Search Results (166)

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

Navigating hilly orchards is challenging for autonomous agricultural vehicles due to the rugged terrain and dense canopy cover. Standard environmental modeling techniques are widely used, yet they often overlook how elevation uncertainty propagates during Digital Elevation Model (DEM) reconstruction. This oversight can directly affect terrain risk assessments and navigation planning. From an error-propagation perspective, this review examines how uncertainties originating from RTK-GNSS, LiDAR, and computer vision propagate through DEM reconstruction, terrain-feature extraction, cost map construction, and path planning. We further analyze how DEM elevation errors and vertical inaccuracies affect slope estimation, roughness representation, traversability assessment, vehicle stability, and navigation safety. Finally, we highlight practical bottlenecks in hilly orchard scenarios and suggest several research priorities, including multimodal fusion, uncertainty-aware modeling, lifelong map updating, and learning-based traversability assessment. 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

Benthic AUVs (underwater quadruped robots) merge the cruising efficiency of submersibles with the bottom-crawling stability of legged robots for unstructured deep-sea exploration. However, the deliberate separation of the center of gravity and buoyancy—essential for static stability—generates a significant righting moment. When climbing steep slopes, this moment resists hull alignment. If the slope exceeds the robot’s maximum hydrostatic pitch limit, conventional inverse kinematics algorithms fail: the hind legs lose ground contact and propulsion is lost. To overcome this, this paper proposes a framework integrating optimal force distribution, adaptive trajectory probing, and admittance control. An analytical multi-point moment balance model derives the terrain-adaptive pitch boundaries. A Quadratic Program (QP) then distributes contact forces, tasking front legs with stabilizing the righting moment while hind legs provide thrust. During the swing phase, adaptive Bezier sequences prevent anterior slope collisions and ensure posterior ground contact. Furthermore, a Cartesian admittance controller provides active compliance to manage the nonlinear friction of dynamic waterproof seals. Validated via a high-fidelity physics-based simulation model calibrated against physical pool trials, the robot achieved robust traversal of $15°$ and $33°$ steep slopes. Statistical robustness is substantiated via a 30-trial Monte Carlo study, where postural stability remained remarkably consistent with a mean Pitch RMSE of $2.88°$ across a $\pm 10\%$ parameter uncertainty envelope. Compared to traditional baseline algorithms, the proposed method successfully suppressed torque chattering by $54.1\%$ in the high-frequency band (2–$50\mathrm{Hz}$) and improved energetic efficiency by up to $43\%$ on steep gradients. These findings offer a validated control architecture for heavy-duty deep-sea platforms navigating complex benthic topographies. Full article

Quadrupedal wheel-legged robots possess exceptional mobility in complex terrains, but their robust locomotion control is severely hindered by the difficulty of accurate state estimation without external sensors. Existing reinforcement learning methods relying on two-stage imitation often suffer from representation collapse and information loss during sim-to-real transfer. To address these challenges, this paper proposes a novel end-to-end reinforcement learning framework for implicit state estimation, incorporating terrain and external force features. Inspired by internal model control, the proposed method leverages a history of purely proprioceptive observations to extract explicit kinematic responses, as well as implicit environmental and external force representations via prototypical contrastive learning, completely circumventing explicit terrain regression and the need for physical force sensors. Furthermore, a tailored composite reward function and a progressive curriculum training strategy with large-scale domain randomization are integrated to ensure dynamic stability and hardware safety. Extensive cross-simulator validations and real-world deployments demonstrate that the approach achieves highly agile and robust locomotion, including adaptive traversal over diverse terrains. Experiments show that the method significantly enhances robustness under external disturbances, notably reducing the lateral linear velocity tracking error from 0.2421 m/s to 0.1319 m/s. The proposed method realizes zero-shot sim-to-real transfer with superior sample efficiency, providing a reliable and universal control paradigm for wheel-legged robots in unstructured environments. Full article

