variables from the observable state that do not affect the agent's policy during learning. This yields compact state representations that reduce inference time by up to 2.6 times. Our approach is policy-dependent, making it agnostic to the underlying learning algorithm. The efficiency gains we demonstrate arise at retraining and inference time on the reduced state. Our method improves both retraining and inference efficiency. We demonstrate its effectiveness across three distinct algorithm classes, namely tabular Q-learning, Actor-Critic, and Proximal Policy Optimization (PPO), evaluated in a range of environments. Furthermore, to highlight the differences between the proposed methodology and the current state-of-the-art feature selection approaches, we present a series of controlled experiments on synthetic data, before generalizing to real-world decision-making tasks. We also introduce a representation of the problem that compactly captures the transfer of information from observable state variables to actions as Bayesian networks.

Language-conditioned robot manipulation is an emerging field aimed at enabling seamless communication and cooperation between humans and robotic agents by teaching robots to comprehend and execute instructions conveyed in natural language. This interdisciplinary area integrates scene understanding, language processing, and policy learning to bridge the gap between human instructions and robot actions. In this comprehensive survey, we systematically explore recent advancements in language-conditioned robot manipulation. We categorize existing methods based on the primary ways language is integrated into the robot system, namely language for state evaluation, language as a policy condition, language for cognitive planning and reasoning, and language in unified vision-language-action models. Specifically, we further analyze state-of-the-art techniques from five axes of action granularity, data and supervision regimes, system cost and latency, environments and evaluations, and task specification. Additionally, we highlight the key debates in the field. Finally, we discuss open challenges and future research directions, focusing on potentially enhancing generalization capabilities and addressing safety issues in language-conditioned robot manipulators.

Purpose: Uncertainty Quantification (UQ) has gained traction in an attempt to improve the interpretability and robustness of machine learning predictions. Specifically (medical) biosignals such as electroencephalography (EEG), electrocardiography (ECG), electrooculography (EOG), and electromyography (EMG) could benefit from good UQ, since these suffer from a poor signal-to-noise ratio, and good human interpretability is pivotal for medical applications. To determine how uncertainty estimation can be used for biosignal tasks, we investigate current methods, use cases, applications, evaluations, and uncertainty measures. Methods: In this paper, we systematically review the state of the art of applying Uncertainty Quantification to Machine Learning tasks in the biosignal domain. All works from Web of Science, Scopus, IEEE XPlore and PsycINFO that discuss uncertainty in Machine Learning on one of the aforementioned biosignals is included. Results: We present various methods, shortcomings, uncertainty measures and theoretical frameworks that currently exist in this application domain based on the 53 reviewed papers and related literature. We address misconceptions in the field, provide recommendations for future work, and discuss gaps in the literature in relation to diagnostic implementations as well as control for prostheses or brain-computer interfaces. Conclusion: Overall it can be concluded that promising UQ methods are available, but that research is needed on how people and systems may interact with an uncertainty-model in a (clinical) environment.

Autonomous systems (AS) often rely on Deep Neural Network (DNN) classifiers to operate in complex and dynamically changing environments. However, during operation, these classifiers may encounter domains that differ from those seen during development, causing performance degradation under distribution shift. Removing systems from operation for labelled data collection and retraining is often impractical, particularly when adaptation must occur quickly and at scale. This paper introduces DIRA-SS, a self-supervised extension of Dynamic Incremental Regularised Adaptation (DIRA) that enables online domain adaptation using only a small number of unlabelled target-domain samples. DIRA-SS augments an existing classifier with an auxiliary retraining branch and adapts the shared feature representation through a rotation-prediction task, while elastic weight consolidation regularises important source-domain parameters to reduce destructive updates. This allows the model to benefit from transfer learning without requiring classification labels during operation. We evaluate DIRA-SS on CIFAR-10C, CIFAR-100C, and ImageNet-C using ResNet architectures under severe common corruptions. The results show that DIRA-SS substantially improves performance over the non-adapted source model, achieves accuracy close to the supervised DIRA method, and outperforms existing unsupervised test-time adaptation baselines on ImageNet-C when using only 100 target-domain samples.

