Empowering High-Level Spinal Cord Injury Patients in Daily Tasks With a Hybrid Gaze and FEMG-Controlled Assistive Robotic System.

Individuals with high-level spinal cord injuries often face significant challenges in performing essential daily tasks due to their motor impairments. Consequently, the development of reliable, hands-free human-computer interfaces (HCI) for assistive devices is vital for enhancing their quality of life. However, existing methods, including eye-tracking and facial electromyogram (FEMG) control, have demonstrated limitations in stability and efficiency. To address these shortcomings, this paper presents an innovative hybrid control system that seamlessly integrates gaze and FEMG signals. When deployed as a hybrid HCI, this system has been successfully used to assist individuals with high-level spinal cord injuries in performing activities of daily living (ADLs), including tasks like eating, pouring water, and pick-and-place. Importantly, our experimental results confirm that our hybrid control method expedites the performance in pick-place tasks, achieving an average completion time of 34.3 s, which denotes a 28.8% and 21.8% improvement over pure gaze-based control and pure FEMG-based control, respectively. With practice, participants experienced up to a 44% efficiency improvement using the hybrid control method. This state-of-the-art system offers a highly precise and reliable intention interface, suitable for daily use by individuals with high-level spinal cord injuries, ultimately enhancing their quality of life and independence.

Multi-dimensional microfluidic paper-based analytical devices (µPADs) for noninvasive testing: A review of structural design and applications.

The rapid emergence of microfluidic paper-based devices as point-of-care testing (POCT) tools for early disease diagnosis and health monitoring, particularly in resource-limited areas, holds immense potential for enhancing healthcare accessibility. Leveraging the numerous advantages of paper, such as capillary-driven flow, porous structure, hydrophilic functional groups, biodegradability, cost-effectiveness, and flexibility, it has become a pivotal choice for microfluidic substrates. The repertoire of microfluidic paper-based devices includes one-dimensional lateral flow assays (1D LFAs), two-dimensional microfluidic paper-based analytical devices (2D µPADs), and three-dimensional (3D) µPADs. In this comprehensive review, we provide and examine crucial information related to paper substrates, design strategies, and detection methods in multi-dimensional microfluidic paper-based devices. We also investigate potential applications of microfluidic paper-based devices for detecting viruses, metabolites and hormones in non-invasive samples such as human saliva, sweat and urine. Additionally, we delve into capillary-driven flow alternative theoretical models of fluids within the paper to provide guidance. Finally, we critically examine the potential for future developments and address challenges for multi-dimensional microfluidic paper-based devices in advancing noninvasive early diagnosis and health monitoring. This article showcases their transformative impact on healthcare, paving the way for enhanced medical services worldwide.

Design and Synthesis of a Robust and Multifunctional Superhydrophobic Coating with a Three-Dimensional Network Structure on a Paper-Based Material.

A fundamental challenge in artificial superhydrophobic papers is their poor resistance to mechanical abrasion, which limits their practical application in different fields. Herein, a robust and multifunctional superhydrophobic paper is successfully fabricated via a facile spraying method by combining silver nanowires and fluorinated titania nanoparticles through a common paper sizing agent (alkyl ketene dimer) onto paper. It is shown that the surface of the paper-based material presents a three-dimensional network structure due to the cross-linking of silver nanowires with a high aspect ratio. Further hydrophilic and hydrophobic performance test results show that it exhibits exceptional water repellency, with a desirable static contact angle of 165° and roll-off angle of 6.2°. The superhydrophobic paper showcases excellent mechanical durability and maintains its superhydrophobicity even after enduring 130 linear sandpaper abrasion cycles or high-velocity water jetting impact benefited from interfacial van der Waals and hydrogen bonding. Simultaneously, the robust superhydrophobic surface can effectively prevent the penetration of acid or alkali solutions, as well as UV light, resulting in excellent chemical stability. Additionally, the superhydrophobic paper offers supplementary features such as self-cleaning, electrical conductivity, and antibacterial capability. Further development of this strategy paves a way toward next-generation superhydrophobic paper composed of nanostructures and characterized by multiple (or additional) functionalities.

A novel process for efficient utilization of bamboo fiber resource in dissolving pulp production by fiber fractionation: Laboratory study and mill trials.

