Journal of Field Robotics最新文献

Modern mobile robots require precise and robust localization and navigation systems to achieve mission tasks correctly. In particular, in the underwater environment, where Global Navigation Satellite Systems cannot be exploited, the development of localization and navigation strategies becomes more challenging. Maximum A Posteriori (MAP) strategies have been analyzed and tested to increase navigation accuracy and take into account the entire history of the system state. In particular, a sensor fusion algorithm relying on a MAP technique for Simultaneous Localization and Mapping (SLAM) has been developed to fuse information coming from a monocular camera and a Doppler Velocity Log (DVL) and to consider the landmark points in the navigation framework. The proposed approach can guarantee to simultaneously locate the vehicle and map the surrounding environment with the information extracted from the images acquired by a bottom-looking optical camera. Optical sensors can provide constraints between the vehicle poses and the landmarks belonging to the observed scene. The DVL measurements have been employed to solve the unknown scale factor and to guarantee the correct vehicle localization even in the absence of visual features. Furthermore, to evaluate the mapping capabilities of the SLAM algorithm, the obtained point cloud is elaborated with a Poisson reconstruction method to obtain a smooth seabed surface. After validating the proposed solution through realistic simulations, an experimental campaign at sea was conducted in Stromboli Island (Messina), Italy, where both the navigation and the mapping performance have been evaluated.

Headland maneuvering is a crucial part of the field operations performed by autonomous agricultural vehicles (AAVs). While motion planning for headland turning in open fields has been extensively studied and integrated into commercial autoguidance systems, the existing methods primarily address scenarios with ample headland space and thus may not work in more constrained headland geometries. Commercial orchards often contain narrow and irregularly shaped headlands, which may include static obstacles, rendering the task of planning a smooth and collision-free turning trajectory difficult. To address this challenge, we propose an optimization-based motion planning algorithm for headland turning under geometrical constraints imposed by headland geometry and obstacles. Our method models the headland and the AAV using convex polytopes as geometric primitives, and calculates optimal and collision-free turning trajectories in two stages. In the first stage, a coarse path is generated using either a classical pattern-based turning method or a directional graph-guided hybrid A* algorithm, depending on the complexity of the headland geometry. The second stage refines this coarse path by feeding it into a numerical optimizer, which considers the vehicle's kinematic, control, and collision-avoidance constraints to produce a feasible and smooth trajectory. We demonstrate the effectiveness of our algorithm by comparing it to the classical pattern-based method in various types of headlands. The results show that our optimization-based planner outperforms the classical planner in generating collision-free turning trajectories inside constrained headland spaces. Additionally, the trajectories generated by our planner respect the kinematic and control limits of the vehicle and, hence, are easier for a path-tracking controller to follow. In conclusion, our proposed approach successfully addresses complex motion planning problems in constrained headlands, making it a valuable contribution to the autonomous operation of AAVs, particularly in real-world orchard environments.

Assessing human stress in agriculture proves to be a complex and time-intensive endeavor within the field of ergonomics, particularly for the development of agricultural systems. This methodology involves the utilization of instrumentation and the establishment of a dedicated laboratory setup. The complexity arises from the need to capture and analyze various physiological and psychological indicators, such as heart rate (HR), muscle activity, and subjective feedback to comprehensively assess the impact of farm operations on subjects. The instrumentation typically includes wearable devices, sensors, and monitoring equipment to gather real-time data of subject during the performance of farm operations. Deep learning (DL) models currently achieve human performance levels on real-world face recognition tasks. In this study, we went beyond face recognition and experimented with the recognition of human stress based on facial features during the drudgery-prone agricultural operation of sugarcane harvesting. This is the first research study for deploying artificial intelligence-driven DL techniques to identify human stress in agriculture instead of monitoring several ergonomic characteristics. A total of 20 (10 each for male and female) subjects comprising 4300 augmented RGB images (215 per subject) were acquired during sugarcane harvesting seasons and then these images were deployed for training (80%) and validation (20%). Human stress and nonstress states were determined based on four ergonomic physiological parameters: heart rate (ΔHR), oxygen consumption rate (OCR), energy expenditure rate (EER), and acceptable workload (AWL). Stress was defined when ΔHR, OCR, EER, and AWL reached or exceeded certain standard threshold values. Four convolutional neural network-based DL models (1) DarkNet53, (2) InceptionV3, (3) MobileNetV2 and (4) ResNet50 were selected due to their remarkable feature extraction abilities, simple and effective implementation to edge computation devices. In all four DL models, training performance results delivered training accuracy ranging from 73.8% to 99.1% at combinations of two mini-batch sizes and four levels of epochs. The maximum training accuracies were 99.1%, 99.0%, 97.7%, and 95.4% at the combination of mini-batch size 16 and 25 epochs for DarkNet53, InceptionV3, ResNet50, and MobileNetV2, respectively. Due to the best performance, DarkNet53 was tested further on an independent data set of 100 images and found 89.8%–93.3% confident to classify stressed images for female subjects while 92.2%–94.5% for male subjects, though it was trained on the integrated data set. The comparative classification of the developed model and ergonomic measurements for stress classification was carried out with a net accuracy of 88% where there were few instances of wrong classifications.

