Computer Science and Mathematics

Abstract: Simultaneous localization and mapping (SLAM) is a foundational capability for autonomous navigation in unknown environments. Its performance is strongly coupled to the type, quality, and reliability of available sensor data, limiting the portability of navigation systems across heterogeneous mobile robot platforms. This paper presents a cross-platform adaptive navigation framework that decouples localization providers from platform-specific sensing configurations. A sensor abstraction layer normalizes heterogeneous and low-fidelity sensor inputs into a unified representation, enabling structured operational modes constructed according to available sensing modalities, computational constraints, and environmental characteristics. A learning-based performance prediction module is further designed to estimate impending SLAM degradation and support proactive mode switching. Due to middleware constraints within the Pepper NAOqi stack, this predictive component was not deployed during experimental evaluation and remains part of the proposed architecture for future validation. Experimental results on real indoor navigation tasks demonstrate improved robustness and portability compared to fixed SLAM configurations without manual retuning.

Abstract: A widely held assumption in cross-embodiment robot learning is that morphologically similar robots transfer behavior more easily, so a similarity measure, a learned transferability predictor, or a sufficiently diverse pretraining set should predict or improve transfer. We test this assumption under an enforced acceptance gate, requiring every claim to beat its strongest trivial baseline by a margin whose bootstrap 95% confidence interval excludes that baseline on independent units, and we refute it four ways. A morphology-distance predictor fails to beat a target-only prior, with Spearman rho = 0.283 versus 0.579 over 42 independent pairs. A transferability oracle trained on full morphology features, with rho = 0.762 over 29 robots, fails to beat a one-bit arm/not-arm indicator, which reaches 0.834; it predicts robot class, not morphology. On the 812-pair suite there is no transfer law; the mean gain is +0.8 percentage points, within-target variation across sources is under-dispersed relative to evaluation noise, with variance ratio 0.53, and every candidate pairwise predictor has a confidence interval spanning zero. The apparent benefit of pretraining diversity vanishes once total data volume is held fixed, with Delta = -0.026 and CI [-0.092, +0.034]; breadth never beats depth at any tested budget. A same-body control shows the assay detects transfer when present, with Delta = +0.067 and p = 0.0006, and a morphology-equivariant graph policy attains zero-shot transfer that distance still fails to grade. The outcome level is set by the target's own trainability and raw data volume; short of exact body identity, no measured relation between bodies moves it.

Abstract: Every system that reached zero-shot cross-embodiment manipulation in the first half of 2026 made the same move, deleting body information from the interface between task reasoning and motor control, whether through body-agnostic handheld data, masked end-effectors, language-coded actions, or contact-intent latents. None of these systems tests that the deletion is what causes transfer, characterizes what the interface still retains, or asks whether the interface must be symbolic. This paper supplies all three on a scene-controlled manipulation substrate where appearance confounds cannot operate. A causal interface ladder over five source and five held-out arms shows that a body-blind end-effector interface transfers zero-shot while leaking body channels back into it collapses transfer once the leak passes a threshold, a gap of $0.157$ that every held-out arm reproduces, and that injecting body identity is actively harmful. At matched body-blindness and identical upstream information, a structured symbolic coding of the interface beats a language-token coding by $0.109$ with the margin compounding over task depth, while a low-capacity continuous latent falls below the task's precision floor. On a released vision-language-action model with scene controlled by robot-swap rendering, most apparent body recoverability is scene appearance, yet a modest scene-invariant residue exceeds a raw-pixel control in all three folds, and an in-model test finds the decoded action body-light. Recoverability is not reliance, at the interface and inside the released model alike, which is the mechanism the zero-shot wave depends on and the boundary it must respect.

Abstract: Cross-embodiment transfer, the reuse of learned behavior across robots of different morphologies, is a central goal of generalist robot learning, and the quantitative claims made about it fail in a small set of specific, recurring ways. A transfer claim can ride a robot-class prior that a single bit reproduces, tighten a confidence interval by treating seeds as independent observations, credit pretraining diversity for what is data volume, or certify an invariant representation with a linear probe that a nonlinear probe falsifies. This paper defines an enforced measurement standard of eight checks, each backed by a runnable tool, that catches these failure modes before a claim ships. The centerpiece is an acceptance gate that recomputes a claim's metric, runs its strongest trivial baseline, bootstraps the difference over independent units, and emits pass or fail. The standard is demonstrated through eleven documented failure-mode case studies drawn from a real cross-embodiment research program, each stated as the tempting claim, the diagnostic that exposes it, the corrected analysis, and the check that catches it, and each traced to a released artifact. The eleven cases span every check, from a correlation of 0.98 that proves geometrically trivial to an identity probe on a released vision-language-action model that a raw eight-by-eight-pixel control exposes as appearance-confounded. The work is positioned within the 2025-2026 movement toward statistical rigor in robot-policy evaluation, to which it adds the confound set specific to cross-embodiment transfer, an enforced gate rather than a checklist, and a worked record of the checks correcting real claims.

