Search Results (521)

Autonomous navigation in unstructured off-road environments presents fundamental challenges due to terrain heterogeneity, the absence of structured road markings, and the necessity for real-time traversability reasoning from raw sensory observations. We present TerrainFormer, a hierarchical framework that integrates a world model for terrain dynamics prediction with a temporal decision transformer for action selection. Our methodology employs a two-phase training paradigm: (1) self-supervised world model pretraining on LiDAR point clouds to learn terrain representations encompassing traversability, elevation, and semantic segmentation; (2) behavioral cloning of the decision transformer conditioned on frozen world model features with temporally derived goal directions. The world model processes raw 3D LiDAR point clouds through a PointPillars encoder for real-time bird’s-eye-view (BEV) projection, followed by a Vision Transformer backbone that produces latent terrain representations. A principal contribution is our cross-dataset generalization paradigm: the world model is trained on separate datasets while the decision transformer is trained on separate sequences, ensuring zero data overlap between training phases. We introduce automatic goal direction computation from vehicle pose trajectories, enabling the model to learn directionally conditioned navigation policies. To address the class imbalance inherent in off-road driving data, we employ focal loss with inverse-frequency class weighting and action-chunk supervision. Experimental evaluation on the RELLIS-3D dataset achieves 87.31% test accuracy with 0.7948 macro F1 across all 12 action classes. The world model’s predicted future frames produce only a 0.79% accuracy drop versus ground-truth observations, with 98.82% action agreement, demonstrating effective cross-dataset generalization for real-time off-road navigation. Full article

Perennial crop systems (e.g., orchards) require frequent spraying with plant protection products. Equipment plays a crucial role in assessing energy efficiency, productivity, economic performance, and the environmental impact of orchard production. In recent years some farmers have replaced conventional tractor-mounted air-blast sprayers (TMABS) and switched to unmanned ground vehicles (UGVs) or unmanned aerial vehicles (UAVs). However, there has been a lack of comparative studies on the energy and environmental assessment of these systems. This study aimed to evaluate the overall viability of different orchard spraying technologies in terms of energy efficiency, economic costs, and environmental impact. A life cycle assessment (LCA) of five sprayers was performed: a TMABS, a UGV, and three UAVs. The CML-IA methodology and SimaPro 9.5 software with the Ecoinvent v3 database were used to determine the environmental impact of the compared machines. Energy efficiency was calculated using fuel consumption data, human labor energy, and the energy embodied in the machinery. Economic viability was evaluated through capital depreciation, labor, energy consumption, consumable and maintenance cost per hectare calculation models. The results indicate that UAV systems, as compared to TMABS, can significantly reduce operational energy consumption, water use, and environmental impacts. The GWP of UAV systems was about 67% lower compared to the TMABS, while the UGV, due to lower performance efficiency, exhibited a 4% larger GWP (kg CO_2eq ha⁻¹). The findings of this study highlight that UAVs can produce the optimal results in comparison to other application methods. Full article

A nonlinear backstepping control framework is developed for autonomous landing of a quadrotor on a wave-excited marine platform. This study addresses the underactuated nature of the aerial vehicle and the strong coupling between translational and rotational dynamics, ensuring stable trajectory tracking under sea-induced disturbances. Reference trajectories are generated through physically grounded Pierson–Moskowitz (PM) and modified Pierson–Moskowitz (MPM) wave spectra, enabling realistic modeling of vertical heave motion, while horizontal position and yaw are defined through harmonic components adapted to the sea-state regime. The controller is designed through a seven-step recursive backstepping procedure, with Lyapunov functions guaranteeing asymptotic stability of the tracking errors for the regulated outputs. A modular MATLAB simulation platform is implemented, integrating the full six-DOF quadrotor dynamics, the control algorithm, and spectral reference generation. Numerical simulations demonstrate that the Lyapunov function derivatives remain negative over the entire simulation horizon, confirming asymptotic convergence. Comparative results with a tuned PID (proportional integral derivative) controller indicate superior tracking performance and damping and reduced amplitude and phase errors for the backstepping approach, especially under MPM-based trajectories representing rough sea states. The proposed framework establishes a reliable basis for adaptive extensions and future hardware-in-the-loop validation of autonomous landing on moving marine platforms. Full article