This paper addresses the challenge of generating clear image frames and minimizing the loss of keyframes by a robot engaging in rapid large viewing angle motion. These issues often lead to detrimental consequences such as trajectory drifting and loss during the construction of curved motion trajectories. To tackle this, we proposed a novel visual simultaneous localization and mapping (SLAM) algorithm, TKO-SLAM, which is based on time-delay feature regression and keyframe position optimization. TKO-SLAM uses a multiscale recurrent neural network to rectify object deformation and image motion smear. This network effectively repairs the time-delay image features caused by the rapid movement of the robot, thereby enhancing visual clarity. Simultaneously, inspired by the keyframe selection strategy of the ORB-SLAM3 algorithm, we introduced a grayscale motion-based image processing method to supplement keyframes that may be omitted due to the robot's rapid large viewing angle motion. To further refine the algorithm, the time-delay feature regression image keyframes and adjacent secondary keyframes were used as dual measurement constraints to optimize camera poses and restore robot trajectories. The results of experiments on the benchmark RGB-D data set TUM and real-world scenarios show that TKO-SLAM algorithm achieves more than 10% better localization accuracy than the PKS-SLAM algorithm in the rapid large viewing angle motion scenario, and has advantages over the SOTA algorithms.

With technological advancement, the use of drones in delivery systems has become increasingly feasible. Many companies have developed rotary-wing drone (RWD) technologies for parcel delivery. At present, the limited endurance is the main disadvantage of RWD delivery. The energy consumption of RWDs must be carefully managed, and it is necessary to develop an effective energy-consumption model to support RWD flight planning. Because the interaction between the forces on the RWD and its flying environment is very complex, it is challenging to estimate accurately the RWD energy consumption. This study summarizes several energy-consumption models proposed in the literature, then we develop an RWD energy-consumption model (called the integrated model) based on analyzing the dynamic equilibrium of forces and power consumption in flight phases (including climb, descent, hover, and horizontal flight). Computational experiments involving several commercial RWDs indicate that the integrated model is more effective than several models in the literature. In the case where an RWD completed one flight segment, on average, 87.63% of the battery capacity was consumed in the horizontal flight phase. We also analyzed the effects of the total mass and horizontal airspeed on the RWD endurance and found that a larger mass corresponded to shorter endurance, and in the experimental range of the horizontal airspeed, a higher horizontal airspeed corresponded to longer endurance. Moreover, the total mass affected the RWD endurance more significantly than the horizontal airspeed.

Enforcement of advanced deep learning methods in hand-object pose estimation is an imperative method for grasping the objects safely during the human–robot collaborative tasks. The position and orientation of a hand-object from a two-dimensional image is still a crucial problem under various circumstances like occlusion, critical lighting, and salient region detection and blur images. In this paper, the proposed method uses an enhanced MobileNetV3 with single shot detection (SSD) and YOLOv5 to ensure the improvement in accuracy and without compromising the latency in the detection of hand-object pose and its orientation. To overcome the limitations of higher computation cost, latency and accuracy, the Network Architecture Search and NetAdapt Algorithm is used in MobileNetV3 that perform the network search for parameter tuning and adaptive learning for multiscale feature extraction and anchor box offset adjustment due to auto-variance of weight in the level of each layers. The squeeze-and-excitation block reduces the computation and latency of the model. Hard-swish activation function and feature pyramid networks are used to prevent over fitting the data and stabilizing the training. Based on the comparative analysis of MobileNetV3 with its predecessor and YOLOV5 are carried out, the obtained results are 92.8% and 89.7% of precision value, recall value of 93.1% and 90.2%, mAP value of 93.3% and 89.2%, respectively. The proposed methods ensure better grasping for robots by providing the pose estimation and orientation of hand-objects with tolerance of −1.9 to 2.15 mm along x, −1.55 to 2.21 mm along y, −0.833 to 1.51 mm along z axis and −0.233° to 0.273° along z-axis.

