Search Results (177)

The demand for large-scale, heavy-duty autonomous pavement-sweeping robots is rising due to urban growth, hygiene needs, and labor shortages. Ensuring their health and safe operation in dynamic outdoor environments is vital, as terrain unevenness and slope gradients can accelerate wear, increase maintenance costs, and pose safety risks. This study introduces an AI-driven condition monitoring (CM) framework designed to detect terrain unevenness and slope gradients in real time, distinguishing between safe and unsafe conditions. As system vibration levels and energy consumption vary with terrain unevenness and slope gradients, vibration and current data are collected for five CM classes identified: safe, moderately safe terrain, moderately safe slope, unsafe terrain, and unsafe slope. A simple-structured one-dimensional convolutional neural network (1D CNN) model is developed for fast and accurate prediction of the safe to unsafe classes for real-time application. An in-house developed large-scale autonomous pavement-sweeping robot, PANTHERA 2.0, is used for data collection and real-time experiments. The training dataset is generated by extracting representative vibration and heterogeneous slope data using three types of interoceptive sensors mounted in different zones of the robot. These sensors complement each other to enable accurate class prediction. The dataset includes angular velocity data from an IMU, vibration acceleration data from three vibration sensors, and current consumption data from three current sensors attached to the key motors. A CM-map framework is developed for real-time monitoring of the robot by fusing the predicted anomalous classes onto a 3D occupancy map of the workspace. The performance of the trained CM framework is evaluated through offline and real-time field trials using statistical measurement metrics, achieving an average class prediction accuracy of 92% and 90.8%, respectively. This demonstrates that the proposed CM framework enables maintenance teams to take timely and appropriate actions, including the adoption of suitable maintenance strategies. Full article

Autonomous exploration of autonomous vehicles in off-road environments remains challenging due to the adverse impact on exploration efficiency and safety caused by uneven terrain. In this paper, we propose a path planning framework for autonomous exploration to obtain feasible and smooth paths for autonomous vehicles in 3D off-road environments. In our framework, we design a target selection strategy based on 3D terrain traversability analysis, and the traversability is evaluated by integrating vehicle dynamics with geometric indicators of the terrain. This strategy detects the frontiers within 3D environments and utilizes the traversability cost of frontiers as the pivotal weight within the clustering process, ensuring the accessibility of candidate points. Additionally, we introduced a more precise approach to evaluate navigation costs in off-road terrain. To obtain a smooth local path, we generate a cluster of local paths based on the global path and evaluate the optimal local path through the traversability and smoothness of the path. The method is validated in simulations and real-world environments based on representative off-road scenarios. The results demonstrate that our method reduces the exploration time by up to 36.52% and ensures the safety of the vehicle while exploring unknown 3D off-road terrain compared with state-of-the-art methods. Full article

Unmanned Aerial Vehicles (UAVs) are increasingly used in the new generation of communication systems. They serve as access points, base stations, relays, and gateways to extend network coverage, enhance connectivity, or offer communications services in places lacking telecommunication infrastructure. However, optimizing UAV placement in three-dimensional (3D) environments with diverse user distributions and uneven terrain conditions is a crucial challenge. Therefore, this paper proposes a novel framework to minimize UAV transmission power while ensuring a guaranteed data rate in realistic and complex scenarios. To this end, using the particle swarm optimization evolution (PSO-E) algorithm, this paper analyzes the impact of user-truncated distribution models for suburban, urban and dense urban environments. Extensive simulations demonstrate that dense urban environments demand higher power than suburban and urban environments, with uniform user distributions requiring the most power in all scenarios. Conversely, Gaussian and exponential distributions exhibit lower power requirements, particularly in scenarios with concentrated user hotspots. The proposed model provides insight into achieving efficient network deployment and power optimization, offering practical solutions for future communication networks in complex 3D scenarios. Full article