Causal discovery aims to learn causal structures up to certain symmetries. Diverse populations or changing environments give rise to heterogeneous data in the following sense: each population/environment is a ``source'' which idiosyncratically determines the forms of causal effects. From this perspective, the source is a latent common cause for every observed variable. While some methods for causal discovery can work around latent confounding in special cases, a global confounder poses a significant challenge. The only known ways to deal with latent global confounding involve making assumptions that limit structural equations and/or noise functions. We demonstrate that globally confounded causal structures can still be identified with arbitrary structural equations and noise functions, so long as the number of latent classes remains small relative to the size and sparsity of the underlying DAG. The approach relies on agglomerating variables into large-enough matrices of moments, whose ranks directly reveal graphical properties of the causal structure. We also provide a statistical test to test the rank of these matrices.

The data market design problem is a problem in economic theory to find a set of signaling schemes (statistical experiments) to maximize expected revenue to the information seller, where each experiment reveals some of the information known to a seller and has a corresponding price [Bergemann et al., 2018]. Each buyer has their own decision to make in a world environment, and their subjective expected value for the information associated with a particular experiment comes from the improvement in this decision and depends on their prior and value for different outcomes. In a setting with multiple buyers, a buyer's expected value for an experiment may also depend on the information sold to others [Bonatti et al., 2022]. We introduce the application of deep learning for the design of revenue-optimal data markets, looking to expand the frontiers of what can be understood and achieved. Relative to earlier work on deep learning for auction design [Dütting et al., 2023], we must learn signaling schemes rather than allocation rules and handle obedience constraints $-$ these arising from modeling the downstream actions of buyers $-$ in addition to incentive constraints on bids. Our experiments demonstrate that this new deep learning framework can almost precisely replicate all known solutions from theory, expand to more complex settings, and be used to establish the optimality of new designs for data markets and make conjectures in regard to the structure of optimal designs.

Omnidirectional camera is a cost-effective and information-rich sensor highly suitable for many marine applications and the ocean scientific community, encompassing several domains such as augmented reality, mapping, motion estimation, visual surveillance, and simultaneous localization and mapping. However, designing and constructing such a high-quality 360$^{\circ}$ real-time streaming camera system for underwater applications is a challenging problem due to the technical complexity in several aspects including sensor resolution, wide field of view, power supply, optical design, system calibration, and overheating management. This paper presents a novel and comprehensive system that addresses the complexities associated with the design, construction, and implementation of a fully functional 360$^{\circ}$ real-time streaming camera system specifically tailored for underwater environments. Our proposed system, UWA360CAM, can stream video in real time, operate in 24/7, and capture 360$^{\circ}$ underwater panorama images. Notably, our work is the pioneering effort in providing a detailed and replicable account of this system. The experiments provide a comprehensive analysis of our proposed system.

We introduce \emph{Calibrated Stackelberg Games (CSGs)}, a generalization of the standard Stackelberg Games (SGs) framework. In CSGs, a principal repeatedly interacts with an agent who (contrary to standard SGs) does not have direct access to the principal's action but instead best-responds to calibrated forecasts about it. This framework provides a powerful and realistic modeling tool that goes beyond assuming that agents use ad hoc and highly specified algorithms for interacting in strategic settings and instead builds on statistical foundations of forecasts and calibration. We show that in CSGs, despite both the principal and the agent having less information than in standard SGs, the principal's optimal utility remains upper and lower bounded by the Stackelberg value of the one-shot game, in both finite and continuous settings. Alongside CSGs, we develop stronger notions of calibration and corresponding algorithms that address two central challenges for calibration in game-theoretic environments. First, achieving point-wise calibration typically incurs an error that scales exponentially with the dimension of the strategy space. Second, the principal's convergence rate in CSGs depends critically on the adaptivity of the agent's calibration algorithm. To address these challenges, we establish a meaningful, efficiently achievable relaxation of calibration based on conditioning on best-response regions. This yields the first notion of calibration in games with a statistical rate that only depends on the number of agents' actions rather than the dimension of the principal's strategy space and that leads to no-swap regret for the agent. We further develop adaptive calibration algorithms for the agents that provide fine-grained, any-time calibration guarantees against adversarial sequences, enabling the principal to achieve faster convergence in CSGs.

