ABSTRACT
The labor shortage and rising costs in the greenhouse industry have driven the development of automation, with the core of autonomous operations being positioning and navigation technology. However, precise positioning in complex greenhouse environments and narrow aisles poses challenges to localization technologies. This study proposes a multi-sensor fusion positioning and navigation robot based on ultra-wideband (UWB), an inertial measurement unit (IMU), odometry (ODOM), and a laser rangefinder (RF). The system introduces a confidence optimization algorithm based on weakening non-line-of-sight (NLOS) for UWB positioning, obtaining calibrated UWB positioning results, which are then used as a baseline to correct the positioning errors generated by the IMU and ODOM. The extended Kalman filter (EKF) algorithm is employed to fuse multi-sensor data. To validate the feasibility of the system, experiments were conducted in a Chinese solar greenhouse. The results show that the proposed NLOS confidence optimization algorithm significantly improves UWB positioning accuracy by 60.05%. At a speed of 0.1 m/s, the root mean square error (RMSE) for lateral deviation is 0.038 m and for course deviation is 4.030°. This study provides a new approach for greenhouse positioning and navigation technology, achieving precise positioning and navigation in complex commercial greenhouse environments and narrow aisles, thereby laying a foundation for the intelligent development of greenhouses.
ABSTRACT
Excessive invalid explorations at the beginning of training lead deep reinforcement learning process to fall into the risk of overfitting, further resulting in spurious decisions, which obstruct agents in the following states and explorations. This phenomenon is termed primacy bias in online reinforcement learning. This work systematically investigates the primacy bias in online reinforcement learning, discussing the reason for primacy bias, while the characteristic of primacy bias is also analyzed. Besides, to learn a policy generalized to the following states and explorations, we develop an online reinforcement learning framework, termed self-distillation reinforcement learning (SDRL), based on knowledge distillation, allowing the agent to transfer the learned knowledge into a randomly initialized policy at regular intervals, and the new policy network is used to replace the original one in the following training. The core idea for this work is distilling knowledge from the trained policy to another policy can filter biases out, generating a more generalized policy in the learning process. Moreover, to avoid the overfitting of the new policy due to excessive distillations, we add an additional loss in the knowledge distillation process, using L2 regularization to improve the generalization, and the self-imitation mechanism is introduced to accelerate the learning on the current experiences. The results of several experiments in DMC and Atari 100k suggest the proposal has the ability to eliminate primacy bias for reinforcement learning methods, and the policy after knowledge distillation can urge agents to get higher scores more quickly.
ABSTRACT
Three-dimensional (3D) printing technology is advantageous in the fast prototyping of complex structures, but its utilization in functional material fabrication is still limited due to a lack of activation capability. To fabricate and activate the functional material of electrets, a synchronized 3D printing and corona charging method is presented to prototype and polarize polylactic acid electrets in one step. By upgrading the 3D printer nozzle and incorporating a needle electrode to apply high voltage, parameters such as needle tip distance and applied voltage level were compared and optimized. Under different experimental conditions, the average surface distribution in the center of the samples was -1498.87 V, -1115.73 V, and -814.51 V. Scanning electron microscopy results showed that the electric field contributes to keeping the printed fiber structure straight. The polylactic acid electrets exhibited relatively uniform surface potential distribution on a sufficiently large sample surface. In addition, the average surface potential retention rate was improved by 12.021-fold compared to ordinary corona-charged samples. The above advantages are unique to the 3D-printed and polarized polylactic acid electrets, proving that the proposed method is suitable for quickly prototyping and effectively polarizing the polylactic acid electrets simultaneously.
ABSTRACT
In view of the differences in appearance and the complex backgrounds of crop diseases, automatic identification of field diseases is an extremely challenging topic in smart agriculture. To address this challenge, a popular approach is to design a Deep Convolutional Neural Network (DCNN) model that extracts visual disease features in the images and then identifies the diseases based on the extracted features. This approach performs well under simple background conditions, but has low accuracy and poor robustness under complex backgrounds. In this paper, an end-to-end disease identification model composed of a disease-spot region detector and a disease classifier (YOLOv5s + BiCMT) was proposed. Specifically, the YOLOv5s network was used to detect the disease-spot regions so as to provide a regional attention mechanism to facilitate the disease identification task of the classifier. For the classifier, a Bidirectional Cross-Modal Transformer (BiCMT) model combining the image and text modal information was constructed, which utilizes the correlation and complementarity between the features of the two modalities to achieve the fusion and recognition of disease features. Meanwhile, the problem of inconsistent lengths among different modal data sequences was solved. Eventually, the YOLOv5s + BiCMT model achieved the optimal results on a small dataset. Its Accuracy, Precision, Sensitivity, and Specificity reached 99.23, 97.37, 97.54, and 99.54%, respectively. This paper proves that the bidirectional cross-modal feature fusion by combining disease images and texts is an effective method to identify vegetable diseases in field environments.