The scenario adaptability of agricultural machinery chassis in hilly and mountainous regions has become a key area of innovation in modern agricultural equipment development in China. Due to the fragmented nature of farmland, steep terrain (often exceeding 15°), complex topography, and limited suitability for mechanization, traditional agricultural machinery experiences significantly reduced operational efficiency—typically by 30% to 50%—along with poor mobility. These limitations impose serious constraints on grain yield stability and the advancement of agricultural modernization. Therefore, enhancing the scenario-adaptive performance of chassis systems (e.g., slope adaptability ≥ 25°, lateral tilt stability > 30°) is a major research priority for China’s agricultural equipment industry. This paper presents a systematic review of the global development status of agricultural machinery chassis tailored for hilly and mountainous environments. It focuses on three core subsystems—power systems, traveling systems, and leveling systems—and analyzes their technical characteristics, working principles, and scenario-specific adaptability. In alignment with China’s “Dual Carbon” strategy and the unique operational requirements of hilly–mountainous areas (such as high gradients, uneven terrain, and small field sizes), this study proposes three key technological directions for the development of intelligent agricultural machinery chassis: (1) Multi-mode traveling mechanism design: Aimed at improving terrain traversability (ground clearance ≥400 mm, obstacle-crossing height ≥ 250 mm) and traction stability (slip ratio < 15%) across diverse landscapes. (2) Coordinated control algorithm optimization: Designed to ensure stable torque output (fluctuation rate < ±10%) and maintain gradient operation efficiency (e.g., less than 15% efficiency loss on 25° slopes) through power–drive synergy while also optimizing energy management strategies. (3) Intelligent perception system integration: Facilitating high-precision adaptive leveling (accuracy ± 0.5°, response time < 3 s) and enabling terrain-adaptive mechanism optimization to enhance platform stability and operational safety. By establishing these performance benchmarks and focusing on critical technical priorities—including terrain-adaptive mechanism upgrades, energy-drive coordination, and precision leveling—this study provides a clear roadmap for the development of modular and intelligent chassis systems specifically designed for China’s hilly and mountainous regions, thereby addressing current bottlenecks in agricultural mechanization. Full article

This paper proposes a novel navigation approach for Unmanned Tracked Vehicles (UTVs) using prior-based ensemble deep reinforcement learning, which fuses the policy of the ensemble Deep Reinforcement Learning (DRL) and Dynamic Window Approach (DWA) to enhance both exploration efficiency and deployment safety in unstructured off-road environments. First, by integrating kinematic analysis, we introduce a novel state and an action space that account for rugged terrain features and track–ground interactions. Local elevation information and vehicle pose changes over consecutive time steps are used as inputs to the DRL model, enabling the UTVs to implicitly learn policies for safe navigation in complex terrains while minimizing the impact of slipping disturbances. Then, we introduce an ensemble Soft Actor–Critic (SAC) learning framework, which introduces the DWA as a behavioral prior, referred to as the SAC-based Hybrid Policy (SAC-HP). Ensemble SAC uses multiple policy networks to effectively reduce the variance of DRL outputs. We combine the DRL actions with the DWA method by reconstructing the hybrid Gaussian distribution of both. Experimental results indicate that the proposed SAC-HP converges faster than traditional SAC models, which enables efficient large-scale navigation tasks. Additionally, a penalty term in the reward function about energy optimization is proposed to reduce velocity oscillations, ensuring fast convergence and smooth robot movement. Scenarios with obstacles and rugged terrain have been considered to prove the SAC-HP’s efficiency, robustness, and smoothness when compared with the state of the art. Full article

With climate warming, the global precipitation patterns have undergone significant changes, which will profoundly impact flood–drought disaster regimes and socioeconomic development in key regions of human activity worldwide. The convergence zone of the Indian Ocean monsoon and Pacific monsoon in China covers most of the middle and lower reaches of the Yangtze River (MLRYR), which is located in the transitional area of the second and third steps of China’s terrain. Changes in precipitation patterns in this region will significantly impact flood and drought control in the MLRYR, as well as the socioeconomic development of the MLRYR Economic Belt. In this study, Huaihua area in China was selected as the study area to study the characteristics of regional precipitation change, and to analyze the evolution in the trends in annual precipitation, extreme precipitation events, and their spatiotemporal distribution, so as to provide a reference for the study of precipitation change patterns in the intersection zone. This study utilizes precipitation data from meteorological stations and the China Meteorological Forcing Dataset (CMFD) reanalysis data for the period 1979–2023 in Huaihua region. The spatiotemporal variation in precipitation in the study area was analyzed by using linear regression, the Mann–Kendall trend test, the moving average method, the Mann–Kendall–Sneyers test, wavelet analysis, and R/S analysis. The results demonstrate the following: (1) The annual precipitation in the study area is on the rise as a whole, the climate tendency rate is 9 mm/10 a, and the precipitation fluctuates greatly, showing an alternating change of “dry–wet–dry–wet”. (2) Wavelet analysis reveals that there are 28-year, 9-year, and 4-year main cycles in annual precipitation, and the precipitation patterns at different timescales are different. (3) The results of R/S analysis show that the future precipitation trend will continue to increase, with a strong long-term memory. (4) Extreme precipitation events generally show an upward trend, indicating that their intensity and frequency have increased. (5) Spatial distribution analysis shows that the precipitation in the study area is mainly concentrated in the northeast and south of Jingzhou and Tongdao, and the precipitation level in the west is lower. The comprehensive analysis shows that the annual precipitation in the study area is on the rise and has a certain periodic precipitation law. The spatial distribution is greatly affected by other factors and the distribution is uneven. Extreme precipitation events show an increasing trend, which may lead to increased flood risk in the region and downstream areas. In the future, it is necessary to strengthen countermeasures to reduce the impact of changes in precipitation patterns on local and downstream economic and social activities. Full article