During the early stages of autonomous vehicle (AV) adoption, traditional human-driven vehicles (HVs) and AVs will share urban roads—potentially diminishing the capacity benefits of AVs; thus, dedicated infrastructure strategies, such as AV-exclusive lanes and AV/Toll (AVT) lanes, have been proposed in the literature. While these approaches enhance overall travel efficiency in mixed traffic networks, they often neglect social equity concerns. In particular, the benefits of dedicated infrastructure are largely felt by AV users, while HV users experience a disproportionate increase in equilibrium travel time, negatively impacting social equity. This study optimizes AVT lane toll rates to balance efficiency and equity, ensuring a fair distribution of transportation impacts across user groups. New measurement formulas are introduced to quantify spatial and social equity based on disparities in generalized equilibrium travel costs across different origin–destination pairs and travel modes after an AVT tolling scheme. An equitable AVT tolling model, grounded in fuzzy utility theory, is developed, and a numerical example demonstrates its effectiveness in addressing spatial and social equity concerns in AVT lane tolling contexts. Full article

Autonomous navigation on unknown uneven terrain remains a critical challenge for unmanned ground vehicle (UGV) deployed in unstructured environments such as disaster relief, wilderness exploration, and off-road logistics. Existing motion planning methods for such environments suffer from three key limitations: under-utilization of the solution space due to discretized terrain assessment, difficulty in transforming complex terrain safety constraints into optimization-compatible forms, and the inherent trade-off between environmental modeling accuracy and real-time performance. This paper presents a hierarchical motion planning framework that enables safe and fast navigation of UGV on unknown uneven terrain. We first construct a traversability map based on terrain slope, roughness, and sparsity extracted from ground point cloud clusters. Non-traversable points are then transformed via spherical inversion and inverse mapping to generate terrain safety corridors composed of a series of convex polygons. The geometric containment relationship between the vehicle’s convex hull and the corridor is reformulated as continuously differentiable Control Barrier Function (CBF) constraints to ensure driving safety. The front-end employs a kinodynamic Hybrid A* algorithm with a traversability-aware node pruning strategy, while the back-end trajectory optimization embeds the CBF constraints as hard constraints within the optimization loop to guarantee forward invariance of the safety set under the linearized dynamics. The proposed framework achieves full-shape collision avoidance without sacrificing the solution space, while maintaining real-time performance for autonomous navigation on complex terrain. Full article

As the core technology for realizing autonomous navigation of unmanned ground vehicles, the path planning algorithm directly determines the reliability and stability of navigation tasks in complex dynamic environments. With the expanding range of application scenarios, traditional path planning approaches have become increasingly inadequate in terms of real-time performance, dynamic obstacle avoidance, and multi-objective optimization. The recent rise in AI-based methods has provided new opportunities for this field. This paper systematically analyzes the latest research progress in this area. By reviewing and analyzing the highly recognized literature in recent years, we classify mainstream path planning and related algorithms into six types: graph-search-based, sampling-based, local optimization-based, meta-heuristic optimization, AI-based, and optimal control methods. The core improvement trends, advantages, and inherent limitations of each algorithm type are deeply analyzed. Through bibliometric analysis, we identify major gaps in current research, including over-reliance on simulation methods, overly restrictive environmental assumptions, and insufficient handling of multiple objectives. Finally, we point out the critical gap between simulation environments and real-world deployment and advocate the use of hybrid algorithms to address the deficiencies of single algorithms, along with effective validation in real environments. This direction is crucial for promoting the broader practical application of unmanned ground vehicle technology. Full article

