Population growth, climate change, and the worldwide COVID-19 pandemic are imposing increasing pressure on global agricultural production. The challenge of increasing crop yield while ensuring sustainable development of environmentally friendly agriculture is a common issue throughout the world. Autonomous systems, sensing technologies, and artificial intelligence offer great opportunities to tackle this issue. In precision agriculture (PA), non-destructive and non-invasive remote and proximal sensing methods have been widely used to observe crops in visible and invisible spectra. Nowadays, the integration of high-performance imagery sensors (e.g., RGB, multispectral, hyperspectral, thermal, and SAR) and unmanned mobile platforms (e.g., satellites, UAVs, and terrestrial agricultural robots) are yielding a huge number of high-resolution farmland images, in which rich crop information is compressed. However, this has been accompanied by challenges, i.e., ways to swiftly and efficiently making full use of these images, and then, to perform fine crop management based on information-supported decision making. In the past few years, deep learning (DL) has shown great potential to reshape many industries because of its powerful capabilities of feature learning from massive datasets, and the agriculture industry is no exception. More and more agricultural scientists are paying attention to applications of deep learning in image-based farmland observations, such as land mapping, crop classification, biotic/abiotic stress monitoring, and yield prediction. To provide an update on these studies, we conducted a comprehensive investigation with a special emphasis on deep learning in multiscale agricultural remote and proximal sensing. Specifically, the applications of convolutional neural network-based supervised learning (CNN-SL), transfer learning (TL), and few-shot learning (FSL) in crop sensing at land, field, canopy, and leaf scales are the focus of this review. We hope that this work can act as a reference for the global agricultural community regarding DL in PA and can inspire deeper and broader research to promote the evolution of modern agriculture.

Understanding the effects of different hip assistance modes is a fundamental step in the process of designing hip assistance devices and controllers that can provide better performance in terms of metabolic cost. We have developed and tested a soft exoskeleton for hip assistance, which includes three assistance modes: hip extension assistance (HEA), hip flexion assistance (HFA), and hip extension and flexion assistance (HEFA). A proportional derivative (PD) iterative learning controller based on the feedforward model was proposed to control the assistive force accurately. The three hip assistance modes were evaluated on seven male subjects walking on a treadmill at a speed of 5 km/h in two scenarios--first with a 15-kg backpack and then without any backpack. The net metabolic costs could be reduced during the loaded condition, compared with those under no exoskeleton condition, by 9.95%, 6.25%, and 15.28% for HEA, HFA, and HEFA, respectively. The reductions were found significant in HEA (p=0.048) and HEFA (p=0.005) modes, while the HFA mode (p=0.202) was not found statistically significant. It indicates that the HEA and HEFA modes with the soft exoskeleton provide more benefit to the net metabolic cost compared with the HFA mode. The net metabolic costs reduced during the unloaded condition were 9.21%, 2.58%, and 13.05% for HEA, HFA, and HEFA, respectively. The improvements in the walking efficiency during both the conditions with the developed soft exoskeleton are demonstrated.

To solve the complexity of the traditional motion intention recognition method using a multi-mode sensor signal and the lag of the recognition process, in this paper, an inertial sensor-based motion intention recognition method for a soft exoskeleton is proposed. Compared with traditional motion recognition, in addition to the classic five kinds of terrain, the recognition of transformed terrain is also added. In the mode acquisition, the sensors’ data in the thigh and calf in different motion modes are collected. After a series of data preprocessing, such as data filtering and normalization, the sliding window is used to enhance the data, so that each frame of inertial measurement unit (IMU) data keeps the last half of the previous frame’s historical information. Finally, we designed a deep convolution neural network which can learn to extract discriminant features from temporal gait period to classify different terrain. The experimental results show that the proposed method can recognize the pose of the soft exoskeleton in different terrain, including walking on flat ground, going up and downstairs, and up and down slopes. The recognition accuracy rate can reach 97.64%. In addition, the recognition delay of the conversion pattern, which is converted between the five modes, only accounts for 23.97% of a gait cycle. Finally, the oxygen consumption was measured by the wearable metabolic system (COSMED K5, The Metabolic Company, Rome, Italy), and compared with that without an identification method; the net metabolism was reduced by 5.79%. The method in this paper can greatly improve the control performance of the flexible lower extremity exoskeleton system and realize the natural and seamless state switching of the exoskeleton between multiple motion modes according to the human motion intention.

