Walking Experiments Research Articles

Impact of human walking on the pollutant removal effectiveness of direction air supply considering environmental disturbances: Dynamic simulation study

Direction air supply (DAS) is a computer vision-assisted ventilation mode designed to address the challenge of respiratory protection during human movement. The DAS parameter design is based on ideal, steady-state air distribution results, but it cannot reflect the dynamic protection performance. This work investigates the effect of human walking on the pollutant removal effectiveness of DAS through computational fluid dynamics simulation with the dynamic mesh method. This work formulates an occupant's movement pattern and implements walking and turning motions using the overset mesh method. To verify the feasibility of the dynamic simulation method, a walking experiment was conducted in an experimental chamber equipped with a DAS system. The evolution of concentration isosurfaces, as well as the concentration, velocity, and static pressure at breathing-zone height are revealed. The negative impacts of three common industrial environmental disturbances: localized high-temperature pollutants, ambient airflow, and distance between the DAS nozzle and the breathing zone, on the protective zone and the DAS barrier against pollutants are analyzed. To comprehensively evaluate the effectiveness of DAS, four assessment indexes are determined: inhalation exposure, protection factor, protective zone area, and effective protective ratio. The inconsistency between the protective zone area and the effective protective ratio needs to be noted. This work confirms the effectiveness of DAS within the protective zone and supports its further application in industrial settings.

Development of a rimless wheel robot with telescopic legs for step adaptability

AbstractIn this study, we developed a rimless wheel robot with elastic telescopic legs that can overcome steps. Numerical studies have shown that a rimless wheel robot with elastic telescopic legs has high adaptability to steps. However, rimless wheel robots that can walk in environments with steps have not yet been developed. To develop a rimless wheel robot that could overcome the steps, we initially developed a three-dimensional model of the robot through Unity software and simulated its walking on level ground and surfaces with steps. Then, we determined the optimal elasticity of the elastic telescopic legs through numerical simulation and constructed a model with optimized parameters. Finally, we conducted the walking experiments employing the developed robot. The robot can walk on level ground and surfaces with steps.

Psychological and Visual Perception of Campus Lightscapes Based on Lightscape Walking Evaluation: A Case Study of Chongqing University in China

The creation of lightscapes in colleges and universities are of great significance in enhancing the perception of the campus environment, improving physical and mental health, and shaping humanistic connotations. This research aims to examine lightscape perceptions and impacts of different campuses. At Chongqing University A and B Campuses, lightscape walking experiments, subjective questionnaires, objective luminance measurements, and HDR picture processing were used to examine lightscape perception and factors. The relevance and differences in the perception of circadian lightscapes in the two campuses were analyzed using SPSS software. The study found: (1) natural lightscapes such as sky light, cloud shadow, and lake water reflection were the most popular during the daytime, while artificial lightscapes, such as decorative lighting of buildings, were positively evaluated at night; (2) the frequency of visits by a crowd directly impacts the ambiance of the environmental area; (3) males showed strong emotional awareness and social interaction skills in daytime, leading to increased social activity and stronger emotional responses, but no differences in nighttime; (4) optimal nighttime luminance enhances the overall perception satisfaction of the illumination; (5) the amount and arrangement of outdoor space, vegetation, minor landscape design, and service facilities all affect the perception of circadian lightscapes. In conclusion, design concepts and proposals of landscapes were suggested to optimize college and university lightscapes.

Structure and Gait Design of a Lunar Exploration Hexapod Robot Based on Central Pattern Generator Model

To address the challenges of sinking, imbalance, and complex control systems faced by hexapod robots walking on lunar soil, this study develops an umbrella-shaped foot lunar exploration hexapod robot. The overall structure of the robot is designed to mimic the body structure of insects. By incorporating a four-bar linkage mechanism to replace the commonly used naked joints in traditional hexapod robots, the robot reduces the number of degrees of freedom and simplifies control complexity. Additionally, an extension mechanism is added to the robot’s foot, unfolding into an umbrella shape to provide a larger support area, effectively addressing the issue of foot sinking instability during walking. This study adopts and simplifies the Central Pattern Generator (CPG) model to generate stable periodic control signals for the robot’s legs. Precise control of the extension mechanism’s unfolding period is achieved through mapping functions. A joint simulation platform using Solid Works and Matlab is established to analyze the stability of the robot’s walking. Finally, walking experiments are conducted on the prototype, confirming the smooth walking of the lunar exploration hexapod robot. The results indicate that the designed lunar exploration hexapod robot has a reasonable structure, excellent stability in motion, and the CPG control scheme is feasible.