This paper addresses inherent limitations in unmanned aerial vehicle (UAV) undercarriages hindering vertical takeoff and landing (VTOL) capabilities on uneven slopes and obstacles. Robotic landing gear (RLG) designs have been proposed to address these limitations; however, existing designs are typically limited to ground slopes of 6–15°, beyond which rollover would happen. Moreover, articulated RLG concepts come with added complexity and weight penalties due to multiple drivetrain components. Previous research has highlighted that even a minor 3-degree slope change can increase the dynamic rollover risks by 40%. Therefore, the design optimization of robotic landing gear for enhanced VTOL capabilities requires a multidisciplinary framework that integrates static analysis, dynamic simulation, and control strategies for operations on complex terrain. This paper presents a novel, hybrid, compliant, belt-driven, three-legged RLG system, supported by a multidisciplinary design optimization (MDO) methodology, aimed at achieving enhanced VTOL capabilities on uneven surfaces and moving platforms like ship decks. The proposed system design utilizes compliant mechanisms featuring a series of three-flexure hinges (3SFH), to reduce the number of articulated drivetrain components and actuators. This results in a lower system weight, improved energy efficiency, and enhanced durability, compared to earlier fully actuated, articulated, four-legged, two-jointed designs. Additionally, the compliant belt-driven actuation mitigates issues such as backlash, wear, and high maintenance, while enabling smoother torque transfer and improved vibration damping relative to earlier three-legged cable-driven four-bar link RLG systems. The use of lightweight yet strong materials—aluminum and titanium—enables the legs to bend 19 and 26.57°, respectively, without failure. An animated simulation of full-contact landing tests, performed using a proportional-derivative (PD) controller and ship deck motion input, validate the performance of the design. Simulations are performed for a VTOL UAV, with two flexible legs made of aluminum, incorporating circular flexure hinges, and a passive third one positioned at the tail. The simulation results confirm stable landings with a 2 s settling time and only 2.29° of overshoot, well within the FAA-recommended maximum roll angle of 2.9°. Compared to the single-revolute (1R) model, the implementation of the optimal 3R Pseudo-Rigid-Body Model (PRBM) further improves accuracy by achieving a maximum tip deflection error of only 1.2%. It is anticipated that the proposed hybrid design would also offer improved durability and ease of maintenance, thereby enhancing functionality and safety in comparison with existing robotic landing gear systems. Full article

Uneven roads pose significant challenges to vehicle stability, passenger comfort, and safety, especially in snowy and mountainous regions. These problems are often complex and challenging to resolve with traditional detection and stabilization methods. This paper presents a dual-method approach to improving vehicle stability by identifying road irregularities and dynamically adjusting the balance. The proposed solution combines YOLOv8 for real-time road anomaly detection with a GY-521 sensor to track the speed of servo motors, facilitating immediate stabilization. YOLOv8 achieves a peak precision of 0.99 at a confidence threshold of 1.0 rate in surface recognition, surpassing conventional sensor-based detection. The vehicle design is divided into two sections: an upper passenger seating area and a lower section that contains the engine and wheels. The GY-521 sensor is strategically placed to monitor road conditions, while the servomotor stabilizes the upper section, ensuring passenger comfort and reducing the risk of accidents. This setup maintains stability even on uneven terrain. Furthermore, the proposed solution significantly reduces collision risk, vehicle wear, and maintenance costs while improving operational efficiency. Its compatibility with various vehicles and capabilities makes it an excellent candidate for enhancing road safety and driving experience in challenging environments. In addition, this work marks a crucial step towards a safer, more sustainable, and more comfortable transportation system. Full article

