Journal of Field Robotics最新文献

With the development of soft crawling robots, pneumatic soft actuators (PSAs) with complicated nonplanar structures are increasingly designed due to the capabilities of achieving compound robot movements. However, the current deformation accuracy of complex PSAs is insufficient to satisfy application requirements. Specifically, the dynamic properties of complex PSAs are still ambiguous and PSA deformation control methods remain lacking, which are caused by inherent characteristics, such as strong nonlinearity and hysteresis. To this end, based on self-fabricated spatial deformation pneumatic leg actuators (SDPLAs), an equivalent dynamic model derived from Euler–Lagrange equations and a modified hysteresis model are established to form the new complete model of SDPLA systems, which accurately describes the bending deformation and hysteresis of SDPLAs at the same time. Furthermore, a novel model-based adaptive fuzzy tracking controller is designed for SDPLAs, which addresses model uncertainties and unknown external torque, and achieves the accurate bending of each SDPLA part. Subsequently, the closed-loop stability is rigorously proven by the Lyapunov theory. Finally, a series of experiments validates the effectiveness of the established dynamic and hysteresis models, the tracking control performance on time-varying trajectories with different amplitudes, frequencies, and shapes, and the control robustness against disturbances.

Western Flower Thrips (Frankliniella occidentalis) is a significant agricultural pest causing substantial economic losses by damaging crops and acting as a vector for plant diseases. Traditional pest control methods relying on chemical pesticides pose environmental and health risks, necessitating alternative solutions. Entomopathogenic nematodes (EPNs) have emerged as a promising biological control agent. This study presents an AI-supported precision application system, Nemabot, designed to optimize EPN deployment based on thrips-induced bean leaf damage. In this study, agricultural disease detection was performed using the Multi-Otsu Thresholding method integrated into deep learning-based object detection and segmentation algorithms. The developed method enhances segmentation accuracy through image processing techniques, thereby increasing the precision in identifying infested regions. The model used in the study was optimized with a YOLO-based architecture during training and reinforced with various data augmentation techniques for segmenting bean leaves. The model's performance evaluation yielded mAP0.5 values of B: 0.9481 and M: 0.94981, while mAP0.5:0.95 values were B: 0.90887 and M: 0.90887. The precision and recall values were 1.0 and 0.99975, respectively, indicating the model's high sensitivity. Additionally, the low values of box_loss, segmentation_loss, and objectness_loss demonstrate that the model maintains a minimal error rate. The proposed approach offers higher accuracy and sensitivity than conventional segmentation methods, contributing significantly to agricultural disease detection applications.

This paper introduces the design methodology and development of an inspection robot for submerged structures in high-flow aquatic environments. The robotic system employs dual counter-rotating vortex suction cups for surface adhesion and achieves omnidirectional mobility through four integrated steering-drive joints. Its reconfigurable articulated structure enables adaptive conformation to diverse structural geometries. Current regulatory frameworks explicitly mandate non-destructive testing (NDT) requirements for underwater infrastructure maintenance. Conventional suspended underwater robots face challenges in maintaining stable positional control and consistent surface contact, while existing adhesion-based systems demonstrate deficiencies in flow-field adaptability, maneuverability, and transitional capability within complex hydrodynamic conditions. Through systematic exploration of robotic design principles balancing adsorption forces and hydrodynamic resistance under intense flow disturbances, we prototyped and validated the system via experimental campaigns in both dam environments and controlled hydrodynamic test basins. Experimental results demonstrate the robot's capability to execute high-dexterity maneuvers including in-situ rotation, comb-pattern scanning, zigzag trajectories, and intersection curve paths. The system proves effective for inspecting both large-curvature-radius surfaces (e.g., dam facades) and small-diameter tubular structures (e.g., jacket node welds). Field trials confirm that even with simplified control architecture requiring minimal operator intervention, the robot successfully acquires high-resolution continuous imaging on dam surfaces and obtains valid phased array ultrasonic testing (PAUT) signals for weld inspection, demonstrating detectable sensitivity to artificially induced defects.

Large-scale semantic mapping is crucial for outdoor autonomous agents to perform high-level tasks such as planning and navigation. In this paper, we propose a novel method for large-scale 3D semantic reconstruction through implicit representations from posed LiDAR measurements alone. We first construct a neural fields via the octree and latent features, then decode implicit features into signed distance value and semantic information through shallow Multilayer Perceptrons (MLPs). We leverage radial window self-attention networks to predict the semantic labels of point clouds. We then jointly optimize the feature embedding and MLP parameters with a self-supervision paradigm for point-cloud geometry and a pseudo-supervision paradigm for semantic and panoptic labels. Subsequently, geometric structures and semantic categories for novel points in the unseen area are regressed, and the marching cubes method is exploited to subdivide and visualize scenes in the inferring stage, the labeled mesh is produced correspondingly. Experiments on two real-world datasets, SemanticKITTI and SemanticPOSS, demonstrate the superior segmentation efficiency and mapping effectiveness of our framework compared to existing 3D semantic LiDAR mapping methods.