Deep deterministic policy gradient with constraints for gait optimisation of biped robots

In this paper, we propose a novel Reinforcement Learning (RL) algorithm for robotic motion control, that is, a constrained Deep Deterministic Policy Gradient (DDPG) deviation learning strategy to assist biped robots in walking safely and accurately. The previous research on this topic highlighted the limitations in the controller’s ability to accurately track foot placement on discrete terrains and the lack of consideration for safety concerns. In this study, we address these challenges by focusing on ensuring the overall system’s safety. To begin with, we tackle the inverse kinematics problem by introducing constraints to the damping least squares method. This enhancement not only addresses singularity issues but also guarantees safe ranges for joint angles, thus ensuring the stability and reliability of the system. Based on this, we propose the adoption of the constrained DDPG method to correct controller deviations. In constrained DDPG, we incorporate a constraint layer into the Actor network, incorporating joint deviations as state inputs. By conducting offline training within the range of safe angles, it serves as a deviation corrector. Lastly, we validate the effectiveness of our proposed approach by conducting dynamic simulations using the CRANE biped robot. Through comprehensive assessments, including singularity analysis, constraint effectiveness evaluation, and walking experiments on discrete terrains, we demonstrate the superiority and practicality of our approach in enhancing walking performance while ensuring safety. Overall, our research contributes to the advancement of biped robot locomotion by addressing gait optimisation from multiple perspectives, including singularity handling, safety constraints, and deviation learning.

An inclined pedal type piezoelectric energy harvester for pedestrian flow and vehicle safety monitoring

This paper proposed an inclined pedal-type piezoelectric energy harvester for pedestrian monitoring and vehicle safety monitoring (IPEH). The IPEH exterior adopts an inclined pedal design, the steel ball is placed inside its cylindrical channel to excite the piezoelectric patches to harvest and convert external mechanical energy. IPEH can be placed under the brake pedal of a car for the function of vehicle safety monitoring. IPEH can also be fixed on the road as an energy harvester and monitoring device, harvesting pedestrian trampling energy and monitoring the density of pedestrian traffic in realtime. The influence of the steel ball diameter and spring layout on the output performance of the prototype is studied in this paper. Under the best parameters of the prototype assembly, the maximum output voltage is 165.6 Vpp, and the maximum output power is 463.7 mW. In the application experiment, the practicability in energy harvesting applications of IPEH is verified through the experiment of lighting LEDs and charging capacity, and the monitoring ability of IPEH was verified by simulating the experiment of different human flow walking and vehicle braking. It provides a new idea for the subsequent application of piezoelectric equipment in traffic auxiliary facilities and intelligent sensing equipment.

An interaction model for predicting brace migration and validation through walking experiment

Brace migration undermines therapeutic efficacy, which is traditionally evaluated through walking experiments. This study developed an interaction model that considered the instantaneous center of rotation (ICR) misalignment to predict migration. The model was validated by walking experiment. Results show a strong positive correlation for four-linkage (FL) (r = 0.952, p < 0.01, root mean squared error (RMSE) = 0.53 mm) and spur gear (SG) (r = 0.898, p < 0.01, RMSE = 1.35 mm) mechanisms. The FL exhibits lower migration than SG (p < 0.05). In conclusion, the interaction model accurately predicts migration, emphasizing the influence of mechanism on migration.

IMU-Based Energy Expenditure Estimation for Various Walking Conditions Using a Hybrid CNN-LSTM Model.

In ubiquitous healthcare systems, energy expenditure estimation based on wearable sensors such as inertial measurement units (IMUs) is important for monitoring the intensity of physical activity. Although several studies have reported data-driven methods to estimate energy expenditure during activities of daily living using wearable sensor signals, few have evaluated the performance while walking at various speeds and inclines. In this study, we present a hybrid model comprising a convolutional neural network (CNN) and long short-term memory (LSTM) to estimate the steady-state energy expenditure under various walking conditions based solely on IMU data. To implement and evaluate the model, we performed level/inclined walking and level running experiments on a treadmill. With regard to the model inputs, the performance of the proposed model based on fixed-size sequential data was compared with that of a method based on stride-segmented data under different conditions in terms of the sensor location, input sequence format, and neural network model. Based on the experimental results, the following conclusions were drawn: (i) the CNN-LSTM model using a two-second sequence from the IMU attached to the lower body yielded optimal performance, and (ii) although the stride-segmented data-based method showed superior performance, the performance difference between the two methods was not significant; therefore, the proposed model based on fixed-size sequential data may be considered more practical as it does not require heel-strike detection.

