Removal of Cu(II) by sodium hexametaphosphate and nano zero-valent iron modified calcium bentonite: characteristic, adsorption performance and mechanism.

Cu (II) is a toxic heavy metal commonly identified in groundwater contaminants. Bentonite-based cutoff wall is the most used method in isolating and adsorbing contaminants, while the bentonite in it easily to fail due to Cu(II) exchange. This study synthesized a novel material through the modification of calcium bentonite (CaB) utilizing sodium hexametaphosphate (SHMP) and nano zero-valent iron (NZVI). The characteristics, adsorption performance, and mechanism of the NZVI/SHMP-CaB were investigated comprehensively. The results showed that SHMP can disperse CaB and reduce flocculation, while NZVI can be further stabilized without agglomeration. The best adsorption performance of NZVI/SHMP-CaB could be obtained at the dosage of 2% SHMP and 4% NZVI. The NZVI/SHMP-CaB exhibited an outstanding removal efficiency of over 60% and 90% at a high Cu(II) concentration (pH = 6, Cu(II) = 300 mg/L) and acidic conditions (pH = 3-6, Cu(II) = 50 mg/L), respectively. The adsorption of Cu(II) by NZVI/SHMP-CaB followed a pseudo-second-order kinetic model, and fitting results from the Freundlich isothermal model suggested that the adsorption process occurred spontaneously. Besides the rapid surface adsorption on the NZVI/SHMP-CaB and ion exchange with interlayer ions in bentonite, the removal mechanism of Cu(II) also involved the chemical reduction to insoluble forms such as Cu0 and Cu2O. The generated FePO4 covered the surface of the homogenized NZVI particles, enhancing the resistance of NZVI/SHMP-CaB to acidic and oxidative environments. This study indicates that NZVI/SHMP-CaB is a promising alternative material which can be used for heavy metal removal from contaminated soil and water.

Human skill knowledge guided global trajectory policy reinforcement learning method.

Traditional trajectory learning methods based on Imitation Learning (IL) only learn the existing trajectory knowledge from human demonstration. In this way, it can not adapt the trajectory knowledge to the task environment by interacting with the environment and fine-tuning the policy. To address this problem, a global trajectory learning method which combinines IL with Reinforcement Learning (RL) to adapt the knowledge policy to the environment is proposed. In this paper, IL is proposed to acquire basic trajectory skills, and then learns the agent will explore and exploit more policy which is applicable to the current environment by RL. The basic trajectory skills include the knowledge policy and the time stage information in the whole task space to help learn the time series of the trajectory, and are used to guide the subsequent RL process. Notably, neural networks are not used to model the action policy and the Q value of RL during the RL process. Instead, they are sampled and updated in the whole task space and then transferred to the networks after the RL process through Behavior Cloning (BC) to get continuous and smooth global trajectory policy. The feasibility and the effectiveness of the method was validated in a custom Gym environment of a flower drawing task. And then, we executed the learned policy in the real-world robot drawing experiment.

Motion planning framework based on dual-agent DDPG method for dual-arm robots guided by human joint angle constraints.

Introduction: Reinforcement learning has been widely used in robot motion planning. However, for multi-step complex tasks of dual-arm robots, the trajectory planning method based on reinforcement learning still has some problems, such as ample exploration space, long training time, and uncontrollable training process. Based on the dual-agent depth deterministic strategy gradient (DADDPG) algorithm, this study proposes a motion planning framework constrained by the human joint angle, simultaneously realizing the humanization of learning content and learning style. It quickly plans the coordinated trajectory of dual-arm for complex multi-step tasks. Methods: The proposed framework mainly includes two parts: one is the modeling of human joint angle constraints. The joint angle is calculated from the human arm motion data measured by the inertial measurement unit (IMU) by establishing a human-robot dual-arm kinematic mapping model. Then, the joint angle range constraints are extracted from multiple groups of demonstration data and expressed as inequalities. Second, the segmented reward function is designed. The human joint angle constraint guides the exploratory learning process of the reinforcement learning method in the form of step reward. Therefore, the exploration space is reduced, the training speed is accelerated, and the learning process is controllable to a certain extent. Results and discussion: The effectiveness of the framework was verified in the gym simulation environment of the Baxter robot's reach-grasp-align task. The results show that in this framework, human experience knowledge has a significant impact on the guidance of learning, and this method can more quickly plan the coordinated trajectory of dual-arm for multi-step tasks.

Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification.

Introduction: As an interactive method gaining popularity, brain-computer interfaces (BCIs) aim to facilitate communication between the brain and external devices. Among the various research topics in BCIs, the classification of motor imagery using electroencephalography (EEG) signals has the potential to greatly improve the quality of life for people with disabilities. Methods: This technology assists them in controlling computers or other devices like prosthetic limbs, wheelchairs, and drones. However, the current performance of EEG signal decoding is not sufficient for real-world applications based on Motor Imagery EEG (MI-EEG). To address this issue, this study proposes an attention-based bidirectional feature pyramid temporal convolutional network model for the classification task of MI-EEG. The model incorporates a multi-head self-attention mechanism to weigh significant features in the MI-EEG signals. It also utilizes a temporal convolution network (TCN) to separate high-level temporal features. The signals are enhanced using the sliding-window technique, and channel and time-domain information of the MI-EEG signals is extracted through convolution. Results: Additionally, a bidirectional feature pyramid structure is employed to implement attention mechanisms across different scales and multiple frequency bands of the MI-EEG signals. The performance of our model is evaluated on the BCI Competition IV-2a dataset and the BCI Competition IV-2b dataset, and the results showed that our model outperformed the state-of-the-art baseline model, with an accuracy of 87.5 and 86.3% for the subject-dependent, respectively. Discussion: In conclusion, the BFATCNet model offers a novel approach for EEG-based motor imagery classification in BCIs, effectively capturing relevant features through attention mechanisms and temporal convolutional networks. Its superior performance on the BCI Competition IV-2a and IV-2b datasets highlights its potential for real-world applications. However, its performance on other datasets may vary, necessitating further research on data augmentation techniques and integration with multiple modalities to enhance interpretability and generalization. Additionally, reducing computational complexity for real-time applications is an important area for future work.

Formulation of PG-FA-L composite modifier for repairing expansive soil based on the statistical mixed design method.

The generation of large amounts of solid waste has led to exploration of solid waste-modified expansive soils; however, the effect of a single solid waste-modified expansive soil is not ideal. This study proposes a composite modification of expansive soils using a PG-FA-L system. Statistical analysis showed that the properties of the cured soil were significantly improved. PG and FA increased soil strength after a certain threshold, and L increased it at all stages. The presence of PG accelerated the volcanic ash reaction. Both PG and FA have a small effect on the swelling of the soil, whereas lime improves it significantly, but has a negative effect after a certain threshold. The 28-day unconfined compressive strength and deformation characteristics were used to derive the relevant regions for roadbed fill requirements and determine the optimum dosage.

Peg-in-hole assembly skill imitation learning method based on ProMPs under task geometric representation.

Introduction: Behavioral Cloning (BC) is a common imitation learning method which utilizes neural networks to approximate the demonstration action samples for task manipulation skill learning. However, in the real world, the demonstration trajectories from human are often sparse and imperfect, which makes it challenging to comprehensively learn directly from the demonstration action samples. Therefore, in this paper, we proposes a streamlined imitation learning method under the terse geometric representation to take good advantage of the demonstration data, and then realize the manipulation skill learning of assembly tasks. Methods: We map the demonstration trajectories into the geometric feature space. Then we align the demonstration trajectories by Dynamic Time Warping (DTW) method to get the unified data sequence so we can segment them into several time stages. The Probability Movement Primitives (ProMPs) of the demonstration trajectories are then extracted, so we can generate a lot of task trajectories to be the global strategy action samples for training the neural networks. Notalby, we regard the current state of the assembly task as the via point of the ProMPs model to get the generated trajectories, while the time point of the via point is calculated according to the probability model of the different time stages. And we get the action of the current state according to the target position of the next time state. Finally, we train the neural network to obtain the global assembly strategy by Behavioral Cloning. Results: We applied the proposed method to the peg-in-hole assembly task in the simulation environment based on Pybullet + Gym to test its task skill learning performance. And the learned assembly strategy was also executed on a real robotic platform to verify the feasibility of the method further. Discussion: According to the result of the experiment, the proposed method achieves higher success rates compared to traditional imitation learning methods while exhibiting reasonable generalization capabilities. It shows that the ProMPs under geometric representation can help the BC method make better use of the demonstration trajectory and thus better learn the task skills.

