Search Results (211)

Ground autonomous mobile robots are increasingly critical for reconnaissance, patrol, and resupply tasks in public safety and national defense scenarios, where global path planning in 3D uneven terrains remains a major challenge. Traditional planners struggle with high dimensionality, while Deep Reinforcement Learning (DRL) is hindered by two key issues: (1) systematic overestimation of action values (Q-values) due to function approximation error, which leads to suboptimal policies and training instability; and (2) inefficient exploration under sparse reward signals. To address these limitations, we propose DSAC-ICM: a Distributional Soft Actor–Critic framework integrated with an Intrinsic Curiosity Module (ICM). Our method fundamentally shifts the learning paradigm from estimating scalar Q-values to learning the full probability distribution of state-action returns, which inherently mitigates value overestimation. We further integrate the ICM to generate dense intrinsic rewards, guiding the agent toward novel and unvisited states to tackle the exploration challenge. Comprehensive experiments conducted in a suite of realistic 3D uneven-terrain environments demonstrate that DSAC-ICM successfully enables the agent to learn effective navigation capabilities. Crucially, it achieves a superior trade-off between path quality and computational cost when compared to traditional path planning algorithms. Furthermore, DSAC-ICM significantly outperforms other RL baselines in terms of convergence speed and return. Full article

Achieving dynamic stability in bipedal locomotion against sustained external disturbances remains a significant challenge in humanoid robotics. Traditional methods, such as zero moment point (ZMP) preview control, often lack the reactive compliance and predictive planning necessary for robust performance on uneven terrain or under continuous force. This paper proposes a novel control framework that synergistically integrates a resistance torso compliance controller with a nonlinear model predictive control (NMPC)-based walking pattern generator. The compliance controller actively modulates the torso’s dynamics via impedance control, creating a virtual mass–spring–damper system that absorbs impacts and generates counterforces to resist sustained pushes. Concurrently, the NMPC module reformulates gait generation as a real-time optimization problem, simultaneously determining optimal footstep positions and orientations while respecting nonlinear constraints derived from centroidal momentum dynamics. Simulation results demonstrate that this integrated approach reduces the maximum ZMP error by 34.1% and the RMS ZMP error by 37.3% compared to traditional ZMP preview control, with a 38.9% improvement in settling time after a disturbance. This work establishes that the tight coupling of reactive impedance control and predictive optimization provides a foundational framework for enhancing the robustness and adaptability of bipedal locomotion. Full article

Rocker–bogie suspension systems have been extensively employed in planetary exploration rovers due to their ability to traverse highly irregular terrains while maintaining ground contact. Traditionally, their mechanical behavior has been analyzed using quasi-static models, given the low operational speeds typical of space missions. However, similar configurations are now being proposed for terrestrial applications in agriculture, defense, and logistics, where higher traversal speeds and more varied terrain conditions require a deeper understanding of the system’s dynamic response. This study analyzes some aspects of the kinematic and dynamic behavior of a rover with rocker–bogie suspension while traversing an obstacle with a harmonic profile. Both quasi-static and dynamic simulations are conducted, focusing on the time-varying contact forces at the wheels. Key findings include identifying the rate at which load reduction at which the load on one wheel becomes zero and the wheel tends to lift off the ground. These threshold speeds are mapped as a function of height and wavelength of the bump, providing design insights for applications requiring higher traversal speeds on uneven terrain. The analysis may also prove valuable for rovers equipped with visual sensor systems capable of mapping their surroundings and identifying obstacles, to determine whether they can be traversed and, if so, at what maximum speed. An experimental investigation was conducted with a small-scale rover to verify the theoretical results, for which the threshold speed was found to be 0.3 m/s, calculated for h = 16 mm and λ = 80 mm. Full article

In recent years, while progress has been made in barrier-free design, the complete elimination of physical barriers such as uneven road surfaces and stairs remains difficult, and wheelchair passengers continue to face significant mobility constraints. This study aims to verify the effectiveness of a transformable quadruped wheelchair that can switch between two modes of movement: walking and wheeled travel. Specifically, reinforcement learning using Proximal Policy Optimization (PPO) was used to acquire walking strategies for uneven terrain and wheeled travel strategies for flat terrain. NVIDIA Isaac Sim was used for simulation. To evaluate the stability of both modes, we performed a frequency analysis of the passenger’s acceleration data. As a result, we observed periodic vibrations around 2 Hz in the vertical direction in walking mode, while in wheeled mode, we confirmed extremely small vibrations and stable running. Furthermore, we distilled these two strategies into a single mode-conditional strategy and conducted long-distance running experiments involving mode transformation. The results demonstrated that by adaptively switching between walking and wheeled modes depending on the terrain, mobility efficiency was significantly improved compared to continuous operation in a single mode. This study demonstrates the effectiveness of an approach that involves learning multiple specialized strategies and switching between them as needed to efficiently traverse diverse environments using a transformable robot. Full article