The design and organization of complex robotic systems traditionally requires laborious trial-and-error processes to ensure both hardware and software components are correctly connected with the resources necessary for computation. This paper presents a novel generalization of the quadratic assignment and routing problem, introducing formalisms for selecting components and interconnections to synthesize a complete system capable of providing some user-defined functionality. By introducing mission context, functional requirements, and modularity directly into the assignment problem, we derive a solution where components are automatically selected and then organized into an optimal hardware and software interconnection structure, all while respecting restrictions on component viability and required functionality. The ability to generate complete functional systems directly from individual components reduces manual design effort by allowing for a guided exploration of the design space. Additionally, our formulation increases resiliency by quantifying resource margins and enabling adaptation of system structure in response to changing environments, hardware or software failure. The proposed formulation is cast as an integer linear program which is provably $\mathcal{NP}$-hard. Two case studies are developed and analyzed to highlight the expressiveness and complexity of problems that can be addressed by this approach: the first explores the iterative development of a ground-based search-and-rescue robot in a variety of mission contexts, while the second explores the large-scale, complex design of a humanoid disaster robot for the DARPA Robotics Challenge. Numerical simulations quantify real world performance and demonstrate tractable time complexity for the scale of problems encountered in many modern robotic systems.

Driven by the need to address labor shortages and meet the demands of a rapidly growing population, robotic automation has become a critical component in precision agriculture. Leaf-level hyperspectral spectroscopy is shown to be a powerful tool for phenotyping, monitoring crop health, identifying essential nutrients within plants as well as detecting diseases and water stress. This work introduces RoMu4o, a robotic manipulation unit for orchard operations offering an automated solution for proximal hyperspectral leaf sensing. This ground robot is equipped with a 6DOF robotic arm and vision system for real-time deep learning-based image processing and motion planning. We developed robust perception and manipulation pipelines that enable the robot to successfully grasp target leaves and perform spectroscopy. These frameworks operate synergistically to identify and extract the 3D structure of leaves from an observed batch of foliage, propose 6D poses, and generate collision-free constraint-aware paths for precise leaf manipulation. The end-effector of the arm features a compact design that integrates an independent lighting source with a hyperspectral sensor, enabling high-fidelity data acquisition while streamlining the calibration process for accurate measurements. Our ground robot is engineered to operate in unstructured orchard environments. However, the performance of the system is evaluated in both indoor and outdoor plant models. The system demonstrated reliable performance for 1-LPB hyperspectral sampling, achieving 95% success rate in lab trials and 79% in field trials. Field experiments revealed an overall success rate of 70% for autonomous leaf grasping and hyperspectral measurement in a pistachio orchard.

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and to transfer knowledge between similar states. We show that this combination enables the agent to learn both safely and effectively. Under standard online learning assumptions, we provide an algorithm whose regret and number of mentor queries are both sublinear in the time horizon for Markov decision processes with irreversible dynamics and infinite state spaces. Our proof involves a sequence of three reductions, making our result more general than a single algorithm. Conceptually, our result may be the first formal proof that it is possible for an agent to obtain high reward while becoming self-sufficient in an unknown, unbounded, and high-stakes environment without resets.

How to endow aerial robots with the ability to operate in close proximity remains an open problem. The core challenges lie in the propulsion system's dual-task requirement: generating manipulation forces while simultaneously counteracting gravity. These competing demands create dynamic coupling effects during physical interactions. Furthermore, rotor-induced airflow disturbances critically undermine operational reliability. Although fully-actuated unmanned aerial vehicles (UAVs) alleviate dynamic coupling effects via six-degree-of-freedom (6-DoF) force-torque decoupling, existing implementations fail to address the aerodynamic interference between drones and environments. They also suffer from oversized designs, which compromise maneuverability and limit their applications in various operational scenarios. To address these limitations, we present FLOAT Drone (FuLly-actuated cOaxial Aerial roboT), a novel fully-actuated UAV featuring two key structural innovations. By integrating control surfaces into fully-actuated systems for the first time, we significantly suppress lateral airflow disturbances during operations. Furthermore, a coaxial dual-rotor configuration enables a compact size while maintaining high hovering efficiency. Through dynamic modeling, we have developed hierarchical position and attitude controllers that support both fully-actuated and underactuated modes. Experimental validation through comprehensive real-world experiments confirms the system's functional capabilities in close-proximity operations.