The loaded walking ability of people can be enhanced by lower limb exoskeleton. How to avoid lower limb joint injuries while improving walking efficiency is a major challenge for loaded walking assistance. Inspired by the muscle-skeleton working mechanism of human, we proposed a lower limb exoskeleton with rigid and soft structure for active hip extension assistance and passive load transfer assistance. Its motion flexibility, load transfer ability and metabolic cost were investigated. Five motions including jumping jack, sit down, crouch, across obstacle, and forward lunge were realized by the wearer. Under the conditions of quiet standing and dynamic walking, the percentages indicating the degree of load transfer to the ground reached up to 88% and 67%, respectively. Compared to the condition of no exoskeleton, the net metabolic reductions of 20kg-loaded walking in three experimental setups, namely, active-passive assistance on, active exosuit assistance only, and active assistance off-passive assistance on, achieved 12.8%, 8.5% and 3.7%, individually. The results demonstrate that our rigid-soft lower limb exoskeleton presents outperformance in loaded walking assistance.

Walking on different terrains leads to different biomechanics, which motivates the development of exoskeletons for assisting on walking according to the type of a terrain. The design of a lightweight soft exoskeleton that simultaneously assists multiple joints in the lower limb is presented in this paper. It is used to assist both hip and knee joints in a single system, the assistance force is directly applied to the hip joint flexion and the knee joint extension, while indirectly to the hip extension also. Based on the biological torque of human walking at three different slopes, a novel strategy is developed to improve the performance of assistance. A parameter optimal iterative learning control (POILC) method is introduced to reduce the error generated due to the difference between the wearing position and the biological features of the different wearers. In order to obtain the metabolic rate, three subjects walked on a treadmill, for 10 min on each terrain, at a speed of 4 km/h under both conditions of wearing and not wearing the soft exoskeleton. Results showed that the metabolic rate was decreased with the increasing slope of the terrain. The reductions in the net metabolic rate in the experiments on the downhill, flat ground, and uphill were, respectively, $9.86\%$, $12.48\%$, and $22.08\%$ compared to the condition of not wearing the soft exoskeleton, where their corresponding absolute values were $0.28$ W/kg, $0.72$ W/kg, and $1.60$ W/kg.

In the lower limb exoskeleton assistance system, motion intention understanding based on biological signals is the human-computer interface’s (HMI) key technology. Due to the close coupling of human and machine, wheelchair-type control modes (combination of motion intentions and switches of different actions) are not applicable. For example, the right/left-hand motor imagery (MI) controls the exoskeleton to move forward/stop. There is a mismatch between MI-based control instructions and actual actions because the forward process alternates between left and right. Therefore, this study aims to design a reasonable HMI for a lower limb exoskeleton assistance system and to prove its rationality and effectiveness. We have designed a new HMI combining the human walking process and multimodal biosignals. Experimental data were collected from 14 subjects. We use feature-based and end-to-end analysis methods to analyze multimode signals. In a feature-based analysis, the advantage of using sEMG to distinguish between different movements does not apply to distinguishing different magnitudes of the same movement. A time-frequency subband selection method based on difference patterns is designed for EEG signals in the feature-based analysis. The fusion of EEG and sEMG is implemented to complement each other. The average recognition rate of the multimodal HMI was evaluated to be up to 89.5%, which is 12% and 7.8% higher than that of EEG and sEMG, respectively. Based on end-to-end analysis, a time-domain translation strategy was used to expand the sample and obtain a cross-subject identification rate of 83.6%. All the results indicate that the designed HMI is rational and effective, and there exists potential for practical application.