Abstract: A central ambition of cross-embodiment robot learning is a single representation of the task that is invariant to the body, a shared task-state that means the same thing on a four-legged robot as on an eight-legged one, or on a Panda arm as on a UR10e. The dominant approach learns such a representation as a continuous latent, trained for control-sufficiency and scrubbed of body identity by an adversary. We prove this is impossible exactly when behavior is body-coupled. The central object is a sufficiency-invariance bound, which states that any continuous task-state $z$ that is $\varepsilon$-sufficient to predict a body's realized outcome $y$ leaks the body identity $m$ at a floor set by how body-coupled the behavior is, $I(z;m) \ge I(y;m) - \kappa(\varepsilon)$. The lower bound is constructive, obtained by composing the sufficiency decoder with a classifier of $m$ from $y$ to build a probe of $m$ from $z$, and its assumption-free content is the measured accuracy of that probe. Lifting it to the closed form requires a margin condition, $\kappa(\varepsilon) \le \inf_t [\delta(t) + \varepsilon/t^2]$. A rate-distortion complement shows when a coarse task-state escapes the floor, namely when bodies reach the same coarse symbol through different fine realizations. We validate the bound on two non-commensurable substrates. On locomotion the floor is $0.90$ under a strong probe against a linear reading of $0.37$, every control-sufficient continuous latent leaks topology above $0.98$, and a coarse state reaches near chance while retaining most task signal. On manipulation the floor is $0.86$ against a linear $0.34$, the leak exceeds $0.80$, and the coarse state again sheds the body. The morphology-invariant interface between deliberation and control must therefore be coarse.

Abstract: Companion work shows that neither morphological similarity nor data diversity governs policy transfer across robot bodies, and that any continuous task representation sufficient for control re-encodes the body it came from. This paper supplies the constructive counterpart, a task factorization whose cross-body interface is a coarse symbolic progress state. On a depth K sequential-reach task over six simulated arms, we compare three behavior-cloned agents that differ only in how the observation is factored. A reactive policy that must infer the active subgoal from perception solves single reaches, with success 0.628, but collapses at depths 2 to 4, with success 0.069, 0.000, and 0.003. A deliberative agent whose plan supplies the active subgoal holds between 0.631 and 0.558 and matches an oracle policy hand-fed the progress state at every depth. Under an enforced acceptance gate requiring every claim to beat its strongest baseline with a bootstrap confidence interval excluding it on independent units, the cross-morphology contrast pooled over depths 2 to 4 is 0.590 versus 0.018, with gap CI [+0.34, +0.81] over six arms, and a pre-registered depth 1 control gap of -0.002. A recurrent policy tuned per morphology to convergence reaches depth 1 parity, with success 0.606, yet still collapses at deeper tasks, with success 0.006, 0.000, and 0.000, so memory does not substitute for the symbolic state under behavior cloning. The factorization also matches the oracle-fed monolith's best success with 2.5 to 3 times less demonstration data, beats a language-token coding of the same information, with gap +0.109 and exact p = 0.031, runs zero-shot on 13 unseen arms, and composes independently trained skills with zero composite demonstrations.