ABSTRACT
The disease image recognition models based on deep learning have achieved relative success under limited and restricted conditions, but such models are generally subjected to the shortcoming of weak robustness. The model accuracy would decrease obviously when recognizing disease images with complex backgrounds under field conditions. Moreover, most of the models based on deep learning only involve characterization learning on visual information in the image form, while the expression of other modal information rather than the image form is often ignored. The present study targeted the main invasive diseases in tomato and cucumber as the research object. Firstly, in response to the problem of weak robustness, a feature decomposition and recombination method was proposed to allow the model to learn image features at different granularities so as to accurately recognize different test images. Secondly, by extracting the disease feature words from the disease text description information composed of continuous vectors and recombining them into the disease graph structure text, the graph convolutional neural network (GCN) was then applied for feature learning. Finally, a vegetable disease recognition model based on the fusion of images and graph structure text was constructed. The results show that the recognition accuracy, precision, sensitivity, and specificity of the proposed model were 97.62, 92.81, 98.54, and 93.57%, respectively. This study improved the model robustness to a certain extent, and provides ideas and references for the research on the fusion method of image information and graph structure information in disease recognition.
ABSTRACT
The quantum anomalous Hall effect (QAHE), carrying dissipationless chiral edge states, occurs without any magnetic field. Two main strategies were proposed to host QAHE: the magnetic topological insulator thin films and graphene systems. Only the former one was realized in experiment at low temperature. In this paper, by dealing with the two-dimensional electron gas with an anti-dot lattice, a realistic platform is proposed to host the QAHE with both Chern number [Formula: see text] and [Formula: see text]. Based on the calculation of the Berry curvature integral and spacial wave function, the topological nature of the QAH edge states is well demonstrated. In the QAH region, the conductance shows quantized plateaus and their values are robust against Anderson disorder. In addition, we have also studied the effects of the size and shape of the anti-dot lattice on QAHE and they provide extra manners to adjust the system parameters. Taking the advantages of the well developed micro-manufacture technique in semiconductors, the proposal is experimentally accessible in micro-scale.
ABSTRACT
Highly efficient proton conductors, polyoxometalate-poly(ethylene glycol) (POM-PEG) hybrid nanocomposites, have been synthesized by encapsulating a single PEG chain inside the 1D nanochannel defined by the frameworks of POMs. By employing two types of neutron scattering techniques complemented by thermal analysis, we prove that in a nanochannel a single PEG chain stays as a distorted helix. More importantly, we reveal that the PEG segments perform a localized longitudinal random walk and quantitatively show the strong correlation between the local motion of PEG and the macroscopic proton conduction of the material. On the basis of these spatial-temporal characteristics, a microscopic picture for the proton conduction process of POM-PEG hybrid materials is proposed.
ABSTRACT
Here, charge-storage nonvolatile organic field-effect transistor (OFET) memory devices based on interfacial self-assembled molecules are proposed. The functional molecules contain various aromatic amino moieties (N-phenyl-N-pyridyl amino- (PyPN), N-phenyl amino- (PN), and N,N-diphenyl amino- (DPN)) which are linked by a propyl chain to a triethoxysilyl anchor group and act as the interface modifiers and the charge-storage elements. The PyPN-containing pentacene-based memory device (denoted as PyPN device) presents the memory window of 48.43 V, while PN and DPN devices show the memory windows of 24.88 and 8.34 V, respectively. The memory characteristic of the PyPN device can remain stable along with 150 continuous write-read-erase-read cycles. The morphology analysis confirms that three interfacial layers show aggregation due to the N atomic self-catalysis and hydrogen bonding effects. The large aggregate-covered PyPN layer has the full contact area with the pentacene molecules, leading to the high memory performance. In addition, the energy level matching between PyPN molecules and pentacene creates the smallest tunneling barrier and facilitates the injection of the hole carriers from pentacene to the PyPN layer. The experimental memory characteristics are well in agreement with the computational calculation.