The rational use of bamboo to make dissolving pulp can offer up new opportunities for cellulose production, alleviating wood scarcity. Bamboo contains a high content of non-fiber cells, which presents technical challenges in dissolving pulp production by the conventional process. In this study, a process concept of separating hemicelluloses is presented by fiber fractionation and purification for cleaner production of bamboo dissolving pulp: bamboo kraft pulp was fractionated into long-fiber and short-fiber fractions. The cellulose-rich long-fiber fraction was converted to dissolving pulp by further purification treatment with acid hydrolysis and cold caustic extraction. The hemicellulose-rich short-fiber fraction was used for papermaking. The laboratory results were confirmed by those from mill trials. The combined pulp yield (dissolving pulp + paper-grade pulp) reached 49 %, which was significantly higher than that of the conventional pre-hydrolysis kraft pulping process. Furthermore, the quality of dissolving pulp was higher due to inherently higher cellulose content of long-fiber fraction.

Biomechanical Consequences of Walking With the Suspended Backpacks.

OBJECTIVE: This article aimed to investigate the biomechanical mechanisms underlying the energetic advantages of the suspended backpacks during load carriage. METHODS: In this study, we examined eight adults walking with a 15 kg load at 5 km/h with a designed suspended backpack, in which the load could be switched to locked and suspended with four combinations of stiffness. Mechanical work and metabolic cost were measured during load carriage. RESULTS: The results showed that the suspended backpacks led to an average reduction of 23.35% in positive work, 24.77% in negative work, and a 12.51% decrease in metabolic cost across all suspended load conditions. Notably, the decreased mechanical work predominantly occurred during single support (averaging 84.19% and 71.16% for positive and negative work, respectively), rather than during double support. CONCLUSION: Walking with the suspended backpack induced a phase shift between body movement and load movement, altering the human-load interaction. This adjustment caused the body and load to move against each other, resulting in flatter trajectories of the human-load system center of mass (COM) velocities and corresponding profiles in ground reaction forces (GRFs), along with reduced vertical excursions of the trunk. Consequently, this interplay led to flatter trajectories in mechanical work rate and reduced mechanical work, ultimately contributing to the observed reduction in energetic expenditure. SIGNIFICANCE: Understanding these mechanisms is essential for the development of more effective load-carrying devices and strategies in various applications, particularly for enhancing walking abilities during load carriage.

A Probability Fusion Approach for Foot Placement Prediction in Complex Terrains.

Prediction of foot placement presents great potential in better assisting the walking of people with lower-limb disability in daily terrains. Previous researches mainly focus on foot placement prediction in level ground walking, however these methods cannot be applied to daily complex terrains including ramps, stairs, and level ground with obstacles. To predict foot placement in complex terrains, this paper presents a probability fusion approach for foot placement prediction in complex terrains which consists of two parts: model training and foot placement prediction. In the first part, a deep learning model is trained on augmented data to predict the probability distribution of preliminary foot placement. In the second part, environmental information and human walking constraints are used to calculate the feasible area, and finally the feasible area is fused with the probability distribution of preliminary foot placement to predict the foot placement in complex terrains. The proposed method can predict the foot placement of next step in complex terrains when heel-off is detected. Experiments (including structured terrains experiments and complex terrains experiments) show that the root mean square error (RMSE) of prediction is 8.19 ± 1.20 cm, which is less than 8% of the average stride length, and the landing feasible area accuracy (LFAA) of prediction is 95.11 ± 3.09%. Comparing with existing foot placement prediction studies, the method proposed in this paper achieves faster and more accurate prediction in complex terrains.

Neural Correlation of EEG and Eye Movement in Natural Grasping Intention Estimation.

Decoding the user's natural grasp intent enhances the application of wearable robots, improving the daily lives of individuals with disabilities. Electroencephalogram (EEG) and eye movements are two natural representations when users generate grasp intent in their minds, with current studies decoding human intent by fusing EEG and eye movement signals. However, the neural correlation between these two signals remains unclear. Thus, this paper aims to explore the consistency between EEG and eye movement in natural grasping intention estimation. Specifically, six grasp intent pairs are decoded by combining feature vectors and utilizing the optimal classifier. Extensive experimental results indicate that the coupling between the EEG and eye movements intent patterns remains intact when the user generates a natural grasp intent, and concurrently, the EEG pattern is consistent with the eye movements pattern across the task pairs. Moreover, the findings reveal a solid connection between EEG and eye movements even when taking into account cortical EEG (originating from the visual cortex or motor cortex) and the presence of a suboptimal classifier. Overall, this work uncovers the coupling correlation between EEG and eye movements and provides a reference for intention estimation.