Multi-unmanned aerial vehicle (UAV) platforms integrate radio-frequency (RF) sensing, datalinks, and onboard embedded compute; adversarial electronic warfare (EW) degrades these subsystems through jamming and forces decentralized control policies to act on fragmented observations—a setting aligned with intelligent electronic systems and autonomous robotics in contested spectrum. Cooperative swarms then face two compounding failure modes: loss of coherent situational awareness, and reward-driven passive survival that suppresses mission completion. Memory-based multi-agent reinforcement learning (MARL) partially addresses the first but tends to reinforce the second; dense intent shaping addresses the second but becomes unreliable when observations are incomplete. We propose CIDA (Cognitive–Intent Dual-Stream Architecture), a reinforcement learning framework that decouples belief reconstruction from tactical intent at the representation level while coupling them through a unified actor–critic update. The cognitive stream encodes a 64-step observation history with a pre-normalized Transformer to reconstruct threat belief; the intent stream supplies a hierarchical potential field (reconnaissance, threat-weighted engagement, and approach incentives). A steady-state training mechanism (dynamic reward scaling and adaptive gradient clipping) stabilizes Transformer-based on-policy learning under non-stationary multi-agent dynamics. In a complex terrain scenario with SAM, AAA, and jammer assets, CIDA reaches 96.15% task success versus 12.21% (memoryless PPO) and 25.28% (MAPPO+RNN), with ablations showing nonlinear coupling and emergent tactics such as jammer bypass and weak-sector traversal. Results are robust to a four-fold sweep of the intent-shaping weight (above 90% success). Full article

Multi-UAV cooperative search is important for applications such as target reconnaissance, environmental monitoring, and emergency response. In practice, communication is often spatially heterogeneous due to terrain occlusion and environmental interference, which may delay information sharing and weaken coordination efficiency when UAVs traverse communication-blocked areas. To address this issue, we propose an Age of Information (AoI)- and Dempster–Shafer (DS)-enhanced cooperative search framework for multi-UAV systems under spatially structured communication constraints. Specifically, a DS belief map is introduced to fuse uncertain observations, while AoI is used to characterize the freshness of delayed information. An AoI-aware update mechanism further integrates buffered observations into the global belief map after communication recovery. The search process is then formulated as a communication-aware multi-agent sequential decision-making problem and solved using reinforcement learning. To demonstrate the generality of the proposed framework, we instantiate it with Proximal Policy Optimization (PPO), Multi-Agent Proximal Policy Optimization (MAPPO), and Q-value Mixing Network (QMIX). Experimental results show that the proposed framework consistently outperforms the baseline methods under heterogeneous environments and different communication conditions. Among all variants, AoI-DS-MAPPO achieves the best overall performance, improving average reward, success rate, and the number of detected targets by 26.13%, 24.32%, and 3.65%, respectively, while reducing episode length by 31.96% relative to the strongest baseline. Full article

Rapid and accurate calculation of lightning-induced electric fields in complex terrain is essential for lightning protection and electromagnetic compatibility analysis. Although conventional full-wave numerical methods such as the finite element method can achieve high-fidelity results, they are computationally expensive and inefficient for large-scale or repetitive engineering analysis. To enable efficient and reliable computation of lightning-induced electrostatic fields over complex terrain, this paper proposes a fast computational framework that integrates multi-level conformal mapping with a multi-objective optimization strategy based on the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). In the proposed method, irregular terrain boundaries are transformed into analytically tractable domains using multi-level conformal mapping, while the critical mapping parameter is reformulated as a dual-objective optimization problem that simultaneously minimizes the maximum local error and the mean global error. Unlike traditional approaches that rely on empirical tuning or exhaustive traversal of mapping parameters, the proposed framework establishes a closed-loop adaptive optimization process that generates a Pareto-optimal solution set, enabling flexible trade-off selection according to practical accuracy requirements. The method is validated against high-fidelity finite element simulations for representative terrain profiles. The results demonstrate that the proposed approach achieves comparable maximum-error performance while reducing mean error and significantly improving parameter-optimization efficiency relative to exhaustive search methods. The proposed framework provides an adaptive and efficient computational solution for preliminary assessment of lightning-induced electric fields in complex terrain environments, and lays a foundation for future extensions toward more realistic multi-dimensional and transient analyses. The improvements in computational accuracy and efficiency offer significant practical value for rapid lightning protection assessment in large-scale complex terrain engineering, enabling parametric analysis and scheme comparison during the preliminary engineering design stage with sufficient reliability. Full article