A robotic emulator for the systematic exploration of transtibial biarticular prosthesis designs.

People with transtibial limb loss frequently experience suboptimal gait outcomes. This is partly attributable to the absence of the biarticular gastrocnemius muscle, which plays a unique role in walking. Although a recent surge of biarticular prostheses aims to restore gastrocnemius function, the broad design space and lack of consensus on optimal hardware and control strategies present scientific and engineering challenges. This study introduces a robotic biarticular prosthesis emulator, comprising a uniarticular ankle-foot prosthesis and knee flexion exoskeleton, each actuated by a custom off-board system. Benchtop experiments were conducted to characterize the emulator's mechatronic performance. Walking experiments with one transtibial amputee demonstrated the system's capability to provide knee and ankle assistance. The -3dB bandwidths for the knee exoskeleton's torque and motor velocity controllers were measured at approximately 5Hz and 100Hz, respectively. A feedforward iterative learning controller reduced the root-mean-squared torque tracking error from 6.04Nm to 0.99Nm in hardware-in-the-loop experiments, an 84% improvement. User-preference-based tuning yielded a peak knee torque of approximately 20% of the estimated biological knee moment. This biarticular prosthesis emulator demonstrates significant potential as a versatile research platform that can offer valuable insights for the advancement of lower-limb assistive devices.

Development and Adaptive Assistance Control of the Robotic Hip Exoskeleton to Improve Gait Symmetry and Restore Normal Gait

Neurological disorders and aging induce abnormal gait kinematics such as asymmetric gait, reduced stride length, and walking speeds. Gait asymmetry increases musculoskeletal pain and joint impairment in the affected leg, increases the risk of patients falling, and induces higher energy expenditure. This paper presents a novel assistive control framework for the series elastic actuator-driven robotic hip exoskeleton that improves gait symmetry and restores normal gait. The proposed assistive control depends on virtual stiffness compensation with a series elastic actuator (SEA)-driven hip exoskeleton to assist without needing estimation, prediction of the gait phase, or human intent. In addition, adaptive adjustment of the virtual stiffness based on the approximate dynamic programming method is used to improve gait symmetry. The proposed control strategy is successfully implemented, and experiments are validated with human subjects’ gait assistance using a SEA-driven wearable hip exoskeleton. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper was motivated by the problem of hip exoskeleton assistive control. The goal of hip exoskeleton assistance is to improve gait symmetry and restore the normal gait of the patient with neurological disorders and the elderly. Existing approaches to fixturing such parts generally need to estimate or predict the gait phase or human intent. And the existing approaches generally adopted fixed control parameters. The hip exoskeleton’s assistance cannot adapt to various walking conditions and human gait differences. The proposed assistive control is based on virtual stiffness compensation with a SEA-driven hip exoskeleton to assist with walking under various walking conditions without estimating or predicting the gait phase or human intent. And the proposed method is online adjusted control parameters with human-in-the-loop to improve the gait symmetry. The human walking experiment results showed that the hip exoskeleton assistive controller not only reduced muscle activation and human effort but also improved the interjoint coordination of the impaired joint online. We also showed how the assistance controller changes the control parameters according to the gait symmetry with a human-in-the-loop strategy.

Probabilistic Estimation of Cadence and Walking Speed From Floor Vibrations.