Abstract: Motion forecasting models in the autonomous driving domain achieve high accuracy but cannot explain their predictions, creating a barrier to safety certification. This paper presents CogSig-Mamba, a model that produces causally validated temporal explanations alongside trajectory predictions. Inspired by hippocampal memory, the model follows a five-stage process: (1) synaptic tagging, where a top-k sparse gate selects which observation windows drove the prediction; (2) evidence encoding, which consolidates window content into memory representations; (3) reverse replay, which confirms causal faithfulness of tags through removal experiments; (4) spatial context, integrating road geometry for grounded predictions; and (5) constructive retrieval, which explains each predicted behavior via mode-specific attention to produce a complete Cognitive Signature. Evaluated on the Argoverse 2 dataset, CogSig-Mamba achieves minADE₆ = 0.908 m and minFDE₆ = 1.949 m with only 1.9M parameters. Removing tagged windows shifts predictions by 4.6 m on average, while removing untagged windows produces negligible impact (0.46 m), confirming causal faithfulness across all 24,988 validation scenarios. To the best of the authors’ knowledge, this is the first motion forecaster with verified temporal credit assignment, supporting the audit trails required by ISO 21448 for safety-critical deployment.

Abstract: Vision-and-Language Navigation (VLN) requires embodied agents to ground natural language instructions in visual perception and make navigation decisions in complex 3D environments, making it a central problem in embodied artificial intelligence. Since the introduction of the Room-to-Room (R2R) benchmark, VLN has made substantial progress. In recent years, as research settings have gradually expanded from closed and single indoor benchmark scenarios to open-world environments, the field has undergone a profound paradigm shift from passive instruction following on fixed benchmarks to autonomous cognitive navigation in open-world settings. However, existing surveys mainly organize prior work according to technical taxonomies, lacking a systematic characterization of this paradigm evolution. To address this gap, this survey proposes an evolution-centered unified analytical framework that reviews contemporary VLN research across four progressive layers: perception, cognition, learning, and generalization. It reveals the intrinsic connections and evolutionary logic among different technical lines, identifies key open challenges at each dimension, and outlines future research directions. This survey aims to provide VLN researchers with a clear panoramic view of capability evolution, while offering the broader embodied intelligence community a systematic roadmap from closed-benchmark evaluation toward trustworthy open-world deployment.

Abstract: The recognition of surgical instruments using Artificial Intelligence (AI) in Minimally Invasive Surgery (MIS) offers significant opportunities for data-driven improvements in surgical training and patient safety, with surgical instrument recognition being a critical component. MIS remains challenging due to complex intraoperative conditions that limit conventional real-time object detection AI algorithms. This paper optimises the state-of-the-art YOLOv8 object detection architecture for surgical instrument recognition and takes a novel approach to deal with imbalance of the dataset. A large-scale dataset of 25 surgical videos, consolidated from CholecTrack20, CholecT50, and Cholec80, underwent custom cleaning and strategic partitioning to address severe class imbalance. A systematic tournament identified YOLOv8l as the best-performing variant of the YOLOv8 versions, achieving Mean Average Precision (mAP)@0.5 of 64.4% on the test set. Despite hyperparameter tuning, the attempt led to overfitting, while the data-balancing strategy, despite a slight reduction in overall mAP@0.5 to 60.4%, the approach significantly improved per-class accuracy, notably doubling performance for the rarely used instruments such as Scissors and Clippers. This study establishes a new performance baseline for surgical instrument recognition using a carefully configured YOLOv8l model, underscoring that data imbalance, rather than architecture, is the primary limitation. Future progress for surgical instrument recognition will hinge on data-centric strategies for robust and clinically reliable models.

Abstract: Search and rescue (SAR) for disaster response involves quick and efficient exploration of large, uncertain, and dangerous spaces. In this paper, we introduce a swarm-drone SAR approach with a key innovation in the form of directional pheromone gradient observation, where each agent’s RL policy is informed not only by local pheromone levels but also by the directional gradients in victim likelihood and coverage in four spatial cones, along with neighbor density information. These attributes are based on four virtual pheromone layers, each evolving independently and representing coverage history, victim likelihood, environment risk, and communication quality. The system uses a centralized training with decentralized execution (CTDE) MARL approach. Experiments were conducted on a custom-designed 40×40 grid-world environment involving 10 drones and 20 victims whose locations are unknown to all agents at episode start, with 180 static obstacles and 50 static hazard zones, over 5,000 training episodes and 30 independent evaluation runs. The hybrid agent achieved 98.9% area coverage and 93.3% victim detection, exceeding the RL-only baseline by 17.1 and 21.6 percentage points, respectively, across five independent training seeds (pooled n=150 evaluation runs). Welch’s t-test confirmed statistically significant improvements over RL-only for both area coverage (t=18.88, df=168, p<0.001, Cohen’s d=2.18) and victim detection (t=16.49, df=218, p<0.001, Cohen’s d=1.90). Ablation confirms that excluding directional gradient features reduces coverage and victim detection by 16.7 and 21.6 percentage points, respectively, identifying them as the dominant contributors to hybrid performance.