Learning adaptive reaching and pushing skills using contact information.

In this paper, we propose a deep reinforcement learning-based framework that enables adaptive and continuous control of a robot to push unseen objects from random positions to the target position. Our approach takes into account contact information in the design of the reward function, resulting in improved success rates, generalization for unseen objects, and task efficiency compared to policies that do not consider contact information. Through reinforcement learning using only one object in simulation, we obtain a learned policy for manipulating a single object, which demonstrates good generalization when applied to the task of pushing unseen objects. Finally, we validate the effectiveness of our approach in real-world scenarios.

Air sparging remediation of VOCs contaminated low-permeability soil based on pressure gradient control.

Air sparging (AS) is deemed unacceptable for remediating VOCs contaminated soil with low-permeability. To improve air flow and contaminant removal in sparging process, an original approach, termed as pressure gradient-enhanced air sparging (PGEAS) approach, is proposed by controlling pressure gradient in soil. Then the remediation efficiency, mass transfer characteristics, and remediation mechanism are investigated. Results showed that, the PGEAS approach accelerates gaseous contaminant exhaust, reduces residue contamination in soil, and promotes total contaminant removal, finally results in an improved remediation efficiency compared to the conventional approach. Controlled by sparging pressure and flow distance, the pressure gradient is created in soil, and a critical value needs to be exceeded to enhance the VOCs removal and mass transfer characteristics. The measured results of pore pressure and liquid saturation confirm a notable pressure gradient and drainage behavior in soil, which indicate the massive air subchannel formation during air sparging. At a two-dimensional scale, discrete distributions of contaminant concentrations in exhaust air and soil are presented, the removal extent and area are both enhanced using the PGEAS approach with a pressure gradient higher than the critical value. The reached conclusions are of great importance to contaminant removal in heterogeneous stratigraphy at sites.

Mass transfer enhancement of air sparging on VOCs contaminated low-permeability soil by establishing pressure gradient.

As one of the most effective methods for remediating VOCs contaminated site, air sparging technology is not suitable to low-permeability soil due to the poor remediation efficiency. To solve this problem, an improved approach aiming for mass transfer enhancement by establishing pressure gradient in soil is proposed in this study, and the remediation efficiency, removal mechanism, as well as the mass transfer characteristic are comprehensively investigated. Test results showed that, using the proposed approach significantly reduced the time for exhaust air contaminants reaching concentration equilibrium, and improved the contaminant removal zone and extent in soil, which were especially strengthened at sparging pressures higher than 40 kPa. The total contaminant removal rate was improved by introducing the proposed approach, with a maximum improved removal rate of 23.7% at 100 kPa sparging pressure. In mechanism analysis, the recorded changes in total pore pressure and average liquid saturation illustrated the pressure drop and discrete drainage phenomena, confirming the pressure gradient and air sub-channels formed in low-permeability soil. Finally, contaminant mass transfer characteristic was quantitatively analyzed using the lumped parameter model, in which the mass transfer coefficient and the air channel influencing fraction were enhanced almost fourfold and fivefold respectively by introducing the proposed approach. Compared to the conventional approach, the improved remediation efficiency using the proposed approach tackled the in-situ remediation challenge on low-permeability soil, and further expanded the application scope of air sparging technology on VOC contaminated site.