Developing and evaluating visual perception systems for autonomous vehicles requires data across diverse and adverse driving conditions, yet collecting and annotating such real-world data is costly and often impractical. To address this challenge, we propose a modular, scenario-driven framework for generating synthetic datasets tailored to the evaluation of visual perception functions. The framework aligns with the operational boundaries and detection–response requirements of automated driving functions and comprises three stages: (1) configuring use-case-driven scenarios, (2) generating sensor data and ground truth via simulation, and (3) post-processing to ensure dataset usability. Designed to be generic and flexible, the framework is instantiated and demonstrated through its integration with specific platforms and tools, namely Pro-SiVIC and RTMaps. We evaluate the generated dataset from two perspectives, image fidelity and perception performance under synthetic weather conditions, in comparison to real-world conditions. Furthermore, we train multiple perception models under different learning paradigms, including baseline, transfer-learning, and mixed-training strategies, to examine the influence of synthetic data on robustness. Experimental results demonstrate not only the high quality of the generated data but also its effectiveness in evaluating visual perception functions, as well as its benefit to model robustness and generalization. Full article

Heterogeneous airground robotic systems, which integrate unmanned ground vehicles and unmanned aerial vehicles, have shown significant potential in complex autonomous missions. However, when deployed in urban canyons, dense high-rise buildings impose severe communication constraints on ground vehicles, necessitating the introduction of aerial vehicles as relays to maintain reliable connectivity. The resulting cooperative trajectory planning problem is challenging for three reasons. First, the kinematic and communication constraints are tightly coupled. Second, the optimization landscape is highly non-convex and non-differentiable. Third, the planner must balance topological exploration with real-time efficiency. To address these challenges, we propose a hierarchical cooperative trajectory planning framework for an air–ground robotic system. Specifically, in the upper layer, a heuristic-search-guided reinforcement learning mechanism is employed to narrow the search space and circumvent the sparse reward problem, rapidly generating an initial solution. Subsequently, the lower-layer planner utilizes an optimization-based solver, together with a corridor-based constraint formulation method, to refine the initial solution into a kinematically feasible cooperative trajectory. Ultimately, this strategy improves real-time efficiency while improving the quality of feasible cooperative trajectories. Extensive ablation studies and comparative experiments with representative baselines demonstrate that the proposed framework improves collision avoidance, communication reliability, trajectory smoothness, and computational efficiency in the tested urban canyon scenarios. Full article

Existing self-supervised methods have achieved significant success in ground-level autonomous driving scenarios, but applying them directly to Unmanned Aerial Vehicle (UAV) videos remains challenging. On the one hand, rapid pose changes in UAVs often lead to oblique-view imaging, making it difficult for conventional methods to handle the perspective distortion in oblique imagery. On the other hand, complex UAV viewpoints may cause depth blurring in low-texture regions. To address these challenges, we propose a lightweight self-supervised monocular depth estimation method for UAV scenarios. By utilizing a Dynamic Direction-Aware Module (DDaM), the network adaptively adjusts the sampling grid to correct distorted features during feature extraction, while enhancing its ability to capture features at different spatial locations. Furthermore, to mitigate the loss of spatial information caused by multiple downsampling operations, we integrate a Coordinate Attention Mechanism into the encoder. This mechanism captures features along two separate spatial axes, preserving the spatial coordinates of object boundaries. Our experiments demonstrate that the synergy between DDaM and the Coordinate Attention Mechanism enables the prediction of more accurate object boundaries and richer local details. To validate the effectiveness and practical applicability of the proposed method, we conduct experiments on both the MidAir synthetic dataset and the UAVid real-world dataset. The results show that, compared with current baseline methods, our approach maintains competitive performance while requiring the fewest parameters. Full article