Autonomous mobile robots operating in outdoor environments must have an understanding of the surrounding terrain geometry to ensure efficient and safe navigation. This article presents a DEM-based intelligent traversability mapping framework to transform open-source geospatial data into slope-aware cost maps for multirobot autonomous navigation within the ROS2 framework. The proposed cv_gdal algorithm automatically processes GeoTIFF elevation data using adaptive slope thresholding based on each robot’s physical capabilities, generating ROS-compatible cell occupancy maps. Six regions of Spain were used to evaluate terrain representation accuracy and navigation performance in kilometer-scale DEMS. This framework enables autonomous perception-to-planning pipelines and supports the deployment of multirobot systems for search and rescue (SAR) tasks. By bridging geospatial analytics with robotic perception and adaptive decision-making, this work contributes to the development of intelligent, self-configuring robotic systems capable of operating safely in complex outdoor environments. Full article

To address the limitation of wheeled mobile robots in traversing unstructured terrain, this paper proposes an Active–Passive Hybrid Obstacle-Crossing Wheel (APHOCW). The mechanism integrates an active angle-adjustment mechanism and a lever-assist mechanism. While maintaining low system complexity and high reliability, it utilizes periodically telescoping assist levers that rotate with the wheel to overcome obstacles. By actively adjusting the eccentric angle, the trajectory of the assist levers can be modified to optimize the crossing posture. Through geometric and quasi-static mechanical modeling, dynamic simulation, and prototype experiments, this study systematically validated the robot’s obstacle-crossing capability and continuous step-climbing performance under different eccentric angles. Simulation and experimental results demonstrate that in the lever-assisted obstacle-crossing mode, the robot can stably overcome obstacles with a height up to 2.1 times its wheel radius and accomplish continuous step ascent. A smaller eccentric angle helps increase the maximum obstacle-crossing height, while a larger eccentric angle exhibits superior energy efficiency under sufficient ground-friction conditions. Full article

Autonomous mobile robots require robust traversability perception to navigate safely in diverse outdoor environments. However, traditional deep learning approaches are data-hungry, requiring large-scale manual annotations, and struggle to adapt quickly to unseen environments. This paper introduces TARTS (Training-free Adaptive Reference-guided Traversability Segmentation), a novel framework combining one-shot prototype initialization with trajectory-guided online adaptation for terrain segmentation. Using a single reference image of desired traversable terrain, TARTS establishes an initial prototype from pre-trained DINO Vision Transformer (ViT) features. The system performs segmentation through superpixel-based feature aggregation and valley-emphasis Otsu thresholding while continuously refining the prototype via Exponential Moving Average (EMA) updates driven by automated footprint supervision from the robot’s traversed trajectory. Extensive experiments on our introduced Reference-guided Traversability Segmentation Dataset (RTSD) and the challenging Off-Road Freespace Detection (ORFD) benchmark demonstrate strong performance, achieving 94.5% IoU on RTSD and 94.1% IoU on ORFD, outperforming state-of-the-art supervised methods that require multi-modal inputs and dedicated training. The framework maintains efficient performance (17–24 FPS) on embedded platforms, enabling practical deployment with only a reference image as initialization. Full article

This paper presents a comprehensive review of quadruped robots in the construction industry, focusing on their applications, technological capabilities, and integration with digital construction workflows. Quadruped robots have emerged as promising mobile platforms due to their ability to traverse uneven terrain, operate autonomously, and support multimodal sensing, enabling tasks such as site inspection, 3D reality capture, safety monitoring, logistics support, and integration with Building Information Modeling (BIM) and digital-twin systems. Despite these advantages, real-world deployment remains constrained by limitations in battery endurance, payload capacity, communication reliability, perception robustness, and system interoperability. This review synthesizes findings from 20 studies published between 2015 and 2025 and incorporates a quantitative bibliometric analysis using both SciVal and Scopus. While SciVal provides performance-based indicators and global research trends, Scopus offers complementary publication coverage, improving analytical reliability. Unlike general robotics surveys, this review adopts a construction-centric perspective by explicitly linking quadruped robot capabilities to construction engineering objectives under practical site conditions. The findings highlight current application domains, technological gaps, and adoption barriers, and outline future research directions to support the effective integration of quadruped robots into construction practice. This review provides actionable insights for researchers, engineers, and practitioners assessing the readiness and limitations of quadruped robots in construction environments. Full article