An Intelligent Rehabilitation Assessment Method for Stroke Patients Based on Lower Limb Exoskeleton Robot.

The 6-min walk distance (6MWD) and the Fugl-Meyer assessment lower-limb subscale (FMA-LE) of the stroke patients provide the critical evaluation standards for the effect of training and guidance of the training programs. However, gait assessment for stroke patients typically relies on manual observation and table scoring, which raises concerns about wasted manpower and subjective observation results. To address this issue, this paper proposes an intelligent rehabilitation assessment method (IRAM) for rehabilitation assessment of the stroke patients based on sensor data of the lower limb exoskeleton robot. Firstly, the feature parameters of the patient were collected, including age, height, and duration, etc. The sensor data of the exoskeleton robot were also collected, including joint angle, joint velocity, and joint torque, etc. Secondly, a gait feature model was constructed to deduce the walking gait parameters of the patient according to the sensor data of the exoskeleton, including the support phase to swing phase ratio, step length and leg lift height of the patient, etc. Then, the 6MWD and FMA-LE values were collected by traditional methods, feature parameters, gait parameters and human-machine interaction parameters (joint torque) of the patient were adopted to train the rehabilitation assessment model. Finally, the assessment model was trained by a machine-learning based algorithm. The new stroke patients' the 6MWD and FMA-LE values can be predicted by the trained model. The experimental results present that the prediction accuracy for the 6MWD and FMA-LE values reach to 85.19% and 92.66%, respectively.

UV and IR dual light triggered cellulose-based invisible actuators with high sensitivity.

Actuators are widely used in bionic devices and soft robots, among which invisible actuators have some unique applications, including performing secret missions. In this paper, highly visible transparent cellulose-based UV-absorbing films were prepared by dissolving cellulose raw materials using N-methylmorpholine-N-oxide (NMMO) and using ZnO nanoparticles as UV absorbers. Furthermore, transparent actuator was fabricated by growing highly transparent and hydrophobic polytetrafluoroethylene (PTFE) film on regenerated cellulose (RC)-ZnO composite film. In addition to its sensitive response to Infrared (IR) light, the as-prepared actuator also shows a highly sensitive response to UV light, which is attributed to the strong absorption of UV light by ZnO NPs. Thanks to the drastic differences in adsorption capacity between the RC-ZnO and PTFE materials for water molecules, the asymmetrically- assembled actuator demonstrates extremely high sensitivity and excellent actuation performance, with a force density of 60.5, a maximum bending curvature of 3.0 cm-1, and a response time of below 8 s. Bionic bug, smart door and the arm of excavator made from the actuator all exhibit sensitive responses to UV and IR lights.

Fully Automatic Dual-Probe Lung Ultrasound Scanning Robot for Screening Triage.

Two-dimensional lung ultrasound (LUS) has widely emerged as a rapid and noninvasive imaging tool for the detection and diagnosis of coronavirus disease 2019 (COVID-19). However, image differences will be magnified due to changes in ultrasound (US) imaging experience, such as US probe attitude control and force control, which will directly affect the diagnosis results. In addition, the risk of virus transmission between sonographer and patients is increased due to frequent physical contact. In this study, a fully automatic dual-probe US scanning robot for the acquisition of LUS images is proposed and developed. Furthermore, the trajectory was optimized based on the velocity look-ahead strategy, the stability of contact force of the system and the scanning efficiency were improved by 24.13% and 29.46%, respectively. Also, the control ability of the contact force of robotic automatic scanning was 34.14 times higher than that of traditional manual scanning, which significantly improves the smoothness of scanning. Importantly, there was no significant difference in image quality obtained by robotic automatic scanning and manual scanning. Furthermore, the scanning time for a single person is less than 4 min, which greatly improves the efficiency of screening triage of group COVID-19 diagnosis and suspected patients and reduces the risk of virus exposure and spread.

Adaptive Oscillator-Based Assistive Torque Control for Gait Asymmetry Correction With a nSEA-Driven Hip Exoskeleton.