Abstract: World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large video generation models, and a parallel line relies on language or vision-language backbones without a video-generation core. This rapid expansion has blurred the boundary among broad world models, video generation models, action-grounded video world models, Vision-Language-Action policies, and WAMs. This survey gives the field a common account. It first clarifies these boundaries, then organizes existing works through two complementary views. The first view asks what each method is required to generate, spanning rendered futures, latent futures, and video-generation-free action reasoning. The second view decomposes each method by predictive substrate, backbone, action coupling, and deployment regime. This anatomy supports a unified discussion of interactability, causality, persistence, physical plausibility, and generalization, followed by data, evaluation, and open challenges. Across these axes, a consistent design pattern emerges: WAMs are not simply video generators with action heads, but predictive-action methods whose design choices trade representational richness against compute, memory, latency, and action-label cost. The field is moving toward methods that generate less of the future while preserving what control requires. The survey homepage is available at https://world-action-models.github.io/.

Abstract: Fouling on ship hulls increases hydrodynamic drag, fuel consumption, and emissions. This, in turn, necessitates the development of efficient methods for side cleaning and inspection. This work focuses on the application of image-based classification to assess the cleanliness of the surface of the hull in robotic cleaning systems, with respect to the ISO 8501-4 standard. Due to limited data availability, transfer learning techniques using pre-trained convolutional neural networks (ResNet50, EfficientNetB0 and MobileNetV2) were used. Both end-to-end models and hybrid approaches that combine deep feature extraction with XGBoost classification were evaluated. Experiments were carried out on binary classification (cleaned vs. uncleaned surfaces) and multi-class classification of cleanliness levels (WA1, WA2, WA2.5). The results show that transfer learning enables effective recognition of cleaning status, achieving high performance for binary classification despite a small dataset. However, multiclass classification remains challenging due to subtle differences between classes and data limitations. The proposed approach supports automated visual inspection of underwater robotic platforms and represents a step toward objective standards-based assessment of hull cleaning processes.

Abstract: Cognitive Robotics seeks to understand and model cognition through embodied artificial agents, guided by the principles of embodied cognition theories. In this framework, cognition emerges from the dynamic coupling between the body and the environment, and is fundamentally rooted in sensorimotor interaction rather than abstract symbolic processing. This review integrates advances in CR, considering its bio-inspired foundations, including predictive mechanisms and intrinsic motivation, which are complementary principles for developmental learning. Emerging directions in CR are examined to clarify their implications for the field, highlighting their contributions and identifying open challenges. In this context, foundation models, such as Vision–Language–Action models, are reframed as structured starting conditions based on perceptual and motor priors to bypass learning low-level control from scratch, focusing instead on learning an internal model together with object-based semantics, and ultimately providing a sensorimotor base onto which linguistic symbols can be grounded. In parallel, the framework of Basal Cognition is introduced as a conceptual extension that reconceptualizes cognition as a multiscale, self-organizing adaptive process, suggesting that the central challenge for CR is to develop systems whose multiscale organization itself constitutes cognition and intelligence. These perspectives point toward novel lines of research and debate in CR. Foundation models can enable the study of increasingly complex, developmentally grounded learning, while Basal Cognition extends embodiment across scales, opening the door to artificial systems in which morphogenesis, adaptive behavior, and learning emerge from self-organizing multiscale dynamics.

Abstract: Decentralized multi-robot navigation in grid-based industrial environments, such as automated warehouses, must reach goals and avoid collisions without centralized control or direct robot-to-robot communication. We study a hybrid framework pairing an offline Rapidly-Exploring Random Tree (RRT) expert with a trained Behavior Cloning (BC) local policy and route reuse, evaluated in a fully reproducible, deterministic, seeded simulator. Our central result is that navigation quality is governed by how well the route library matches the deployment environment: a library generated for one map and deployed unchanged on another leaves robots blocked by the new obstacles, whereas an environment-adapted library transfers the learned skill and cuts collisions by 37-85% and task failures by 43-69% across fleets of two to ten robots (15 seeds; Mann-Whitney U, all p < 10^-5). An online RRT baseline attains a lower collision rate, but only through costly frequent replanning, so the environment-adapted hybrid recovers most of its navigation quality while reusing pre-computed routes. We further evaluate an optional, communication-free collision-history-sharing add-on; within the full framework its benefit is limited and layout-dependent, a nominally significant 13% collision reduction on one map that does not survive multiple-comparison correction.

