Search Results (43)

The accurate characterization and geo-localization of objects using image data and LiDAR are important for forestry, agriculture, urban planning, infrastructure monitoring, and related geospatial applications. However, reliability is affected by uncertainty introduced during sensor acquisition, LiDAR-image projection, segmentation, object-parameter estimation, and final geo-localization. This paper presents a proof-of-concept and method prototype for an uncertainty-aware LiDAR-image workflow in a forestry setting. The novelty of the work does not lie in proposing a new segmentation architecture, but in integrating image-based segmentation, LiDAR-image projection, DBH-level geometric estimation, stage-wise uncertainty propagation, and uncertainty-aware reconciliation of alternative estimates within a single modular workflow. The experimental evaluation was conducted on a limited pilot dataset consisting of 12 individual trees, multiple LiDAR acquisition viewpoints, and 18 high-resolution photographs. The number of trees is the number of independent analyzed objects, whereas the scans and photographs represent acquisition observations. Dense LiDAR point clouds provide many object-level geometric measurements, but these points are not interpreted as independent biological samples. Under the tested acquisition and processing conditions, the uncertainty-aware reconciliation step reduced the estimated spatial uncertainty to approximately 2.5 ± 0.4 cm. This value should be interpreted as a pilot result for the analyzed dataset, not as a general performance guarantee across forest types, tree species, stand densities, lighting conditions, or occlusion patterns. The contribution of this study is therefore positioned as a modular engineering-oriented uncertainty propagation and reconciliation workflow for DBH-level forestry localization. Potential use in robotics, infrastructure monitoring, or other high-precision geospatial applications is discussed only as a future direction requiring separate validation, larger datasets, and real-time implementation work. Full article

Accurate LiDAR point cloud registration on resource-constrained edge platforms is a prerequisite for intelligent robotics and industrial automation, yet it remains challenging because low-overlap matching, false correspondences, and fine alignment must be handled under limited computing budgets without GPU acceleration. While learning-based methods have advanced the field, their heavy hardware dependency and training requirements often hinder their practical deployment on mobile edge devices. To bridge this gap, this paper proposes GeoRescue, a training-free geometric registration framework designed for high-precision perception under stringent hardware limits. The method consists of three modular stages: Asymmetric Correspondence Expansion (ACE), which enlarges the candidate correspondence set to reduce the loss of true matches; Dynamic Geometric Topology Gating (DGTG), which suppresses false matches through distance-consistency-based hypothesis filtering; and Uncertainty-Aware Manifold Refinement (UAMR), which improves fine alignment by explicitly modeling local anisotropic noise via covariance-guided optimization. Experiments on 3DMatch, 3DLoMatch, and KITTI show that GeoRescue achieves registration recall rates of 84.84% and 41.27%, respectively, and a 94.95% success rate on KITTI. Remarkably, the framework matches the accuracy of high-capacity learning models while running on a GPU-free, 15 W edge CPU platform (Intel Core i5-8265U). These results indicate that GeoRescue provides a deployment-ready solution with an optimal efficiency–accuracy trade-off for LiDAR sensing and robotics perception in complex, real-world scenarios. Full article

Human pose estimation in orbit is critical for astronaut health monitoring, task assistance, and intelligent human–robot interaction aboard space stations. However, in microgravity, human poses exhibit arbitrary orientations and are often affected by severe occlusion and complex background interference, while the scarcity of annotated in-orbit data makes it difficult to directly transfer models trained on ground-based datasets. Existing semi-supervised methods also lack explicit constraints from human structural topology and pose-related physical priors, which often leads to unreasonable pseudo-labels and limits performance gains. To address these issues, we propose a physics-inspired semi-supervised pose estimation framework for microgravity scenarios. Specifically, a Canonical Orientation Constraint is introduced to alleviate orientation ambiguity; a Structure-aware Pseudo-Label Refinement module is designed to improve pseudo-label quality; and an Uncertainty-guided Rotational Consistency Framework is proposed to adaptively weight consistency learning under multi-view rotation augmentation. Within a Mean Teacher architecture, the proposed method jointly optimizes the supervised loss, orientation constraint, pseudo-label refinement, and rotational consistency objectives. Experiments on the Astro-Pose dataset show that the proposed method consistently outperforms both fully supervised and semi-supervised baselines under various extreme poses and occlusion conditions, improving AP from 47.6 to 55.6 and AR from 52.4 to 60.1, demonstrating its potential for space-station visual monitoring. Full article