Gait asymmetry is an important clinical characteristic of the hemiplegic gait most stroke survivors suffered, leading to restricted functional mobility and long-term negative impact on their quality of life. In recent years, robot assistance has been proven able to improve stroke patients' functional walking, but few studies have been conducted to specifically correct gait asymmetry of stroke patients during the whole gait cycle. In this work, an adaptive oscillator-based assistive torque control was developed and implemented on a unilateral hip exoskeleton driven by a novel nonlinear series elastic actuator (nSEA), aiming at correcting gait asymmetry at hip joints during the whole gait cycle. The adaptive oscillator-based gait asymmetry detection method extracted continuous gait phase and gait asymmetry seamlessly, and then the proposed assistive control attempted to correct gait asymmetry by delivering precise assistive torques synchronized with the continuous gait phase of the patients' gait. An initial experimental study was conducted to evaluate the proposed assistive control on seven healthy subjects with artificial impairment. The participants walked on a treadmill with assistance from the hip exoskeleton, while artificial impairment was added to mimic the hemiplegic gait with both spacial and temporal asymmetry (such as reduced hip flexion in the impaired side and reduced hip extension in the healthy side). Experimental results suggested the effectiveness of the proposed assistive control in restoring gait symmetry to levels comparable to a normal gait of the participants ( ).

A Supervised-Reinforced Successive Training Framework for a Fuzzy Inference System and Its Application in Robotic Odor Source Searching.

Fuzzy inference systems have been widely applied in robotic control. Previous studies proposed various methods to tune the fuzzy rules and the parameters of the membership functions (MFs). Training the systems with only supervised learning requires a large amount of input-output data, and the performance of the trained system is confined by that of the target system. Training the systems with only reinforcement learning (RL) does not require prior knowledge but is time-consuming, and the initialization of the system remains a problem. In this paper, a supervised-reinforced successive training framework is proposed for a multi-continuous-output fuzzy inference system (MCOFIS). The parameters of the fuzzy inference system are first tuned by a limited number of input-output data from an existing controller with supervised training and then are utilized to initialize the system in the reinforcement training stage. The proposed framework is applied in a robotic odor source searching task and the evaluation results demonstrate that the performance of the fuzzy inference system trained by the successive framework is superior to the systems trained by only supervised learning or RL. The system trained by the proposed framework can achieve around a 10% higher success rate compared to the systems trained by only supervised learning or RL.

Unsupervised Sim-to-Real Adaptation for Environmental Recognition in Assistive Walking.

Powered lower-limb prostheses with vision sensors are expected to restore amputees' mobility in various environments with supervised learning-based environmental recognition. Due to the sim-to-real gap, such as real-world unstructured terrains and the perspective and performance limitations of vision sensor, simulated data cannot meet the requirement for supervised learning. To mitigate this gap, this paper presents an unsupervised sim-to-real adaptation method to accurately classify five common real-world (level ground, stair ascent, stair descent, ramp ascent and ramp descent) and assist amputee's terrain-adaptive locomotion. In this study, augmented simulated environments are generated from a virtual camera perspective to better simulate the real world. Then, unsupervised domain adaptation is incorporated to train the proposed adaptation network consisting of a feature extractor and two classifiers is trained on simulated data and unlabeled real-world data to minimize domain shift between source domain (simulation) and target domain (real world). To interpret the classification mechanism visually, essential features of different terrains extracted by the network are visualized. The classification results in walking experiments indicate that the average accuracy on eight subjects reaches (98.06% ± 0.71 %) and (95.91% ± 1.09 %) in indoor and outdoor environments respectively, which is close to the result of supervised learning using both type of labeled data (98.37% and 97.05%). The promising results demonstrate that the proposed method is expected to realize accurate real-world environmental classification and successful sim-to-real transfer.

Design of asymmetric-adhesion lignin-reinforced hydrogels based on disulfide bond crosslinking for strain sensing application.

Soft and elastic polymer hydrogel materials are booming in the fields of wearable biomimetic skin, sensors, robotics, and bioelectrodes. Currently, many researchers are exploring new chemistries for the preparation of hydrogels to improve their performance. In the present study, we design and develop a strategy to prepare lignin reinforced hydrogels based on disulfide bond crosslinking mechanisms, and resultant hydrogels exhibit excellent stretchability, with tensile strain of up to 1085.4%, and high adhesion (with the highest T-peel strength of up to 432.2 N/m to pigskin). The underlying mechanism is based on the disulfide bonds that act as crosslinkers in the as-prepared hydrogel, and they can be easily cleaved and re-formed under mild conditions. Thanks to the presence of lignin, the as-obtained hydrogels also have excellent UV shielding effect. When assembled into a strain sensor, they can output stable and sensitive sensing signals, with gauge factor (GF) of 2.72 (strain: 0-72.8%). Furthermore, a simple and effective strategy to construct asymmetric adhesive hydrogels was adopted, which is based on directional soaking of the top portion of the hydrogel in a high-concentrated calcium chloride solution. The asymmetric hydrogel strain sensor transmits accurate and stable signals without the interference of various contaminants.