To address the challenges in unstructured orchard environments, including high geometric similarity between fruit trees (with the measured average Euclidean distance difference between point cloud descriptors of adjacent trees being less than 0.5 m), significant dynamic interference (e.g., interference from pedestrians or moving equipment can occur every 5 min), and uneven terrain, this paper proposes an improved mapping algorithm named OSC-LIO (Orchard Scan Context Lidar Inertial Odometry via Smoothing and Mapping). The algorithm designs a dynamic point filtering strategy based on Euclidean clustering and spatiotemporal consistency within a 5-frame sliding window to reduce the interference of dynamic objects in point cloud registration. By integrating local semantic features such as fruit tree trunk diameter and canopy height difference, a two-tier verification mechanism combining “global and local information” is constructed to enhance the distinctiveness and robustness of loop closure detection. Motion compensation is achieved by fusing data from an Inertial Measurement Unit (IMU) and a wheel odometer to correct point cloud distortion. A three-level hierarchical indexing structure—”path partitioning, time window, KD-Tree (K-Dimension Tree)”—is built to reduce the time required for loop closure retrieval and improve the system’s real-time performance. Experimental results show that the improved OSC-LIO system reduces the Absolute Trajectory Error (ATE) by approximately 23.5% compared to the original LIO-SAM (Tightly coupled Lidar Inertial Odometry via Smoothing and Mapping) in a simulated orchard environment, while enabling stable and reliable path planning and autonomous navigation. This study provides a high-precision, lightweight technical solution for autonomous navigation in orchard scenarios. Full article

With the rapid development of the power Internet of Things (IoT), the traditional manual inspection mode can no longer meet the growing demand for power equipment inspection. Unmanned aerial vehicle (UAV) intelligent inspection technology, with its efficient and flexible features, has become the mainstream solution. The rapid development of computer vision and deep learning (DL) has significantly improved the accuracy and efficiency of UAV intelligent inspection systems for power equipment. However, mainstream deep learning models have complex structures, and manual design is time-consuming and labor-intensive. In addition, the images collected during the power inspection process by UAVs have problems such as complex backgrounds, uneven lighting, and significant differences in object sizes, which require expert DL domain knowledge and many trial-and-error experiments to design models suitable for application scenarios involving power inspection with UAVs. In response to these difficult problems, evolutionary computation (EC) technology has demonstrated unique advantages in simulating the natural evolutionary process. This technology can independently design lightweight and high-precision deep learning models by automatically optimizing the network structure and hyperparameters. Therefore, this review summarizes the development of evolutionary deep learning (EDL) technology and provides a reference for applying EDL in object detection models used in UAV intelligent power inspection systems. First, the application status of DL-based object detection models in power inspection is reviewed. Then, how EDL technology improves the performance of the models in challenging scenarios such as complex terrain and extreme weather is analyzed by optimizing the network architecture. Finally, the challenges and future research directions of EDL technology in the field of UAV power inspection are discussed, including key issues such as improving the environmental adaptability of the model and reducing computing energy consumption, providing theoretical references for promoting the development of UAV power inspection technology to a higher level. Full article

The use of wireless sensor networks (WSNs) enables multidimensional and high-precision forest environment monitoring around the clock. However, the limited energy supply of sensor nodes using solely batteries is insufficient to support long-term data collection. Furthermore, since the complex terrain, dense vegetation, and variable weather in forests present unique challenges, relying on a single energy source is insufficient to ensure a stable energy supply for sensor nodes. Combining multiple energy sources is a promising way which has not been well studied. In this paper, to effectively utilize multiple energy sources, we propose a novel dynamic clustering routing protocol which considers the inherent diversity and intermittency of energy sources of the WSN in the forest. First, to address the inconsistency in residual energy caused by uneven energy harvesting among sensor nodes, a cluster head selection weight function is developed, and a dynamic weight-based cluster head election algorithm is proposed. This mechanism effectively prevents low-energy nodes from being selected as cluster heads, thereby maximizing the utilization of harvested energy. Second, a Q-learning-based adaptive hybrid transmission scheme is introduced, integrating both single-hop and multi-hop communication. The scheme dynamically optimizes intra-cluster transmission paths based on the current network state, reducing energy consumption during data transmission. The simulation results show that the proposed routing algorithm significantly outperforms existing methods in total network energy consumption, network lifetime, and energy balance. These advantages make it particularly suitable for forest environments characterized by strong fluctuations in harvested energy. In summary, this work provides an energy-efficient and adaptive routing solution suitable for forest environments with fluctuating energy availability. Full article