Non-uniform illumination underwater image enhancement via events and frame fusion.

Absorption and scattering by aqueous media can attenuate light and cause underwater optical imagery difficulty. Artificial light sources are usually used to aid deep-sea imaging. Due to the limited dynamic range of standard cameras, artificial light sources often cause underwater images to be underexposed or overexposed. By contrast, event cameras have a high dynamic range and high temporal resolution but cannot provide frames with rich color characteristics. In this paper, we exploit the complementarity of the two types of cameras to propose an efficient yet simple method for image enhancement of uneven underwater illumination, which can generate enhanced images containing better scene details and colors similar to standard frames. Additionally, we create a dataset recorded by the Dynamic and Active-pixel Vision Sensor that includes both event streams and frames, enabling testing of the proposed method and frame-based image enhancement methods. The experimental results conducted on our dataset with qualitative and quantitative measures demonstrate that the proposed method outperforms the compared enhancement algorithms.

Synergistic solidification of lead-contaminated soil by magnesium oxide and microorganisms.

Although microbially induced carbonate precipitation (MICP) technology effectively promotes the remediation of heavy metal contaminated soils in low concentrations, the high concentration of heavy metals has a toxic effect on microorganisms, which leads to the decline of carbonate yield and makes the soil strength and environmental safety after remediation no up to the standard. This study describes the synergistic curing effect of MgO and microorganisms on soil contaminated with high concentrations of heavy metals. The experimental results with MgO showed 2-6 times increase in unconfined compressive strength (UCS) compared to bio-cemented samples without MgO. Toxicity characteristic leaching procedure experiments indicated that Pb-contaminated soil at 10,000 mg/kg with quantitative MgO for synergistic solidification could meet the international solid waste disposal standards, which leachable Pb2+ are less than 5 mg/L. In addition, the microscopic results showed that the introduction of MgO promoted the formation of magnesium calcite and dolomite, improved the solidification efficiency of heavy metal contaminants, and demonstrated the presence of Pb2+ in carbonate minerals. This study suggests that MgO and microorganisms have broad application prospects for synergistic solidification of Pb2+ soil.

American Sign Language Translation Using Wearable Inertial and Electromyography Sensors for Tracking Hand Movements and Facial Expressions.

A sign language translation system can break the communication barrier between hearing-impaired people and others. In this paper, a novel American sign language (ASL) translation method based on wearable sensors was proposed. We leveraged inertial sensors to capture signs and surface electromyography (EMG) sensors to detect facial expressions. We applied a convolutional neural network (CNN) to extract features from input signals. Then, long short-term memory (LSTM) and transformer models were exploited to achieve end-to-end translation from input signals to text sentences. We evaluated two models on 40 ASL sentences strictly following the rules of grammar. Word error rate (WER) and sentence error rate (SER) are utilized as the evaluation standard. The LSTM model can translate sentences in the testing dataset with a 7.74% WER and 9.17% SER. The transformer model performs much better by achieving a 4.22% WER and 4.72% SER. The encouraging results indicate that both models are suitable for sign language translation with high accuracy. With complete motion capture sensors and facial expression recognition methods, the sign language translation system has the potential to recognize more sentences.

Remediation characteristics of surfactant-enhanced air sparging (SEAS) technology on volatile organic compounds contaminated soil with low permeability.