Preparation of Hemicellulose Nanoparticle-Containing Ionic Hydrogels with High Strength, Self-Healing, and UV Resistance and Their Applications as Strain Sensors and Asymmetric Pressure Sensors.

Smart functional fillers can significantly enhance the comprehensive properties of ionic hydrogels, such as their mechanical properties, which are key features of hydrogels in wearable sensor applications. As a plant-derived natural polymer, hemicellulose can serve as smart functional fillers. In this study, tannic acid-modified hemicellulose nanoparticles (TA@HC) and Fe3+ were used in the preparation of PAA/TA@HC/Fe3+ hydrogels. The addition of TA@HC and Fe3+ in the sodium persulfate (SPS) and acrylic acid (AA) polymerization system resulted in a fast gelation process that was completed within a short time (as short as 30 s) at room temperature. The catechol-rich TA and Fe3+ system allows for quick activation of SPS to produce free radicals, generating abundant hydroxyl groups in a short period of time, which was responsible for the fast gelation. Furthermore, due to the TA@HC effect and the dynamic catechol (TA)-Fe3+ redox system, the PAA/TA@HC/Fe3+ hydrogel exhibited excellent mechanical properties with an exceptionally high strain (as high as 5600%), adhesiveness, rapid and efficient self-healing ability, and reproducible self-adhesion onto various substrates. More importantly, asymmetric adhesive PAA/TA@HC/Fe3+ hydrogels were prepared by selective Fe3+ coating of the upper hydrogel surface to render the top surface nonadhesive so that the same hydrogel with different adhesiveness between the upper and bottom surfaces was obtained. The asymmetric adhesive hydrogel design permits the adhesive side to fit comfortably to the skin and the nonadhesive side showing anti-interference against various different pollutant materials, accurately serving as a pressure sensor.

Gait Phase Subdivision and Leg Stiffness Estimation During Stair Climbing.

Leg stiffness is considered a prevalent parameter used in data analysis of leg locomotion during different gaits, such as walking, running, and hopping. Quantification of the change in support leg stiffness during stair ascent and descent will enhance our understanding of complex stair climbing gait dynamics. The purpose of this study is to investigate a methodology to estimate leg stiffness during stair climbing and subdivide the stair climbing gait cycle. Leg stiffness was determined as the ratio of changes in ground reaction force in the direction of the support leg Fl (leg force) to the respective changes in length Ll during the entire stance phase. Eight subjects ascended and descended an instrumented staircase at different cadences. In this study, the changes of leg force and length (force-length curve) are described as the leg stiffness curve, the slope of which represents the normalized stiffness during stair climbing. The stair ascent and descent gait cycles were subdivided based on the negative and positive work fluctuations of the center-of-mass (CoM) work rate curve and the characteristics of leg stiffness. We found that the leg stiffness curve consists of several segments in which the force-length relationship was similarly linear and the stiffness value was relatively constant; the phase divided by the leg stiffness curve corresponds to the phase divided by the CoM work rate curve. The results of this study may guide biomimetic control strategies for a wearable lower-extremity robot for the entire stance phase during stair climbing.

Preparation and Performance of Lignin-Based Multifunctional Superhydrophobic Coating.

Superhydrophobic coatings have drawn much attention in recent years for their widespread potential applications. However, there are challenges to find a simple and cost-effective approach to prepare superhydrophobic materials and coatings using natural polymer. Herein, we prepared a kraft lignin-based superhydrophobic powder via modifying kraft lignin through 1H, 1H, 2H, 2H-perfluorodecyl-triethoxysilane (PFDTES) substitution reaction, and constructed superhydrophobic coatings by direct spraying the suspended PFDTES-Lignin powder on different substrates, including glass, wood, metal and paper. The prepared lignin-based coatings have excellent repellency to water, with a water contact angle of 164.7°, as well as good friction resistance, acid resistance, alkali resistance, salt resistance properties and quite good self-cleaning performance. After 30 cycles of sand friction or being stayed in 2 mol/L HCl, 0.25 mol/L NaOH and 2 mol/L NaCl solution for 30 min, the coatings still retain super hydrophobic capability, with contact angles higher than 150°. The superhydrophobic performance of PFDTES-Lignin coatings is mainly attributed to the constructed high surface roughness and the low surface energy afforded by modified lignin. This lignin-based polymer coating is low-cost, scalable, and has huge potential application in different fields, providing a simple way for the value-added utilization of kraft lignin.