Deep learning models are widely used in autonomous vehicle systems for perception, localization, and decision-making. However, their lack of transparency poses significant challenges in safety-critical environments. This systematic review presents a unified mathematical framework for explainable deep learning which integrates multimodal inputs, graph-theoretic road geometry, uncertainty modeling, and intrinsically interpretable representations. Road-structured priors that include lane topology and spatial constraints are incorporated into learning and optimization processes for ensuring model predictions and explanations to remain physically and semantically grounded. The review synthesizes methods across saliency-based, concept-based, causal, and intrinsic explainability, and extends them to vision-language models. This enables language-grounded, human-interpretable reasoning in autonomous vehicle systems. While vision-language models offer a new paradigm for semantic explainability, their limitations such as hallucinations, misgrounding, and reduced reliability under distribution shifts are also critically examined. Along with the role of road priors in improving alignment and robustness, another key contribution of this work is its quantitative evaluation metrics for road-aware explainability. These evaluation metrics link the explanations to spatial consistency, uncertainty alignment, and graph-structured reasoning. The overall framework connects latent representations, predictions, and explanations within a single formulation, enabling systematic comparison and analysis across models. Based on a PRISMA-guided review of 164 studies, this research identifies gaps in real-world reliability, temporal reasoning, and standardized evaluation, and outlines future directions including human-in-the-loop systems, regulatory readiness, and language-based auditing. Overall, this study advances a mathematically grounded and road-aware perspective on explainable vehicle AI which significantly bridges the gap between high-performance models and transparent, trustworthy autonomous systems. Full article

Autonomous ground vehicle navigation in dynamic real-world environments demands path planning systems that simultaneously accommodate real-time environmental hazards and diverse user-defined objectives requirements that classical algorithms, with their static, single-objective cost functions, cannot fulfil. This paper presents the Semantic Personalised Path Planning (SPPP) system, centred on a novel Semantic Personalised Cost (SPC) algorithm that augments the A* search framework with a dynamically computed personalised cost term. The SPC function integrates eight real-time semantic obstacle categories including traffic congestion, weather severity, road surface conditions, and construction activity with eight user-defined preference dimensions spanning safety, travel time, emergency response, comfort, and battery efficiency. An adaptive scaling mechanism amplifies obstacle penalties near the goal, and a gradient-based weight evolution rule refines preference weights iteratively over successive route segments. The user-defined preference activation directly personalises the routing objective to individual operational needs, with the gradient-based evolution further refining preference alignment over successive route segments. Experiments were conducted in two phases: 500 randomised obstacle configurations on a controlled $8\times 8$ grid, and a real 847-node road graph extracted from OpenStreetMap around SRM Institute of Science and Technology, Kattankulathur, representing a single 1.4 km urban corridor, with obstacle scores derived from live Mapbox Traffic and OpenWeatherMap application programming interface data. Under the full emergency preference scenario, SPPP achieves 94.3% obstacle avoidance versus 31.7% for the Euclidean distance threshold A* baseline, a difference statistically significant at $p < 0.001$ under the Wilcoxon signed-rank test with Cohen’s d ≈ 18.9. Real-world computation time of 1.91 ms on a standard laptop and 3.76 ms on a Raspberry Pi 4 confirms deployability on embedded autonomous vehicle hardware. Full article

This study provides a comparative performance evaluation of commercial Precise Point Positioning Real-Time Kinematic (PPP-RTK) and public Network RTK (NRTK) services for vehicle-based positioning in urban and suburban environments. Using low-cost u-blox ZED-F9 receivers, the research assesses the accuracy, availability, and robustness of the u-blox PointPerfect service against a regional NRTK network across diverse real-world scenarios, including high-speed highway conditions and signal-challenging urban corridors. The experimental framework utilizes a rigid-bar setup for high-precision ground-truth validation and incorporates an independent vertical accuracy assessment against a LiDAR-derived digital elevation model (DEM). The results demonstrate that all tested configurations achieve decimeter-level accuracy. Notably, the integration of PPP-RTK with an inertial measurement unit (IMU) delivers performance nearly equivalent to NRTK, effectively mitigating vertical biases and ensuring positioning continuity in GNSS-denied areas such as tunnels. These results confirm that low-cost GNSS solutions, when paired with modern augmentation services and IMU integration, can meet the stringent demands of mass-market applications like Cooperative Intelligent Transport Systems (C-ITS) and autonomous mobility. Full article