Achieving stable contact on uneven terrain remains a key challenge in humanoid robotics, as most feet rely on rigid or passively compliant structures with fixed stiffness. This work presents the design, fabrication, and analytical modeling of a compact soft pneumatic submodule capable of tunable longitudinal stiffness, developed as a proof-of-concept unit for adaptive humanoid feet. The submodule features a tri-layer architecture with two antagonistic pneumatic chambers separated by an inextensible layer and reinforced by rigid inserts. A single-step wax-core casting process integrates all materials into a monolithic soft–rigid structure, ensuring precise geometry and repeatable performance. An analytical model relating internal pressure to equivalent stiffness was derived and experimentally validated, showing a linear stiffness–pressure relation with mean error below 10% across 0–30 kPa. Static and dynamic tests confirmed tunable stiffness between 0.18 and 0.43 N·m/rad, a rapid symmetric response (2.9–3.4 ms), and stable stiffness under cyclic loading at gait-relevant frequencies. These results demonstrate the submodule’s suitability as a scalable building block for distributed, real-time stiffness modulation in next-generation humanoid feet. Full article

Sport horse feeding robots face significant challenges in achieving precise navigation within complex stable environments. Uneven terrain and frequently moist ground often cause drive wheel slippage, resulting in path deviation and cumulative pose errors that compromise feeding accuracy and operational efficiency. To address this challenge, an enhanced Dynamic Window Approach (DWA) path planning framework, which integrates an automatic drift correction module based on an Inertial Measurement Unit (IMU) and a two-stage cascade proportional–integral–derivative (PID) controller, is proposed in this paper. This enhanced DWA enables precise yaw adjustment while preserving the native velocity sampling and trajectory evaluation framework of conventional DWA. Field validations were conducted through ten independent trials along a fixed 28 m feeding route in an actual sport horse feeding environment to quantitatively evaluate the robot’s path deviation and yaw angle stability. The results demonstrated that the enhanced algorithm reduced the standard deviation of path deviation from 0.161 m to 0.144 m (10.56% improvement) and decreased yaw angle standard deviation from 2.19° to 1.74° (20.55% reduction in angular oscillation). These improvements validated the effectiveness of the proposed algorithm in mitigating slippage-induced pose drift and significantly improving the locomotion capability of robots for sport horse feeding within stable environments. Full article

This paper presents a new approach to the dimensional synthesis of a robotic limb mechanism for a wheel-legged robot. The proposed kinematic structure enables independent control of wheel motions relative to the robot platform, allowing each drive to perform a distinct movement. The selection of the mechanism’s common dimensions simplifies platform levelling to a single-drive actuation. The hybrid limb design, which combines features of driving and walking systems, enhances platform stability on uneven terrain and is suitable for rescue, exploration, and inspection robots. The synthesis method defines the desired trajectory of the wheel centre and applies a genetic algorithm to determine mechanism dimensions that reproduce this motion. The stochastic optimisation process yields multiple feasible solutions, enabling the introduction of additional design criteria for optimal configuration selection. Analytical kinematic relations were developed for workspace and trajectory evaluation, solving both direct and inverse kinematic problems. The results confirm the effectiveness of evolutionary optimisation in synthesising complex kinematic mechanisms. The proposed approach can be adapted to other mobile robot structures. Future work will address dynamic modelling, adaptive control for real-time platform levelling, and comparative studies with other synthesis methods. Full article

To address issues such as chassis attitude deviation, reduced operational efficiency, and diminished precision when agricultural machinery operates in complex terrains—including steep slopes and fragmented plots in hilly and mountainous regions—a servo electric cylinder-based active suspension levelling system has been designed. Real-time dynamic control is achieved through a fuzzy PID algorithm. Firstly, the suspension’s mechanical structure and key parameters were determined, employing a ‘servo electric cylinder-spring-shock absorber series’ configuration to achieve load support and passive vibration damping. Secondly, a kinematic and dynamic model of the quarter-link suspension was established. Finally, Simulink simulations were conducted to model the agricultural machinery traversing mountainous, uneven terrain at segmented stable operating speeds, thereby validating the suspension’s control performance. Simulation results demonstrate that the system maintains chassis height error within ±0.05 m, chassis height change rate within ±0.2 m/s, and response time ≤ 0.8 s. It rapidly and effectively counteracts terrain disturbances, achieving precise chassis height control. This provides theoretical support for designing whole-vehicle levelling systems for small agricultural machinery in hilly and mountainous terrains. Full article