In recent years, many countries have increased their investment in the field of humanoid robots, promoting significant technological development. This study aims to enable humanoid robots to better adapt to various complex environments, enhancing the robustness of their motion systems and the generalization ability of their motion strategies. Using reinforcement learning algorithms, training on varied terrain is a critical factor for developing adaptable humanoid robots. This paper takes the humanoid robot G1 as the research platform. First, it completes the training, transfer verification, and real-machine deployment of a flat-ground walking model. Then, using fuzzy logic control and a phased training strategy, walking models for ascending/descending stairs and traversing slopes are trained. By systematically varying the stair height and slope gradient, the convergence of the reward function and the task completion success rate are analyzed. Furthermore, the dynamic stability of the robot on complex terrains is validated through qualitative kinematic analysis. The research concludes that as the single-step height and slope gradient increase, the reward value initially rises with more iterations but converges more slowly and at a lower final value. Statistical analysis shows that the success rates of phased training for stair and slope terrains are higher than 86% and 92%, respectively. Full article

Ground vehicles navigating uneven terrain must simultaneously guarantee motion safety and efficiency. Safety requires that the planned waypoints lie in highly traversable terrain, while ensuring vehicle reachability to these waypoints, which must be kinematically feasible. Efficiency demands fewer detours and smoother paths that avoid excessive vehicle acceleration and steering. However, existing path planning research for uneven terrain fails to comprehensively integrate vehicle kinematic constraints, terrain factors, path smoothness, rollover risk, and total path length. To address this problem, this paper proposes a novel navigation framework. It first integrates terrain slope, flatness, elevation variation, and sparsity to generate a 2D global terrain traversability cost map. Subsequently, a three-phase path planning algorithm integrates A*, guided Rapidly-exploring Random Tree (RRT), and our proposed Kinematic and Terrain-Aware Probabilistic Roadmap (KT-PRM) local re-planning algorithm, which jointly considers multiple factors including ground vehicle kinematic constraints, terrain factors, path smoothness, rollover risk, and path length. This three-phase combination delivers safe, smooth, and short global paths over uneven terrain within a relatively short planning time. Finally, Nonlinear Model Predictive Control (NMPC) is employed for path tracking in the framework. Experiments were conducted in both simulated and real-world uneven terrain environments. The results demonstrated that the three-phase path planning algorithm integrated with our proposed KT-PRM algorithm achieves comprehensive performance in generating safer, smoother, and shorter paths. Our proposed navigation framework achieves safer and more efficient navigation compared with existing navigation frameworks. Full article

In contrast to structured urban settings, road networks in post-disaster or unstructured wildland environments are often incomplete or compromised. Navigation in these contexts requires navigating complex terrains and mitigating potential hazards that impede unmanned ground vehicles (UGVs). While high-mobility off-road vehicles are specifically designed to traverse challenging features like ditches and steep slopes, traditional path planning algorithms often fail to exploit these capabilities. These algorithms typically suffer from a binary focus, either relying strictly on road networks or ignoring them altogether, thereby neglecting the synergy between infrastructure and vehicle mobility. This chapter introduces a global path planning method based on traversability analysis and terrain matching to bridge this gap. The methodology incorporates a grid-based traversability evaluation, a road network expansion algorithm for densifying critical segments, and a unified planning strategy. By correlating terrain characteristics with vehicle mobility limits and optimizing the road network density, the proposed framework achieves an integrated on-road and off-road planning solution that maximizes the operational efficiency of high-mobility vehicles in degraded environments. Full article