This paper develops an accountability-aware fractional control framework for embodied intelligent systems in shared human environments. The approach combines a Caputo fractional-order stabilizing law, an intent-evidence realization with softmax belief reconstruction, and a conditional proxemic safety layer. Sufficient conditions are established for local Mittag-Leffler stability of the augmented error dynamics and forward invariance of the safe set. Numerical results are presented as a theorem-validation benchmark. For the base case with $\alpha =0.9$, the augmented error norm decays from $1.2359$ to $9.90\times {10}^{-3}$ while the safety margin remains strictly positive, and the robustness condition is satisfied with a margin of $1.8641$. An $\alpha$-sweep and a step-size convergence study further show that the fractional order induces a systematic safety–performance trade-off and that the reported behaviors are numerically stable. Additional simulations with four intent classes, bounded observation noise, and Monte Carlo uncertainty stress tests are included to strengthen the numerical evidence beyond the two-intent theorem-validation case. The manuscript also clarifies the quantitative interpretation of the accountability index, the conditional nature of the safety theorem, and an implementable sampled safety-filter realization for concrete robotic platforms. The results support the proposed framework as a mathematically consistent tool for shaping the balance between regulation and proxemic safety. Full article

This paper presents a Python-based v3.12 framework for robotic object sorting in a virtual workcell, combining learning-from-demonstration with a comparative evaluation of classical machine learning classifiers. A user provides a minimal demonstration (e.g., one cube and one cylinder placed into two bins) from which a dynamic type-to-bin rule is inferred. In this study, learning-from-demonstration is implemented at the level of rule acquisition from minimal task examples rather than at the level of trajectory imitation or low-level motion teaching. This rule is used to relabel a larger dataset of pre-generated object positions, enabling training with a selectable number of file-based samples (2–1600) optionally augmented with manual samples. Five classifiers—decision tree, k-nearest neighbors, logistic regression, naive Bayes, and linear SVM—were trained and then used to drive autonomous pick-and-place execution while logging replication time and correctness (correct/incorrect moves and accuracy). Because the task reaches accuracy saturation under a deterministic rule, an additional offline inference benchmark was included to compare prediction throughput using 10,000 probes with repeated timing (median over 50 runs or mean ± standard deviation over 30 runs). To complement this nominal evaluation, the framework also included a perturbation-aware robustness protocol based on controlled positional perturbation, systematic bias, controlled shape corruption, repeated perturbation voting, and stability-aware scoring. This additional layer makes it possible to examine classifier behavior under controlled uncertainty, especially in reduced-data settings, without changing the compact simulator-based nature of the workflow. Results indicate identical sorting accuracy across models, while inference-time differences remain measurable, highlighting deployment-oriented trade-offs and confirming that end-to-end cycle time is dominated by robot motion rather than model computation. Full article

Action chunking strategies in robot imitation learning struggle to dynamically balance between long-range motion efficiency and short-range operational precision due to their fixed planning horizon. This paper presents an Adaptive Action Chunking framework that enables robots to dynamically predict the optimal action chunk length based on real-time visual context. We design an end-to-end dual-branch network comprising a shared visual encoder, a parallel action prediction head, and a chunk-size prediction head. Experiments on two real-world bimanual robot manipulation tasks (transport-and-place and flip-and-handover) demonstrate that the method autonomously derives two distinct intelligent strategy patterns—phase-aware switching and sustained high-frequency adjustment—in response to task uncertainty. It significantly outperforms fixed-chunk baselines in both success rate and efficiency. Ablation studies confirm that the performance gain stems from the adaptive decision-making mechanism itself. Full article

Robotics is increasingly positioned as an enabling technology for precision agriculture, where management actions must be spatially and temporally targeted under constraints on labour, input use, safety, and environmental impact. This review synthesises studies on agricultural field robotics and organises the literature along four complementary axes: task (monitoring, weeding, spraying, and harvesting), platform (UGV, UAV, gantry/fixed-structure, greenhouse robot, and hybrid systems), autonomy-stack module (perception, localisation, planning, control, actuation, safety, and human–robot interaction), and evaluation setting (lab, greenhouse, open-field single season, and open-field multi-season/multi-site). Across these dimensions, this review analyses how platform constraints shape sensing geometry, actuation capability, localisation reliability, energy/endurance, supervision burden, and safety requirements. It further examines enabling technologies that recur across tasks, including vision and multimodal perception under occlusion and illumination variability, localisation and mapping under weak or denied GNSS, uncertainty-aware planning in deformable and partially observed environments, and compliant end-effectors for contact-rich operations. Beyond cataloguing systems, this paper emphasises evaluation practice by synthesising core task-relevant metrics, comparing laboratory and field validation settings, and proposing a reporting checklist and benchmark ladder to improve reproducibility and cross-study comparability. This review identifies recurring bottlenecks in domain shift, long-term autonomy, calibration robustness, crop-safe actuation, and safety assurance near humans, and it concludes with a staged research roadmap linking near-term evaluation reform to longer-term credible multi-site autonomy. Overall, this paper provides a structured framework for interpreting agricultural robotic systems not only by application but also by deployment context, system maturity, and evaluation credibility. Full article