To address the challenges of low automatic leveling efficiency and insufficient control precision for small tracked operation chassis navigating uneven terrain in hilly and mountainous areas, this study proposes a leveling control system that integrates a dual-layer threshold strategy with a BP neural network algorithm. The system is developed based on a four-point lifting leveling mechanism. Building upon this foundation, the conventional single-threshold angle error compensation control strategy was optimized to meet the specific leveling demands of chassis operating in such complex environments. A co-simulation platform was established using Matlab/Simulink-AMEsim for subsequent simulation and comparative analysis. Simulation results demonstrate that the proposed method achieves a 15.6% improvement in leveling response speed and a 21.3% enhancement in leveling accuracy compared to the classical single-threshold PID control algorithm. Static test results reveal a smooth leveling process devoid of significant overshoot or hysteresis, with the leveling error consistently maintained within 0.5°. Field tests further indicate that at a travel speed of 3 km/h under a 50 kg load, the platform stabilization time is reduced by an average of 1.3 s, while the leveling angle error remains within 0.5°. The proposed system not only improves leveling response speed and precision but also effectively enhances the overall leveling efficiency of the tracked chassis system. Full article

The operation of walking excavators on rugged terrain often leads to leg lift-off, which can result in uneven force distribution, accelerated structural wear, and even systemic instability. To address these issues, this paper proposes a coordinated control framework comprising three integral components: a Dual Strong Tracking Kalman Filter (DSTKF) for estimating unmeasurable system states—such as joint velocities, external forces, and hydraulic disturbances; a fuzzy adaptive virtual model-based force planner that dynamically adjusts the desired leg forces in real time to minimize support force variations; and a DSTKF-based force controller that precisely regulates the output force of each leg. Simulations and physical experiments demonstrate that the proposed approach effectively achieves autonomous balance of ground contact forces and optimizes force distribution among the legs. This study provides a lightweight, fully closed-loop solution for state estimation and walking force balance in walking excavators equipped with standard proportional valves. Full article

Low-cost and real-time remote sensing of moving targets is increasingly required in civilian applications. Micro unmanned aerial vehicles (UAVs) provide a promising platform for such missions because of their small size and flexible deployment, but they are constrained by payload capacity and energy budget. Consequently, they typically carry lightweight monocular cameras only. These cameras cannot directly measure distance and suffer from scale ambiguity, which makes accurate geolocation difficult. This paper tackles geolocation and short-term trajectory prediction of moving targets over uneven terrain using bearing-only measurements from a monocular camera. We present a two-stage estimation framework in which a pseudo-linear Kalman filter (PLKF) provides real-time state estimates, while a sliding-window nonlinear least-squares (NLS) back end refines them. Future target positions are obtained by extrapolating the estimated trajectory. To improve localization accuracy, we analyze the relationship between the UAV path and the Cramér–Rao lower bound (CRLB) using the Fisher Information Matrix (FIM) and derive an observability-enhanced trajectory planning method. Real-flight experiments validate the framework, showing that accurate geolocation can be achieved in real time using only low-cost monocular bearing measurements. Full article

Accurate rainfall estimation remains a critical challenge in hydrology, particularly in Italy, where complex topography and uneven rain-gauge distribution introduce major uncertainties. To address this gap, this study assessed five widely used satellite precipitation products, CHIRPS, GPM, HSAF, PDIRNOW, and SM2RAIN, against the high-resolution SCIA-ISPRA ground dataset. These products were selected because they represent distinct retrieval approaches (infrared–station hybrid, microwave integration, geostationary blending, neural-network infrared, and soil–moisture inversion) and offer diverse temporal and spatial resolutions suitable for both research and operational monitoring. The evaluation, conducted at daily, seasonal, and annual scales using categorical, continuous, and extreme-event indices, revealed that no single product performs optimally across all metrics. GPM achieved the most balanced and reliable performance overall, whereas PDIRNOW and SM2RAIN provided strong detection but frequent overestimation. CHIRPS yielded conservative estimates with few false alarms, while HSAF was less consistent, especially during winter. The results underscore that product suitability depends on the intended application: detection-oriented systems like PDIRNOW are preferable for flood forecasting, whereas conservative datasets like CHIRPS better support drought monitoring. Overall, integrating multiple products or adopting hybrid approaches is recommended to enhance precipitation assessment accuracy over complex Mediterranean terrains. Full article