Design of asymmetric-adhesion lignin reinforced hydrogels with anti-interference for strain sensing and moist air induced electricity generator.

Flexible hydrogels with integration of excellent mechanical and electrical properties are well suited for applications as wearable electronic sensors, and others. Self-adhesion is an important feature of wearable sensors. However, the usual isotropic- adhesion hydrogels have the drawback of poor anti-interference, which negatively affects their applications. In this study, we developed asymmetric-adhesion and tough lignin reinforced hydrogels in a facile two-step process: 1) PAA hydrogels, with lignin as the binder and conductive filler, were first prepared; 2) the asymmetric-adhesion property was imparted to lignin reinforced hydrogel by simple soaking of the top portion of the hydrogel in CaCl2 solution. The as-obtained asymmetric-adhesion lignin reinforced hydrogel was assembled into a wearable sensor, which shows excellent anti-interference and accurate and stable collections of sensing signals, with its gauge factor (GF) of 2.51 (in the strain range of 0-51.5%). In addition, the tough hydrogel is capable of generating electricity upon moist air sweeping through it, showing excellent energy conversion capabilities, with open-circuit voltage of as high as 306.6 mV. These results provided new prospects for the application of polyelectrolyte hydrogel materials in the fields of wet-to-electric conversion and wearable electronic sensors.

Lignin reinforced hydrogels with fast self-recovery, multi-functionalities via calcium ion bridging for flexible smart sensing applications.

Hydrogels have found applications in many different fields. However, poor mechanical properties, such as low elasticity and lack of rapid recovery under large deformation, can severely limit their applications. In this study, we developed lignin reinforced hydrogels made of calcium ion containing ternary polymers (lignosulfonate (LS), alginate (Alg), and polyacrylic acid (PAA)). The resultant hydrogel has excellent elasticity, rapid self-recovery, and multi-functionalities. The covalent PAA network acts as the elastic scaffold of hydrogel, while calcium bridging networks of LS, Alg, and PAA, as well as the strong hydrogen bonding network in the system, function as sacrifice bonds to dissipate energy and transfer stress. The PAA/LS/Alg/Ca hydrogels exhibit rapid and durable elastic recovery ability under large deformation with the highest compressive stress of 835 kPa (95% strain), highest tensile fracture stress of 357 kPa, and highest tensile strain of 1144%. In addition, these tough hydrogels show UV resistance, self-healing, antifreeze, and excellent electro-conductivity. When assembled into a strain sensor, stable and reliable electrical responses with 375 ms response time are demonstrated. The PAA/LS/Alg/Ca hydrogel strain sensors can monitor human movements with responsive and accurate physiological signals. These results support the conclusion that the PAA/LS/Alg/Ca hydrogel strain sensors have great application potential in flexible wearable electronics and smart devices.

A Probability Distribution Model-Based Approach for Foot Placement Prediction in the Early Swing Phase With a Wearable IMU Sensor.

Predicting the next foot placement of humans during walking can help improve compliant interactions between humans and walking aid robots. Previous studies have focused on foot placement estimation with wearable inertial sensors after heel-strike, but few have predicted foot placements in advance during the early swing phase. In this study, a Bayesian inference-based foot placement prediction approach was proposed. Possible foot placements were modeled as a probability distribution grid map. With selected foot motion feature events detected sequentially in the early swing phase, the foot placement probability map could be updated iteratively using the feature models we built. The weighted center of the probability distribution was regarded as the predicted foot placement. Prediction errors were evaluated with collected walking data sets. When testing with the data from inertial measurement units, the prediction errors were (5.46 cm ± 10.89 cm, -0.83 cm ± 10.56 cm) for cross-velocity walking data and (-4.99 cm ± 12.31 cm, -11.27 cm ± 7.74 cm) for cross-subject-cross-velocity walking data. The results were comparable to previous works yet the prediction could be made earlier. For the subject who walked with more stable gaits, the prediction error can be further decreased. The proposed foot placement prediction approach can be utilized to help walking aid robots adjust their pose before each heel-strike event during walking, which will make human-robot interactions more compliant. This study is also expected to inspire additional probabilistic gait analysis works.