Underwater dynamic target detection, classification, localization, and tracking (DCLT) is central to maritime surveillance and monitoring and increasingly relies on distributed AUV-based robotic sonar networks operating in passive listening and, when required, cooperative multistatic modes. Achieving a robust performance in realistic oceans remains challenging, because sensor placement must adapt to time-varying acoustic conditions and target priors while preserving acoustic communication connectivity, and because frequent reconfiguration under dynamic currents makes classical large-scale planning computationally expensive. This paper presents an integrated deep reinforcement learning (DRL)-based framework for passive-stage sonar placement and dynamic reconfiguration in distributed AUV networks. First, we cast placement as a constructive finite-horizon Markov decision process (MDP) and train a Proximal Policy Optimization (PPO) agent to sequentially build a collision-free layout on a discretized surveillance grid. The terminal reward is formulated to jointly optimize the environment-aware detection performance, computed from BELLHOP-based transmission loss models, and global network connectivity, quantified using algebraic connectivity. Second, to enable time-critical reconfiguration, we estimate flow-aware motion costs for all AUV–destination pairs using a PPO with a Long Short-Term Memory (LSTM) trajectory policy trained for partial observability. The learned policy can be deployed onboard, allowing each AUV to refine its path online using locally sensed currents, improving robustness to ocean-model uncertainty. The resulting cost matrix is solved via an efficient zero-element assignment method to obtain the optimal one-to-one reassignment. In the reported simulation studies, the proposed Sequential PPO placement method achieves a final reward 16–21% higher than Particle Swarm Optimization (PSO) and 2–3.7% higher than the Genetic Algorithm (GA), while the proposed PPO + LSTM planner reduces average travel time by 30.44% compared with A*. The proposed closed-loop architecture supports frequent re-optimization, scalable fleet operation, and a seamless transition to communication-supported cooperative multistatic tracking after detection, enabling efficient, adaptive DCLT in dynamic marine environments. Full article

The synchronous continuum robot (SCR) was developed to emulate biological structures, such as animal tails and elephant trunks, based on continuum robot principles. By synchronizing disk motions, the SCR generates biologically inspired continuous movements while maintaining precise trajectory control. However, its synchronization-based architecture limits adaptability during physical interaction due to rigid trajectory-following characteristics. To address this limitation, this paper proposes a sensorless variable admittance control (VAC)-based compliant motion generation framework for the SCR. A dynamic model-based sensorless disturbance observer is designed to estimate external torques without additional force sensors. To compensate for uncertainties inherent in the cable-driven transmission mechanism, an adaptive term is incorporated into the parameter identification process, improving disturbance estimation accuracy. Based on the estimated external torques, admittance parameters are adaptively modulated according to joint angles, angular velocities, and robot posture, enabling interaction-aware motion speed regulation. Furthermore, the proposed method simultaneously enforces constraints on both joint angles and angular velocities through the adaptive regulation of target positions and velocities, ensuring safe and physically feasible motion. Experimental results under various interaction scenarios demonstrate reliable contact-independent force estimation and effective compliant motion generation. The proposed framework provides an integrated solution for robust force estimation, adaptive compliance control, and simultaneous constraint enforcement in mechanically synchronized continuum robots. Full article