Surfactant-enhanced air sparging (SEAS) is an effective technology for the remediation of volatile organic compounds contamination of medium and high-permeability soil, though applying SEAS to low-permeability soil contamination has rarely been explored. In this study, a series of two-dimensional physical model tests were designed to explore the feasibility and remediation characteristics of SEAS on low-permeability soil. In the test results, the incorporation and increase in surfactant concentration promoted air channel formation in the low-permeability soil, finally reduced the capillary breakthrough pressure and improved the airflow rate. The majority of the exhausted gaseous contaminants were distributed along the horizontal direction, differing from the results observed in medium and high-permeability soils. The exhausted gaseous contaminant concentration changed slightly when the sparging pressure and surfactant concentration increased at relatively low levels and increased as the sparging pressure and surfactant concentration increased further. Increasing the air sparging pressure without surfactant incorporation or with a low surfactant concentration cannot effectively remove the contaminant, while the removal efficiency can be enhanced with further increases in surfactant concentration. The discrete remediation characteristics had been confirmed during SEAS application on low-permeability soil, then the relationships between the ratios of remediation area and remediation extent under different surfactant concentrations and sparging pressures were established for remediation efficiency evaluation. Using this method, the discrete remediation characteristics can be recreated once the surfactant concentration and the sparging pressure were chosen. On the other side, targeted improvements in the remediation area or extent can be achieved by controlling the surfactant concentration and sparging pressure. Through this study, SEAS technology and the proposed evaluation method were successfully implemented in soil with hydraulic conductivity around 9E-7 m/s, which expanded the application scope of SEAS technology for contaminant removal.

Biocementation of Pyrite Tailings Using Microbially Induced Calcite Carbonate Precipitation.

Tailing sand contains a large number of heavy metals and sulfides that are prone to forming acid mine drainage (AMD), which pollutes the surrounding surface environment and groundwater resources and damages the ecological environment. Microbially induced calcium carbonate precipitation (MICP) technology can biocement heavy metals and sulfides in tailing sand and prevent pollution via source control. In this study, through an unconfined compressive strength test, permeability test, and toxic leaching test (TCLP), the curing effect of MICP was investigated in the laboratory and the effect of grouting rounds on curing was also analyzed. In addition, the curing mechanism of MICP was studied by means of Fourier transform infrared spectroscopy (FTIR), thermogravimetric analysis (TGA), X-ray diffraction spectroscopy (XRD), and scanning electron microscopy (SEM). The experimental results showed that MICP could induce calcium carbonate precipitation through relatively complex biochemical and physicochemical reactions to achieve the immobilization of heavy metals and sulfides and significantly reduce the impact of tailing sand on the surrounding environment.

Creating Better Collision-Free Trajectory for Robot Motion Planning by Linearly Constrained Quadratic Programming.

Many algorithms in probabilistic sampling-based motion planning have been proposed to create a path for a robot in an environment with obstacles. Due to the randomness of sampling, they can efficiently compute the collision-free paths made of segments lying in the configuration space with probabilistic completeness. However, this property also makes the trajectories have some unnecessary redundant or jerky motions, which need to be optimized. For most robotics applications, the trajectories should be short, smooth and keep away from obstacles. This paper proposes a new trajectory optimization technique which transforms a polygon collision-free path into a smooth path, and can deal with trajectories which contain various task constraints. The technique removes redundant motions by quadratic programming in the parameter space of trajectory, and converts collision avoidance conditions to linear constraints to ensure absolute safety of trajectories. Furthermore, the technique uses a projection operator to realize the optimization of trajectories which are subject to some hard kinematic constraints, like keeping a glass of water upright or coordinating operation with dual robots. The experimental results proved the feasibility and effectiveness of the proposed method, when it is compared with other trajectory optimization methods.

Exoskeleton Active Walking Assistance Control Framework Based on Frequency Adaptive Dynamics Movement Primitives.

This paper introduces a novel exoskeleton active walking assistance control framework based on frequency adaptive dynamics movement primitives (FADMPs). The FADMPs proposed in this paper is an online learning and prediction algorithm which is able to online estimate the fundamental frequency of human joint trajectory, learn the shape of joint trajectory and predict the future joint trajectory during walking. The proposed active walking assistance control framework based on FADMPs is a model-based controller which relies on the human joint torque estimation. The assistance torque provided by exoskeleton is estimated by human lower limb inverse dynamics model which is sensitive to the noise in the joint motion trajectory. To estimate a smooth joint torque profile, the joint motion trajectory must be filtered first by a lowpass filter. However, lowpass filter will introduce an inevitable phase delay in the filtered trajectory. Both simulations and experiments in this paper show that the phase delay has a significant effect on the performance of exoskeleton active assistance. The active assistant control framework based on FADMPs aims at improving the performance of active assistance control by compensating the phase delay. Both simulations and experiments on active walking assistance control show that the performance of active assistance control can be further improved when the phase delay in the filtered trajectory is compensated by FADMPs.