This paper presents a comprehensive review of recent works (2020–2026) on machine learning (ML) algorithms applied to autonomous platforms such as unmanned underwater vehicles (UUVs), unmanned surface vehicles (USVs), unmanned aerial vehicles (UAVs), and ground-based mobile robots. The review focuses on the following functional areas: environment perception, simultaneous localization and mapping (SLAM), collision avoidance and path planning, and motion control. Different ML methods are covered, including supervised, semi-supervised, and unsupervised learning, as well as reinforcement learning and deep reinforcement learning. The reviewed methods are analyzed with respect to their performance, robustness, and suitability for different operational environments, including underwater, surface, air, and land domains. Finally, the authors identify key challenges and outline promising future directions aimed at improving the safety, autonomy, and reliability of autonomous vehicles. Full article

Reliable altitude and vertical speed estimation are fundamental for unmanned aerial vehicle (UAV) autonomous flight, especially during low-altitude operations such as takeoff and landing. Barometric altimeters are widely used due to their low cost, high availability, and good long-term stability, providing smooth altitude trends over a wide operating range. However, barometric measurements are indirectly inferred from static pressure and are therefore sensitive to local airflow disturbances. In particular, rotor downwash and ground effect-induced pressure perturbations near the surface can introduce significant biases and short-term fluctuations in barometric altitude, which propagate into erroneous vertical speed estimates during critical flight phases. Time-of-flight (TOF) altimeters, such as radar or laser sensors, provide direct above-ground-level (AGL) measurements and are largely insensitive to ground effect-related pressure disturbances. Within their limited operational range, TOF altimeters typically offer higher accuracy and lower short-term noise compared with barometric altitude. Nevertheless, TOF sensors are characterized by a restricted valid measurement range and frequently exhibit non-ideal behaviors in real-world UAV operations, including out-of-range outputs, frozen measurements, and in-range biased readings. These anomalies violate the nominal sensor assumptions used in conventional Kalman filter-based fusion and can significantly degrade estimation performance if not properly handled. This paper proposes a hybrid Kalman–rule-based altitude estimation framework that fuses barometric and TOF altitude measurements to exploit their complementary characteristics while mitigating their respective limitations. A vertical dynamic state-space model is formulated to jointly estimate altitude, vertical velocity, accelerometer bias, and ground height offset. A rule-based anomaly detection and classification module is developed to identify multiple TOF altimeter failure modes observed in operational UAV flights. The detected anomaly states are incorporated into the Kalman filter to adaptively weight, accept, or reject TOF measurements, thereby improving robustness against sensor non-idealities. The proposed approach is validated using 39 real UAV flight logs covering diverse flight regimes, including low-altitude maneuvers, cruise, and autonomous landing. Experimental results show that the proposed framework provides more stable and robust altitude and vertical speed estimation under practical sensor anomaly conditions compared with conventional barometer-only and standard Kalman fusion configurations. These results demonstrate the practical effectiveness of the proposed method for fault-aware altitude estimation in UAV autonomous flight. Full article

Unmanned Aerial Vehicle (UAV), particularly rotary-wing platforms such as quadcopters and octocopters, has evolved from controlled remote sensing platforms into autonomous agents capable of active task execution. This evolution from collect-then-analyze workflows to closed-loop perception, reasoning, and action signifies a paradigm shift toward Embodied AI, unlocking opportunities for the low-altitude economy. However, current research on UAV Embodied AI (UAV-EAI) often implicitly frames the field as a direct extension of indoor robotics or autonomous driving, which overlooks the fundamental distinctions of aerial agents. To bridge this gap, we introduce a comparative framework contrasting UAV-EAI with Indoor-EAI and Autonomous Driving Embodied AI (AD-EAI). By systematically decomposing the domain into nine key dimensions, we (i) analyze core tasks such as perception, localization, and exploration; (ii) review enabling infrastructure, including simulators and datasets; and (iii) categorize modeling methods ranging from physics-centric control to cognition-centric models. Our analysis demonstrates that the convergence of 6-DoF motion space, kilometer-scale unstructured environments, and stringent on-device constraints establishes a research regime qualitatively different from ground-based agents. These factors significantly impede the migration of existing VLM/LLM-based embodied systems for UAVs. Finally, we summarize open challenges and outline promising directions for the next generation of UAV-EAI. Full article