Large-scale aerospace components (e.g., wings, fuselage sections, wing boxes, and rocket segments) feature large dimensions, low stiffness, complex interfaces, and strict assembly tolerances. Traditional rigid tooling and manual alignment struggle to meet the demands of high precision, efficiency, and flexibility in modern aerospace manufacturing. This paper presents a structured literature review on the automated assembly of large-scale aerospace components, summarizing advances in three core domains: pose adjustment and positioning mechanisms, digital measurement technologies, and trajectory planning and control. Particular emphasis is placed on two cross-cutting themes: measurement uncertainty analysis and flexible assembly, which are critical for high-quality docking. The review classifies pose adjustment mechanisms into four categories (NC positioners, parallel kinematic machines, industrial robots, and novel mechanisms) and digital measurement into five branches (vision metrology, large-scale metrology, measurement field construction, uncertainty analysis, and auxiliary techniques). It also outlines five trajectory planning and control routes, covering traditional methods, multi-sensor fusion, digital twins, flexible assembly, and emerging intelligent approaches. The analysis reveals that current research suffers from fragmentation among mechanism design, metrology, and control, with insufficient integration of uncertainty propagation and flexible deformation modeling. Future systems will rely on heterogeneous equipment collaboration, uncertainty-aware closed-loop control, high-fidelity flexible modeling, and digital twin-driven decision-making. This review provides a unified framework and a technical reference for developing reliable, flexible, and scalable automated assembly systems for next-generation aerospace structures. Full article

Rapid advancements in foundation models, including Large Language Models, Vision-Language Models, Multimodal Large Language Models, and Vision-Language-Action models, have opened new avenues for embodied AI in mobile service robotics. By combining foundation models with the principles of embodied AI, where intelligent systems perceive, reason, and act through physical interaction, mobile service robots can achieve more flexible understanding, adaptive behavior, and robust task execution in dynamic real-world environments. Despite this progress, embodied AI for mobile service robots continues to face fundamental challenges related to the translation of natural language instructions into executable robot actions, multimodal perception in human-centered environments, uncertainty estimation for safe decision-making, and computational constraints for real-time onboard deployment. In this paper, we present the first systematic review of foundation models in mobile service robotics, following the preferred reporting items for systematic reviews and meta-analysis (PRISMA) guidelines. Using an OpenAlex literature search, we considered 7506 papers for the years spanning 1968–2025. Our detailed analysis identified four main challenges and how recent advances in foundation models, related to the translation of natural language instructions into executable robot actions, multimodal perception in human-centered environments, uncertainty estimation for safe decision-making, and computational constraints for real-time onboard deployment, have addressed these challenges. We further examine real-world applications in domestic assistance, healthcare, and service automation, highlighting how foundation models enable context-aware, socially responsive, and generalizable robot behaviors. Beyond technical considerations, we discuss ethical, societal, human-interaction, and physical design and ergonomic implications associated with deploying foundation-model-enabled service robots in human environments. Finally, we outline future research directions emphasizing reliability and lifelong adaptation, privacy-aware and resource-constrained deployment, as well as the governance and human-in-the-loop frameworks required for safe, scalable, and trustworthy mobile service robotics. Full article

Vision–language–action (VLA) models often suffer from limited robustness in long-horizon manipulation tasks—where robots must execute extended sequences of actions over multiple time steps to achieve complex goals—due to their inability to explicitly exploit structural symmetries and to react adaptively when such symmetries are violated by environmental uncertainty. To address this limitation, this paper proposes PI-VLA, a symmetry-aware predictive and interactive VLA framework for robust robotic manipulation. PI-VLA is built upon three key symmetry-driven principles. First, a Cognitive–Motor Synergy (CMS) module jointly generates discrete and continuous action chunks together with predictive world-model features in a single forward pass, enforcing cross-modal action consistency as an implicit symmetry constraint across heterogeneous action representations. Second, a unified training objective integrates imitation learning, reinforcement learning, and state prediction, encouraging invariance to task-relevant transformations while enabling adaptive symmetry breaking when long-horizon deviations emerge. Third, an Active Uncertainty-Resolving Decider (AURD) explicitly monitors action consensus discrepancies and state prediction errors as symmetry-breaking signals, dynamically adjusting the execution horizon through closed-loop replanning. Extensive experiments on long-horizon benchmarks demonstrate that PI-VLA achieves state-of-the-art performance, attaining a 73.2% average success rate on the LIBERO benchmark (with particularly strong gains on the Long-Horizon suite) and an 88.3% success rate in real-world manipulation tasks under visual distractions and unseen conditions. Ablation studies confirm that symmetry-aware action consensus and uncertainty-triggered replanning are critical to robust execution. These results establish PI-VLA as a principled framework that leverages symmetry preservation and controlled symmetry breaking to enable reliable and interactive robotic manipulation. Full article