Heavy-duty robots such as hexapod robots exhibit tremendous potential with their high payload ability and terrain adaptability. This paper introduces a control approach for heavy-duty hexapod robot that traverses uneven and transition stage from a flat surface to a sloped terrain without prior geometric knowledge of the environment. Using force sensors on the robot feet and position sensors at its joints, the transition from a flat surface to a sloped terrain is detected. Constraint models based on terrain geometric information and joint limit positions are presented. The models are derived to estimate the unknown slope gradient based on the landing feet positions. The constraints for different terrains have also been investigated. An optimal force allocation method under contact constraints is developed to minimize the linear and quadratic costs in the commands and constrained contact forces. Extensive experiments have been conducted, and the results have demonstrated the effectiveness of the proposed control approach.

The flight efficiency of bionic flapping-wing robots is largely influenced by the flapping mechanism. This paper presents the development of a large wingspan flapping-wing flying robot that utilizes a rigid-flexible coupling flapping mechanism to reduce energy consumption, improve flight efficiency, and enhance wind resistance. The rigid-flexible coupling flapping mechanism consists of a DC motor with a gearset and a flexible flapping mechanism based on torsion spring. This mechanism combines the high torque driving capability of a rigid mechanism with the energy storage capacity of a flexible mechanism. Synchronizing the passive deformation of the torsion spring with the periodic acceleration and deceleration of the wings during the flapping cycle enables the storage, transfer, and release of kinetic energy and torsional spring elastic strain energy. Simulation studies show that the proposed design effectively reduces the peak power required. A prototype with a wingspan of 1.8 meters and a mass of 1.0 kilograms was developed. Compared to a rigid mechanism, the proposed design significantly reduces the electrical power consumption, especially when achieving flapping frequencies exceeding 1.5 Hz, as validated through wind tunnel experiments. At a flapping frequency of 2.2 Hz, the maximum reduction in electrical power consumption reaches 14.8%. The flexible elements also increased the downstroke ratio, consequently enhancing thrust and propulsion efficiency. Outdoor flight experiments have demonstrated that the prototype propelled by the rigid-flexible coupling drive mechanism consumes only 81.56 W during cruising, which is 8.78 W (9.72%) less than the rigidly driven prototype.

Ice cover hinders the deployment of acoustic arrays or satellites, making it challenging to locate underwater vehicles in the polar regions. Odometry based on acoustic or optical sensors has the potential to provide precise navigation results for vehicles. However, the robustness of single-sensor-based odometry is significantly compromised by the smooth and featureless nature of the ice-covered bottom, which lacks distinct points, lines, or surfaces. This paper presents a filter-based multi-sensor fusion underwater ice odometry system, integrating measurements from a stereo camera, a forward-looking sonar (FLS), a low-cost inertial measurement unit (IMU), and a depth gauge (DG). To balance real-time performance and accuracy, the Multi-State Constraint Kalman Filter (MSCKF) algorithm is employed to fuse inertial and stereo measurements for vehicle state estimation. Additionally, FLS images and relative depth measurements from the DG are utilized to enhance the accuracy and robustness of the state estimation. Specifically, a Fourier-based algorithm is proposed to estimate linear speed using global information from FLS images. A compensation factor is introduced to address the impact of FLS elevation angle on estimation accuracy. Furthermore, a residual-based adaptive method and forgetting factor are implemented to adjust the measurement noise covariance of linear speed and relative depth, improving dynamic state estimation precision. The proposed system was evaluated through tank and field experiments using a remotely operated vehicle (ROV). Results show it provides more accurate and robust under-ice navigation compared to state-of-the-art algorithms.

Despite the increasing prevalence of robots in daily life, their navigation capabilities are still limited to environments with prior knowledge, such as a global map. To fully unlock the potential of robots, it is crucial to enable them to navigate in large-scale unknown and changing unstructured scenarios. This requires the robot to construct an accurate static map in real-time as it explores, while filtering out moving objects to ensure mapping accuracy and, if possible, achieving high-quality pedestrian tracking and collision avoidance. While existing methods can achieve individual goals of spatial mapping or dynamic object detection and tracking, there has been limited research on effectively integrating these two tasks, which are actually coupled and reciprocal. In this study, we propose a solution called S²MAT (simultaneous and self-reinforced mapping and tracking) that integrates a front-end dynamic object detection and tracking module with a back-end static mapping module. S²MAT leverages the close and reciprocal interplay between these two modules to efficiently and effectively solve the open problem of simultaneous tracking and mapping in highly dynamic scenarios. The proposed method is primarily designed for use with 3D LiDAR and offers a solution for real-time navigation in large-scale, unknown dynamic scenarios with a low computational cost, making it feasible for deployment on onboard computers equipped with only a single CPU. We conducted long-range experiments in real-world urban scenarios spanning over 7 km, which included challenging obstacles like pedestrians and other traffic agents. The successful navigation provides a comprehensive test of S²MAT's robustness, scalability, efficiency, quality, and its ability to benefit autonomous robots in wild scenarios without pre-built maps.