Abstract: Vision-Language-Action (VLA) models are advancing faster than the field can evaluate them reliably. Researchers use different metrics and lab-specific protocols, making it hard to tell whether reported gains reflect genuine progress or favorable evaluation choices. We present the first comprehensive benchmark-centric survey of VLA evaluation, covering 582 papers from 2023 to May 2026. We argue that a benchmark number supports a progress claim only if four conditions hold: the benchmark discriminates among top models; metrics capture the claimed capability; the procedure permits cross-paper comparison; and the inference from benchmark to deployment is valid. Current practice fails at all four. Benchmark choice is concentrated and saturated, with leading models clustering near the ceiling of dominant simulation suites. Metric reporting is one-dimensional, dominated by task success rate while efficiency, safety, and trajectory consistency remain underreported. Real-world evaluation is fragmented, with no widely adopted standard and few trials per task. Simulation scores are widely treated as evidence of real-world capability, yet standard task-centric suites correlate only weakly with real-robot performance unless explicitly calibrated to the target physical setup. These failures reveal a fundamental evaluation bottleneck: VLA models are advancing faster than our ability to measure that advance.

Abstract: Background: Multi-Agent Path Finding (MAPF) has been widely studied in recent years. However, the computational cost of solving MAPF and MAPF for large agents (LA-MAPF) grows exponentially as the number of agents increases. This challenge is particularly severe for LA-MAPF, primarily due to the increased overhead of conflict detection between geometric agents. Objectives: To reduce the computational cost of solving MAPF and LA-MAPF problems, a general method is needed that can accelerate a variety of MAPF algorithms. Methods: We propose a framework that decomposes an LA-MAPFproblem into multiple subproblems, which are solved independently to reduce computational costs. The framework is general and compatible with various MAPF algorithms (e.g., CBS or LaCAM). The decomposition of an LA-MAPF problem is formulated as a combinatorial optimization problem and solved using neighborhood search. To handle unsolvable subproblems generated during decomposition, we introduce a solvability safeguard mechanism that merges subproblems until all are solvable. Results: Our experiments demonstrate the performance of the framework across various mapsasthenumberofagentsincreases, showing substantial acceleration of both MAPF and LA-MAPF methods. Specifically, after applying Break Loops, the average runtime of CBS and LA-CBS is reduced from 49.0 s to 6.8 s and from 54.0 s to 18.65 s, respectively; LaCAM and LA-LaCAM are reduced from 9.5 s to 7.0 s and from 52.9 s to 16.2 s, respectively. The success rate of CBS and LA-CBS increases from 0.27 to 0.98 and from 0.11 to 0.72, respectively; LaCAM and LA-LaCAM increase from 0.85 to 0.97 and from 0.10 to 0.77, respectively. Conclusions: Our results show that incorporating Break Loops into MAPF and LA-MAPF methods significantly reduces computational costs and improves success rates. These f indings demonstrate that solving MAPF problems can be accelerated by decomposing them into subproblems. To facilitate further research, we have made the source code for the framework publicly available at https://github.com/JoeYao-bit/LayeredMAPF/tree/main/algorithm/LA-MAPF.

Abstract: Vision–Language–Action (VLA) models trained on embodied demonstration data exhibit substantial performance degradation when transferred from simulation to reality. We argue that part of this gap is attributable to the implicit and incomplete encoding of geometric and bilateral symmetries in manipulation. We introduce SymBridge, a symmetry-aware framework whose acting group is the semidirect product G=Z₂⋉R³⋊SO(2)_z, in which the bilateral generator σ acts on the workspace subgroup by outer automorphism; cross-modal alignment is treated as a soft regulariser rather than as a subgroup. The framework couples a head-mounted display (HMD) teleoperation system based on the Meta Quest 3 and dual Franka Panda arms with a decoder-level Z₂-equivariant action head (full-policy bilateral equivariance is empirically achieved through L_sym, not architecturally guaranteed), an augmentation-based soft equivariance for the workspace subgroup, and a contrastive sim–real alignment objective. We collected 12,400 bimanual demonstrations spanning 28 tabletop tasks. Under controlled-variable ablations, SymBridge raises the average sim-to-real success rate from 47.3% (OpenVLA) to 78.9% on 12 unseen real-world tasks, outperforms strong equivariant baselines (EquiBot, EquiAct) by 14–17 percentage points, reduces the encoder-level sim–real Wasserstein-2 distance by 41%, and lowers the trained-axes equivariance error from 0.184 to 0.054 rad. Bilateral mirror augmentation alone contributes +9.1 percentage points on bimanual tasks. Symmetry violation is, in our diagnostic, a strong and actionable predictor of baseline failure, and symmetry-aware training substantially reduces the observed gap.