Biological systems can adaptively navigate multi-terrain environments via morphological and behavioral flexibility. While robotic systems increasingly achieve locomotion versatility in one or two domains, integrating terrestrial, aquatic, and aerial mobility into a single platform remains an engineering challenge. This work tackles this by introducing a bipedal robot equipped with a reconfigurable locomotion framework, enabling seven adaptive policies: (1) thrust-assisted jumping, (2) legged crawling, (3) balanced wheeling, (4) tricycle wheeling, (5) paddling-based swimming, (6) air-propelled drifting, and (7) quadcopter flight. Field experiments and indoor statistical tests validated these capabilities. The robot achieved a 3.7-m vertical jump via thrust forces counteracting gravitational forces. A unified paddling mechanism enabled seamless transitions between crawling and swimming modes, allowing amphibious mobility in transitional environments such as riverbanks. The crawling mode demonstrated the traversal on uneven substrates (e.g., medium-density grassland, soft sand, and cobblestones) while generating sufficient push forces for object transport. In contrast, wheeling modes prioritize speed and efficiency on flat terrain. The aquatic locomotion was validated through trials in static water, an open river, and a narrow stream. The flight mode was investigated with the assistance of the jumping mechanism. By bridging terrestrial, aquatic, and aerial locomotion, this platform may have the potential for search-and-rescue and environmental monitoring applications. Full article

Autonomous navigation in mining environments is challenged by complex wheel–terrain interaction, traction losses caused by slip dynamics, and sensor limitations. This paper investigates the effectiveness of Deep Reinforcement Learning (DRL) techniques for the trajectory tracking control of skid-steer mobile robots operating under terra-mechanical constraints. Four state-of-the-art DRL algorithms, i.e., Proximal Policy Optimization (PPO), Deep Deterministic Policy Gradient (DDPG), Twin Delayed DDPG (TD3), and Soft Actor–Critic (SAC), are selected to evaluate their ability to generate stable and adaptive control policies under varying environmental conditions. To address the inherent partial observability in real-world navigation, this study presents an original approach that integrates Long Short-Term Memory (LSTM) networks into DRL-based controllers. This allows control agents to retain and leverage temporal dependencies to infer unobservable system states. The developed agents were trained and tested in simulations and then assessed in field experiments under uneven terrain and dynamic model parameter changes that lead to traction losses in mining environments, targeting various trajectory tracking tasks, including lemniscate and squared-type reference trajectories. This contribution strengthens the robustness and adaptability of DRL agents by enabling better generalization of learned policies compared with their baseline counterparts, while also significantly improving trajectory tracking performance. In particular, LSTM-based controllers achieved reductions in tracking errors of 10%, 74%, 21%, and 37% for DDPG-LSTM, PPO-LSTM, TD3-LSTM, and SAC-LSTM, respectively, compared with their non-recurrent counterparts. Furthermore, DDPG-LSTM and TD3-LSTM reduced their control effort through the total variation in control input by 15% and 20% compared with their respective baseline controllers, respectively. Findings from this work provide valuable insights into the role of memory-augmented reinforcement learning for robust motion control in unstructured and high-uncertainty environments. Full article

The safety of power transmission lines is crucial to public well-being, with insulators being prone to failures such as self-detonation. However, images captured by unmanned aerial vehicles (UAVs) carrying optical sensors often face challenges, including uneven object scales, complex backgrounds, and difficulties in feature extraction due to distance, angles, and terrain. Additionally, conventional models are too large for UAV deployment. To address these issues, this paper proposes RML-YOLO, an improved insulator defect detection method based on YOLOv8. The approach introduces a tiered scale fusion feature (TSFF) module to enhance multi-scale detection accuracy by fusing features across network layers. Additionally, the multi-scale feature extraction network (MSFENet) is designed to prioritize large-scale features while adding an extra detection layer for small objects, improving multi-scale object detection precision. A lightweight multi-scale shared detection head (LMSHead) reduces model size and parameters by sharing features across layers, addressing scale distribution imbalances. Lastly, the receptive field attention channel attention convolution (RFCAConv) module aggregates features from various receptive fields to overcome the limitations of standard convolution. Experiments on the UID, SFID, and VISDrone 2019 datasets show that RML-YOLO outperforms YOLOv8n, reducing model size by 0.8 MB and parameters by 500,000, while improving AP by 7.8%, 2.74%, and 3.9%, respectively. These results demonstrate the method’s lightweight design, high detection performance, and strong generalization capability, making it suitable for deployment on UAVs with limited resources. Full article