The operational environments in which a mobile robot executes its missions often exhibit nonflat terrain characteristics, encompassing outdoor and indoor settings featuring ramps and slopes. In such scenarios, the conventional methodologies employed for localization encounter novel challenges and limitations. This study delineates a localization framework incorporating ground elevation and incline considerations, deviating from traditional two-dimensional localization paradigms that may falter in such contexts. In our proposed approach, the map encompasses elevation and spatial occupancy information, employing Gridmaps and Octomaps. At the same time, the perception model is designed to accommodate the robot's inclined orientation and the potential presence of ground as an obstacle, besides usual structural and dynamic obstacles. We provide an implementation of our approach fully working with Nav2, ready to replace the baseline Adaptative Monte Carlo Localization (AMCL) approach when the robot is in nonplanar environments. Our methodology was rigorously tested in both simulated environments and through practical application on actual robots, including the Tiago and Summit XL models, across various settings ranging from indoor and outdoor to flat and uneven terrains. Demonstrating exceptional precision, our approach yielded error margins below 10 cm and 0.05 radians in indoor settings and less than 1.0 m in extensive outdoor routes. While our results exhibit a slight improvement over AMCL in indoor environments, the enhancement in performance is significantly more pronounced when compared to three-dimensional simultaneous localization and mapping algorithms. This underscores the considerable robustness and efficiency of our approach, positioning it as an effective strategy for mobile robots tasked with navigating expansive and intricate indoor/outdoor environments.

The cover image is based on the Research Article ASAH: An arc-surface-adsorption hexapod robot with a motion control scheme by Congjun Ma et al., https://doi.org/10.1002/rob.22296

The continuous and close combination of artificial intelligence technology and agriculture promotes the rapid development of smart agriculture, among which the agricultural robot navigation line recognition algorithm based on deep learning has achieved great success in detection accuracy and detection speed. However, there are still many problems, such as the large size of the algorithm is difficult to deploy in hardware equipment, and the accuracy and speed of crop row detection in real farmland environment are low. To solve the above problems, this paper proposed a navigation line extraction algorithm for corn spraying robot based on YOLOv8s-CornNet. First, the Convolution (Conv) module and C2f module of YOLOv8s network are replaced with Depthwise Convolution (DWConv) module and PP-LCNet module respectively to reduce the parameters (Params) and giga floating-point operations per second of the network, so as to achieve the purpose of network lightweight. Second, to reduce the precision loss caused by network lightweight, the spatial pyramid pooling fast module in the backbone network is changed to atrous spatial pyramid pooling faster module to improve the accuracy of network feature extraction. Meanwhile, normalization-based attention module is introduced into the network to improve the network's attention to corn plants. Then the corn plant was located by using the midpoint of the corn plant detection box. Finally, the least square method is used to extract the corn crop row line, and the middle line of the corn crop row line is the navigation line of the corn spraying robot. From the experimental results, it can be seen that the navigation line extraction algorithm proposed in this paper ensures both the real-time and accuracy of the navigation line extraction of the corn spraying robot, which contributes to the development of the visual navigation technology of agricultural robots.

Hyper-redundant manipulators have strong flexibility that benefits from their redundant limb structure. However, a large number of redundant degrees of freedom will also lead the solution of inverse kinematics much more difficult, which restricts their motion performance to some extent. Inspired by the FABRIK (Forward and Backward Reaching Inverse Kinematics) method, an improved inverse kinematics solution method for the hyper-redundant manipulator is proposed. Based on the space vector method, the kinematic model of the manipulator is established to dynamically acquire its endpoint position, and the workspace is further obtained by using the Monte Carlo method. The original search method is optimized, the include angle decoupling mechanism between adjacent links is established to obtain the rotation angles of each joint, and the joint angle limitation is introduced to meet the actual manipulator structural restriction. On this basis, the pose constraint mechanism is established to realize the control of the end-link pose, and the linear degree of freedom is introduced to realize the solution after the directional expansion of the manipulator's workspace. A series of simulation experiments are carried out. In the experiments, the position error of the manipulator's endpoint is always less than 10⁻⁶ mm. Meanwhile, the comparative experimental results show that compared with the original method, the proposed method exhibits higher position accuracy under the condition that the computation time is almost the same. In addition, in the end-link pose constraint experiment and path motion experiments, the pose error of the end-link is always less than 10⁻⁷°, indicating that the end-link pose can also meet the high accuracy requirements under the premise of ensuring high position accuracy. Finally, the prototype experiment further verifies its performance.