Safe navigation in dynamic environments remains challenging because classical distance-based constraints ignore the coupling between a robot’s translational motion and attitude dynamics, and fixed safety margins are either over-conservative or risky under varying uncertainty and approach speed. This paper presents a Risk-Aware Model Predictive Control (RA-MPC) framework that addresses both limitations through two integrated components. First, we introduce Orientation–Motion Coupled Control Barrier Functions (O-MCBFs) that enforce unified safety constraints linking collision avoidance with attitude stability limits, preventing dangerous pose configurations during dynamic obstacle avoidance. Second, we develop Risk-Aware Adaptive Margins (RAAMs) that compute time-varying safety buffers based on relative velocity, robot braking capability, and prediction uncertainty, enabling context-dependent safety–efficiency trade-offs without manual parameter tuning. The proposed method integrates these components into a quadratic programming formulation within MPC, ensuring real-time computational tractability. Experimental results demonstrate higher success rates, smoother trajectories, and improved progress toward the goal, with no observed safety violations under the tested conditions. These findings indicate that coupling pose-space safety with risk-adaptive margins provides a principled and practical path to safe and efficient navigation in dynamic scenes. Full article

Accurate braking-distance prediction for heavy-duty multi-axle trucks remains challenging due to the large gross vehicle weight, tandem-axle interactions, and strong transient load transfer during emergency braking. Recent studies on tire–road friction estimation, commercial-vehicle braking control (EBS/AEBS), and weigh-in-motion (WIM) sensing have highlighted that unmeasured vertical-load dynamics and time-varying friction are key sources of prediction uncertainty. To address these limitations, this study proposes an integrated sensing–simulation–AI framework that combines real-time axle-load estimation, full-scale robotic braking tests, fused road-friction sensing, and physics-consistent machine-learning modeling. A micro-electro-mechanical systems (MEMS)-based load-angle sensor was installed on the leaf-spring panel linking tandem axles, enabling the continuous estimation of dynamic vertical loads via a polynomial calibration model. Full-scale on-road braking tests were conducted at 40–60 km/h under systematically varied payloads (0–15.5 t) using an actuator-based braking robot to eliminate driver variability. A forward-looking optical friction module was synchronized with dynamic axle-load estimates and deceleration signals, and additional scenarios generated in a commercial ASM environment expanded the operational domain across a broader range of friction, grade, and loading conditions. A gradient-boosting regression model trained on the hybrid dataset reproduced measured stopping distances with a mean absolute error (MAE) of 1.58 m and a mean absolute percentage error (MAPE) of 2.46%, with most predictions falling within ±5 m across all test conditions. The results indicate that incorporating real-time dynamic axle-load sensing together with fused friction estimation improves braking-distance prediction compared with static-load assumptions and purely kinematic formulations. The proposed load-aware framework provides a scalable basis for advanced driver-assistance functions, autonomous emergency braking for heavy trucks, and infrastructure-integrated freight safety management. All full-scale braking tests were carried out at approximately 60% of the nominal service-brake pressure, representing non-panic but moderately severe braking conditions, and the proposed model is designed to accurately predict the resulting stopping distance under this prescribed braking regime rather than to minimize the absolute stopping distance itself. Full article

Autonomous navigation in cluttered and dynamic industrial environments remains a major challenge for mobile robots. Traditional occupancy-grid and geometric planning approaches often struggle in such unstructured settings due to partial observability, sensor noise, and the frequent presence of moving agents (machinery, vehicles, humans). These limitations seriously undermine long-term reliability and safety compliance—both essential for Industry 4.0 applications. This paper introduces S3PM, a lightweight entropy-regularized framework for simultaneous mapping and path planning that operates directly on dense 3D point clouds. Its key innovation is a dynamics-aware entropy field that fuses per-voxel occupancy probabilities with motion cues derived from residual optical flow. Each voxel is assigned a risk-weighted entropy score that accounts for both geometric uncertainty and predicted object dynamics. This representation enables (i) robust differentiation between reliable free space and ambiguous/hazardous regions, (ii) proactive collision avoidance, and (iii) real-time trajectory replanning. The resulting multi-objective cost function effectively balances path length, smoothness, safety margins, and expected information gain, while maintaining high computational efficiency through voxel hashing and incremental distance transforms. Extensive experiments in both real-world and simulated settings, conducted on a Raspberry Pi 5 (with and without the Hailo-8 NPU), show that S3PM achieves 18–27% higher IoU in static/dynamic segmentation, 0.94–0.97 AUC in motion detection, and 30–45% fewer collisions compared to OctoMap + RRT* and standard probabilistic baselines. The full pipeline runs at 12–15 Hz on the bare Pi 5 and 25–30 Hz with NPU acceleration, making S3PM highly suitable for deployment on resource-constrained embedded platforms. Full article