When an interactive benchmark reports a single success rate for a language-model agent, it is rarely clear what that number measures. A failure can come from perception, ambiguous instructions, retrieval, missing commonsense about what actions do, an incorrect model of the dynamics, or planning, and an aggregate score does not separate them. LLM-BabyBench recasts the procedurally generated BabyAI gridworld as a fully observable, purely textual environment in which every source of failure but planning is removed by construction. The whole grid is serialised into the prompt, instructions come from a small formal grammar, every object's coordinate is stated, the six actions and their effects are specified, and a deterministic expert validates each answer by executing it rather than judging it. On this substrate we define the PPD suite: Predict asks for the state that follows an action sequence, Plan for an action sequence that reaches a goal, and Decompose for a subgoal sequence that achieves a mission, scored by three assistance-aware metrics that separate understanding a mission from sequencing it. Across seven frontier and open models, simulation is far ahead of planning for every model, near saturation for the strongest and well short of it for the weakest, and the length of the required solution, not grid size or obstacle count, governs planning failure. Each model has a characteristic horizon beyond which single-attempt success collapses. Where enough instances are solved to support the ratio, returned plans stay near-optimal. Models that write out their working show why: they commit to one family of corridor-shaped route and verify it with no means of backing out, so what they return is either near-optimal or invalid. The same pattern holds one level up: decomposition precision falls to zero on long missions even where comprehension persists.

Developing agents capable of exploring, planning and learning in complex open-ended environments is a grand challenge in artificial intelligence (AI). Hierarchical reinforcement learning (HRL) offers a promising solution to this challenge by discovering and exploiting the temporal structure within a stream of experience. The strong appeal of the HRL framework has led to a rich and diverse body of literature attempting to discover a useful structure. However, it is still not clear how one might define what constitutes good structure in the first place, or the kind of problems in which identifying it may be helpful. This work aims to identify the benefits of HRL from the perspective of the fundamental challenges in decision-making, as well as highlight its impact on the performance trade-offs of AI agents. Through these benefits, we then cover the families of methods that discover temporal structure in HRL, ranging from learning directly from online experience to offline datasets, to leveraging large language models (LLMs). Finally, we highlight the challenges of temporal structure discovery and the domains that are particularly well-suited for such endeavours.

Robotic cutting is a challenging, contact-rich manipulation task where the robot must simultaneously negotiate unknown object mechanics, large contact forces, and precise motion requirements. Our hypothesis is that this complexity can be alleviated through the design of a physically structured virtual-model controller that uses switched virtual mechanisms to generate a robust, rhythmic rock-chop motion for robotic cutting, without requiring pre-planned trajectories or precise environmental information. Motion is generated by the interaction between the environment, the robot's dynamics, and the virtual forces of the switching virtual mechanism, ultimately realized through the available actuation. Through theoretical and numerical analysis, together with experimental validation, we demonstrate that the controlled robot behavior settles into a stable periodic motion. Experiments with a Franka manipulator demonstrate robust cuts across five different vegetables, achieving sub-millimeter slice accuracy for thicknesses from 1 mm to 7 mm at a rate of nearly one cut per second. The controller maintains high performance despite changes in knife shape or cutting board height, and successfully adapts to a different humanoid manipulator, demonstrating robustness and platform independence.

The synthesis of spatiotemporally coherent 4D content presents fundamental challenges in computer vision, requiring simultaneous modeling of high-fidelity spatial representations and physically plausible temporal dynamics. Current approaches often struggle to maintain view consistency while handling complex scene dynamics, particularly in large-scale environments with multiple interacting elements. This work introduces Dream4D, a novel framework that bridges this gap through a synergy of controllable video generation and neural 4D reconstruction. Our approach seamlessly combines a two-stage architecture: it first predicts optimal camera trajectories from a single image using few-shot learning, then generates geometrically consistent multi-view sequences via a specialized pose-conditioned diffusion process, which are finally converted into a persistent 4D representation. This framework is the first to leverage both rich temporal priors from video diffusion models and geometric awareness of the reconstruction models, which significantly facilitates 4D generation and shows higher quality (e.g., mPSNR, mSSIM) over existing methods.