Abstract: Reliable localization of interaction-feasible branch regions is a critical prerequisite for autonomous UAV(Unmanned Aerial Vehicle) interaction in natural environments. However, natural tree branches exhibit slender geometries, irregular topologies, frequent occlusions, and unstable bifurcation structures, thus rendering it difficult to extract physically reliable grasp candidates under the limited computational resources of onboard platforms. Hence, we propose a real-time branch-grasp localization framework that integrates semantic perception with topology-aware geometric reasoning. For perception, we introduce a strip-swift pyramid pooling module to enhance the elongated structure representation through progressive pooling and strip-based directional context aggregation. To further improve the deployment efficiency and boundary quality, a reparameterized golden cudgel block and a boundary-optimization module are incorporated into the lightweight segmentation architecture. Based on predicted masks, we develop a topology-guided grasp-localization pipeline. Skeleton-based structural analysis is first performed to remove unstable regions such as branch junctions and overlapping structures. Subsequently, directional kernels are applied to extract geometrically consistent branch segments aligned with feasible interaction orientations. Finally, temporal stabilization and geometric constraints are introduced to suppress localization jitter caused by UAV motion. Experimental results show that the proposed method achieves a mean intersection over union of 89.96% on the Drone-Branch dataset. When deployed on the NVIDIA Jetson Orin Nano with TensorRT acceleration, the system achieves a stable latency of 13.9 ms, thus demonstrating its effectiveness and real-time suitability for onboard UAV branch interaction and grasp-candidate localization.

Abstract: Rigid 2D-3D image registration plays a critical role in modern image-guided interventions by enabling the alignment of intraoperative X-ray images with preoperative volumetric data such as computed tomography (CT). Accurate 2D-3D registration allows clinicians to localize anatomical structures in three-dimensional space while relying on fast and low-dose intraoperative imaging, which is essential for applications including orthopedic surgery, spine navigation, radiation therapy, and interventional radiology. Despite significant progress over the past two decades, achieving robust and accurate registration remains challenging due to factors such as limited imaging viewpoints, occlusions, imaging noise, and the large search space of rigid transformations. This paper provides a comprehensive survey of rigid 2D-3D registration methods with a particular focus on X-ray-to-CT alignment. We first introduce the mathematical formulation of the registration problem and present a taxonomy of existing approaches. We then review the key technical components underlying modern registration systems. In addition, we summarize commonly used datasets and evaluation protocols, discussing widely adopted metrics such as target registration error (TRE), pose error, and reprojection error. The survey also highlights representative clinical applications and analyzes the practical challenges that remain in real-world deployment, including robustness to imaging artifacts, variations in imaging dose, and real-time computational constraints. Finally, we discuss emerging research directions, such as differentiable rendering, deep learning based pose estimation, and multi-view registration frameworks, which are expected to further improve the accuracy, robustness, and clinical applicability of 2D-3D registration methods.

Abstract: Micro-ROS is a lightweight robot operating system for embedded devices with resource-constrained real-time features. Its communication mechanism, based on the XRCE-DDS protocol, facilitates data exchange in constrained environments. To ensure the safety and reliability of message transmission in Micro-ROS, this paper presents an integrated approach that combines simulation and runtime verification. A formal model of XRCE-DDS is constructed using timed automata, while key properties derived from the protocol are expressed in constrained Signal Temporal Logic (STLlb=0). The model is implemented and simulated via Simulink/Stateflow. Furthermore, the key properties are verified with the runtime verification method using the Logical and Temporal Assessments tool in the Test Manager of Simulink Test. Through integrating simulation with runtime verification, this work effectively improves the safety assurance of the Micro-ROS communication mechanisms.