Abstract

Abstract
Wheeled mobile robots are increasingly deployed in harsh environments where dense obstacles, traps, variable terrain, soil effects, tight energy budgets, and sensor noise often deem classical navigation stacks insufficient. This paper presents a PRISMA-guided systematic review of recent work on Deep Reinforcement Learning (DRL) for wheeled ground-robot navigation in harsh environments and organizes the field via a practical six-dimensional taxonomy: environmental challenges, navigation architecture, observation modality, action strategy, action space, and learning algorithm. The taxonomy is refined through an iterative, evidence-grounded coding process on the included studies, and applied under a transparent coding protocol to support reproducible categorization. Across the literature, DRL appears both as a planner module as well as end-to-end policy (behavior) implementer tool. Regarding observation, mapless navigation based on LiDAR or cameras are prevalent. Actions are predicted mostly one time step ahead and are continuous. Actor-critic methods are prevalent, notably PPO and SAC are the common DRL methods used. As for the evaluation methodology, it remains largely simulation-based, with only limited sim-to-real protocols. Building on these findings, we use the previously mentioned taxonomy to identify common design choices for navigation in harsh terrains, propose minimum reporting practices to enable reproducible comparison, and propose research directions including energy-aware learning, improved robustness to sensor degradation, all weather soil-vehicle interaction modeling, short-horizon look-ahead for stability and smoothness, standardized tasks and metrics. The proposed taxonomy and guidelines, as well as identified trends, intend to help researchers and practitioners select methods that best suits their own objectives and constraints, thus hopefully accelerating progress from promising simulation results to dependable, field-ready autonomy.

Abstract
This study aimed to identify how service operations managers perceive the effects of task duration variability and activity pooling on key performance indicators such as flow time, queue length, perceived service quality, and customer satisfaction. A scenario-based experiment was conducted with 229 professionals working in service operations in Brazil and Portugal. Participants evaluated fictional processes with varying levels of variability (low vs. high) and task allocation formats (specialized vs. pooled). All scenarios were validated through computer simulations prior to the experiment. The results reveal a gap between analytical models in the literature and managerial perceptions. While queuing theory associates increased variability with performance deterioration, respondents frequently attributed positive effects to higher variability and activity pooling, especially in relation to perceived quality. The study contributes by uncovering managerial interpretations that diverge from established operations management principles, suggesting the need for greater integration between analytical approaches and service-oriented perspectives. From a practical standpoint, the findings underscore the importance of strengthening managerial training in process analysis and promoting the use of computational tools as support for decision-making in complex service operations.

Abstract
We present a federated edge-intelligence framework for smart-mobility cybersecurity that integrates Edge AI, Federated Learning (FL), and blockchain anchoring, and we provide a runnable artifact for full reproducibility. Using a synthetic IDS-like workload with non-IID client splits, we benchmark centralised, edge-only, and FL (FedAvg) training while accounting for communication, a latency proxy, and a FLOPs-based energy index. FL maintained near-centralised accuracy (˜99.8%) and F1 (0.9932–0.9938), whereas edge-only degraded under client skew (˜85.3% accuracy; F1 ˜ 0). Training-time communication for FL was 98.96% lower than centralised at 5 clients/10 rounds (0.033 MB vs. 3.206 MB) and 97.99% lower at 10 clients/10 rounds (0.065 MB vs. 3.206 MB). The latency proxy grows linearly with FL rounds yet remains well below centralised inference (132 ms vs. 3,301 ms at 5 clients/10 rounds). Energy results follow expectations: edge-only lowest (0.000832), centralised mid (0.001040), and FL highest due to local training (0.001300–0.001560). Overall, the results quantify accuracy/communication/latency/energy trade-offs and show that federated-edge learning preserves accuracy under client heterogeneity while minimizing raw-data transfer; blockchain anchoring adds only a small, parameterized per-commit overhead. All configurations and logs are released to enable exact reproduction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
This study examines whether Parameter-Efficient Fine-Tuning (PEFT) of lightweight, free, and open-licensed Large Language Models (LLMs) can yield tutoring assistants for introductory circuit analysis methods, while fitting the students' needs. We analyzed 260 Electrical and Computer Engineering (ECE) exam responses to classify and quantify frequent students' mistakes when applying the Loop Current Method (LCM). Only 28.5% solved the target problem without error, and most difficulties were conceptual (e.g., miscounting the number of independent Kirchhoff's Voltage Law (KVL) equations). Driven by this taxonomy, we assembled official course materials and curated a bilingual (Portuguese-English) pedagogical dataset. Using GTP-4o for distillation, we generated question-answer (QA) pairs for fine-tuning smaller models (Meta Llama 3.2 1B and 3.1 8B), via Quantized Low-Rank Adaptation (QLoRA) on a single commodity GPU, with an end-to-end pipeline completing in under 7 min. A blind study involving 77 first-year ECE students evaluated responses to (never seen) questions from both our tuned models and GPT-4.5, rating correctness, clarity, educational value, task coverage, and style. The 8B model scored within one point (5-point Likert) of GPT-4.5 model and both 1B and 8B were consistently preferred over untuned baseline versions for clarity and task coverage. As a complementary cross-check, 12 higher education senior professors independently evaluated model responses, largely corroborating the student-based rankings. These results provide evidence that carefully curated documents introducing electrical circuit theory, combined with smaller models optimized with PEFT, namely QLoRA, can be used in the construction of a always-available tutoring application. The proposed system features modest cost, runs on consumer-grade hardware, and paves the way for deployable front-end applications that do not involve possibly expensive, resource-hungry, remote machines.

Abstract
This study proposes a two-stage Intrusion Detection System (IDS) for Controller Area Networks (CAN) that leverages protocol-specific timing characteristics. Modern vehicular networks are vulnerable to injection attacks due to the CAN protocol's lack of built-in authentication. Our methodology transforms raw CAN traffic into a structured feature space consisting of CAN IDs, message offsets, and inter-message intervals derived from the CAN Remote Frame request-response mechanism. The first stage applies unsupervised z-score statistical thresholding, requiring no labeled attack data. The second stage employs three independent binary Random Forest (RF) classifiers for precise characterization. Individual classifiers achieve F1-scores of 0.96 (Fuzzy), 0.77 (DoS), and 0.79 (Impersonation). In the integrated end-to-end pipeline, while the system effectively filters 97% of legitimate traffic, a performance stratification is observed: high detection is maintained for timing-disruptive attacks (Fuzzy), whereas timing-preserving attacks (DoS, Impersonation) exhibit lower recall due to the restrictive nature of the timing-only first-stage gating mechanism. Hardware profiling confirmed an inference latency of similar to 0.018 ms and footprint of 8.8-19.2 MB, offering a deployable, computationally efficient defense for legacy automotive environments.