Single-track electric agricultural chassis plays a vital role in autonomous navigation and driving operations in hilly and mountainous regions, where its path tracking performance directly affects the operational accuracy and stability. However, in complex farmland environments, traditional methods often suffer from frequent turning and large tracking errors due to variable path curvature, uneven terrain, and track slippage. To address these issues, this paper proposes a path tracking algorithm combining a segmented preview model with variable universe fuzzy control, enabling dynamic adjustment of the preview distance for better curvature adaptation. Additionally, a heading deviation prediction model based on Support Vector Regression (SVR) optimized by Particle Swarm Optimization (PSO) is introduced, and a steering angle compensation controller is designed to improve the turning accuracy. Simulation and field experiments show that, compared with fixed preview distance and fixed-universe fuzzy control methods, the proposed algorithm reduces the average number of turns per control cycle by 30.19% and 18.23% and decreases the average lateral error by 34.29% and 46.96%, respectively. These results confirm that the proposed method significantly enhances path tracking stability and accuracy in complex terrains, providing an effective solution for autonomous navigation of agricultural machinery. Full article

Improper car tire pressure affects dynamics, fuel economy, and driver safety. Current central tire inflation systems (CTISs) regulate tire pressure relative to its reference value. However, the current CTIS is limited in its automation, as the system requires the loading of present conditions and the manual input of terrain conditions. Therefore, the system lacks intelligent components which would increase its efficiency. Adding a terrain recognition feature to the current CTIS technology, the tire pressure management system (TPMS) described in this paper enhances the capability to adjust to the ideal tire pressure according to the terrain condition. In this study, we integrate a terrain recognition component which uses a convolutional neural network (CNN), specifically, ResNet-18, into the TPMS to classify and detect terrain conditions and apply the correct pressure level. A one-tire terrain-based TPMS model was developed through system integration. The system was tested under flat, uneven, and soft terrain conditions. The CNN model demonstrated 95% accuracy in classifying the chosen terrains, with demonstrated adaptability to nighttime environments. Inflation and deflation tests were conducted at varying speeds and terrains, and the results showed longer inflation times at higher pressure ranges, while deflation times remained consistent regardless of pressure range. A negligible impact on inflation and deflation speed was observed at speeds below 15 km/h. Instantaneous response time between the microcontrollers increases efficiency in the overall CTIS process. Full article

Mecanum and omni wheel-based assistive technologies present an alternative to conventional mobility devices for individuals with motor impairments, owing to their omnidirectional movement capabilities and high maneuverability in constrained environments. This systematic review identifies and categorizes the key challenges and emerging trends in the development of such systems. Primary obstacles include limited stability and maneuverability on uneven terrain, high energy consumption, complex control requirements, and elevated production costs. In response, recent studies have introduced several innovative approaches, such as advanced suspension systems to enhance terrain adaptability, modular mechanical designs to reduce manufacturing complexity, energy-efficient motor control strategies such as field-oriented control, AI-driven autonomous navigation, and hands-free user interfaces—including gesture recognition and brain–computer interfaces. By synthesizing findings from 26 peer-reviewed studies, this review outlines current technical limitations, surveys state-of-the-art solutions, and offers strategic recommendations to inform future research in intelligent assistive mobility technologies. Full article

Agricultural robots can mitigate labor shortages and advance precision farming. However, the dense vegetation canopies and uneven terrain in orchard environments reduce the reliability of traditional GPS-based localization, thereby reducing navigation accuracy and making autonomous navigation challenging. Moreover, inefficient path planning and an increased risk of collisions affect the robot’s ability to perform tasks such as fruit harvesting, spraying, and monitoring. To address these limitations, this study integrated stereo visual odometry with real-time appearance-based mapping (RTAB-Map)-based simultaneous localization and mapping (SLAM) to improve mapping and localization in both indoor and outdoor orchard settings. The proposed system leverages stereo image pairs for precise depth estimation while utilizing RTAB-Map’s graph-based SLAM framework with loop-closure detection to ensure global map consistency. In addition, an incorporated inertial measurement unit (IMU) enhances pose estimation, thereby improving localization accuracy. Substantial improvements in both mapping and localization performance over the traditional approach were demonstrated, with an average error of 0.018 m against the ground truth for outdoor mapping and a consistent average error of 0.03 m for indoor trails with a 20.7% reduction in visual odometry trajectory deviation compared to traditional methods. Localization performance remained robust across diverse conditions, with a low RMSE of 0.207 m. Our approach provides critical insights into developing more reliable autonomous navigation systems for agricultural robots. Full article