Acid rain leaching behavior of Zn-contaminated soils solidified/stabilized using cement-soda residue.

Cement-soda residue (CSR) has been proven to be an effective binder for treating heavy metal-contaminated soils, and the durability is its most important characteristic. In this study, the effects of acid rain (AR) on the leaching behavior of CSR-solidified/stabilized, zinc-contaminated soils were investigated using flexible-wall soil column leaching tests. After leaching, some parameters were determined such as the unconfined compressive strength (UCS) and permeability coefficient of the samples, the concentrations of Zn2+ and Ca2+ in the filtrate. The test results showed that after AR leaching, the UCS of the solidified soil samples decreased and the permeability coefficient increased, while the zinc concentration in the filtrate always met the third grade of the applicable standard, the Chinese National Environmental Quality Standards (<1 mg⋅L-1). To reveal the binding mechanism, scanning electron microscopy (SEM) and mercury intrusion testing (MIP) were used to observe the microscopic characteristics of the soil samples. At the micro scale, the MIP and SEM results confirmed that the hydration products in the soil samples-hydrated calcium silicate, calcium hydroxide, and calcium zincate hydrate-partially dissolved during AR leaching, resulting in the loss of their internal structure. Consequently, the high alkalinity of the soda residue contributed to H+ neutralization in the AR leaching agent, indicating that soda residue can not only solidify heavy metal zinc ions effectively but can also buffer the erosive effect of AR on soil.

A Bionic Spatial Cognition Model and Method for Robots Based on the Hippocampus Mechanism.

The hippocampus and its accessory are the main areas for spatial cognition. It can integrate paths and form environmental cognition based on motion information and then realize positioning and navigation. Learning from the hippocampus mechanism is a crucial way forward for research in robot perception, so it is crucial to building a calculation method that conforms to the biological principle. In addition, it should be easy to implement on a robot. This paper proposes a bionic cognition model and method for mobile robots, which can realize precise path integration and cognition of space. Our research can provide the basis for the cognition of the environment and autonomous navigation for bionic robots.

Effects of surfactant injection position on the airflow pattern and contaminant removal efficiency of surfactant-enhanced air sparging.

Surfactant-enhanced air sparging (SEAS) is an effective remediation technique for VOCs-contaminated soil. In this study, three types of tests are performed to investigate the effects of the surfactant injection position on the airflow pattern, contaminant removal efficiency, and airflow path control. The three tests are conventional air sparging (CAS), entire SEAS (ESEAS), where the surfactant is incorporated into the entire contaminated soil, and local SEAS (LSEAS), where the surfactant is injected locally at different positions. With increasing distance between the injection position and the central axis, the LSEAS test results approach the results measured in the CAS test. When the surfactant is injected directly at the central axis, a high contaminant removal rate of 89% is obtained, which is even higher than that obtained for the ESEAS test. As the injection position moves away from the central axis, the removal rate decreases. Furthermore, when the injection position is close to the sparging point, the surfactant can successfully control the airflow path. Based on the test results, a critical distance between the surfactant injection position and sparging point exists where high remediation efficiency can be achieved. This optimal surfactant injection position is specific to each contamination site.

Spatial Topological Relation Analysis for Cluttered Scenes.

The spatial topological relations are the foundation of robot operation planning under unstructured and cluttered scenes. Defining complex relations and dealing with incomplete point clouds from the surface of objects are the most difficult challenge in the spatial topological relation analysis. In this paper, we presented the classification of spatial topological relations by dividing the intersection space into six parts. In order to improve accuracy and reduce computing time, convex hulls are utilized to represent the boundary of objects and the spatial topological relations can be determined by the category of points in point clouds. We verified our method on the datasets. The result demonstrated that we have great improvement comparing with the previous method.