This research aims to extract human gait parameters from floor vibrations. The proposed approach provides an innovative methodology on occupant activity, contributing to a broader understanding of how human movements interact within their built environment. A multilevel probabilistic model was developed to estimate cadence and walking speed through the analysis of floor vibrations induced by walking. The model addresses challenges related to missing or incomplete information in the floor acceleration signals. Following the Bayesian Analysis Reporting Guidelines (BARG) for reproducibility, the model was evaluated through twenty-seven walking experiments, capturing floor vibration and data from Ambulatory Parkinson's Disease Monitoring (APDM) wearable sensors. The model was tested in a real-time implementation where ten individuals were recorded walking at their own selected pace. Using a rigorous combined decision criteria of 95% high posterior density (HPD) and the Range of Practical Equivalence (ROPE) following BARG, the results demonstrate satisfactory alignment between estimations and target values for practical purposes. Notably, with over 90% of the 95% HPD falling within the region of practical equivalence, there is a solid basis for accepting the estimations as probabilistically aligned with the estimations using the APDM sensors and video recordings. This research validates the probabilistic multilevel model in estimating cadence and walking speed by analyzing floor vibrations, demonstrating its satisfactory comparability with established technologies such as APDM sensors and video recordings. The close alignment between the estimations and target values emphasizes the approach's efficacy. The proposed model effectively tackles prevalent challenges associated with missing or incomplete data in real-world scenarios, enhancing the accuracy of gait parameter estimations derived from floor vibrations. Extracting gait parameters from floor vibrations could provide a non-intrusive and continuous means of monitoring an individual's gait, offering valuable insights into mobility and potential indicators of neurological conditions. The implications of this research extend to the development of advanced gait analysis tools, offering new perspectives on assessing and understanding walking patterns for improved diagnostics and personalized healthcare.Clinical and Translational Impact Statement: This manuscript introduces an innovative approach for unattended gait assessments with potentially significant implications for clinical decision-making. By utilizing floor vibrations to estimate cadence and walking speed, the technology can provide clinicians with valuable insights into their patients' mobility and functional abilities in real-life settings. The strategic installation of accelerometers beneath the flooring of homes or care facilities allows for uninterrupted daily activities during these assessments, reducing the reliance on specialized clinical environments. This technology enables continuous monitoring of gait patterns over time and has the potential for integration into healthcare platforms. Such integration can enhance remote monitoring, leading to timely interventions and personalized care plans, ultimately improving clinical outcomes. The probabilistic nature of our model enables uncertainty quantification in the estimated parameters, providing clinicians with a nuanced understanding of data reliability.

Trajectory Deformation-Based Multi-Modal Adaptive Compliance Control for a Wearable Lower Limb Rehabilitation Robot.

Adaptive compliance control is critical for rehabilitation robots to cope with the varying rehabilitation needs and enhance training safety. This article presents a trajectory deformation-based multi-modal adaptive compliance control strategy (TD-MACCS) for a wearable lower limb rehabilitation robot (WLLRR), which includes a high-level trajectory planner and a low-level position controller. Dynamic motion primitives (DMPs) and a trajectory deformation algorithm (TDA) are integrated into the high-level trajectory planner, generating multi-joint synchronized desired trajectories through physical human-robot interaction (pHRI). In particular, the amplitude modulation factor of DMPs and the deformation factor of TDA are adapted by a multi-modal adaptive regulator, achieving smooth switching of human-dominant mode, robot-dominant mode, and soft-stop mode. Besides, a linear active disturbance rejection controller is designed as the low-level position controller. Four healthy participants and two stroke survivors are recruited to conduct robot-assisted walking experiments using the TD-MACCS. The results show that the TD-MACCS can smoothly switch three control modes while guaranteeing trajectory tracking accuracy. Moreover, we find that appropriately increasing the upper bound of the deformation factor can enhance the average walking speed (AWS) and root mean square of trajectory deviation (RMSTD).

Mechatronic Design and Implementation of a Low-Noise Powered Knee Prosthesis With High Backdrivability

Working noise is an important consideration that hinders the acceptance of powered prostheses by amputees. In this article, we present a powered knee prosthesis with low noise and high backdrivability. The powertrain of the proposed prosthesis consists of a motor and a four-stage synchronous belt to decrease working noise. At the same time, benefiting from the low impedance of the motor and low impedance design, the proposed prosthesis is endowed with the characteristics of low impedance, and thus, high backdrivability. A three-layer control method based on a finite state machine is implemented, and walking experiments have been carried out on a transfemoral amputee. The results show the characteristics of the proposed prosthesis in low impedance, low noise, and the ability to reproduce a natural gait. In particular, the working noise of the proposed prosthesis is less than 46 dBA most time, which is lower than common household appliances, and may have positive effects on the acceptance of daily uses.

Parametric Design and Optimization of a Knee-Joint Biomechanical Energy Harvester to Maximize Power Generation With Minimal Metabolic Cost

Reliable supplies of electric energy for the electrical devices carried by field workers is important for work and survival, while the hand-crank generator commonly used is toilsome. Using knee-joint biomechanical energy harvesters to harness dissipated biomechanical energy and generate electric power is an ingenious way to solve this problem. However, the lack of a parametric design method for the harvesters has caused power generation with large bioenergy consumption. In this work, we proposed an optimal design method for the parameters of the critical harvester components, including the generator, gearbox, and load resistor. Power generation and the total metabolic cost of the harvesting (TCOH) were set as the optimization objectives, and the equations to calculate both objectives were established. The optimal electric parameters of the generator were obtained by deduction and analysis of the equations, and the gear rate of the gearbox and resistance of the load resistor were optimized by a dynamic programming. Prototypes built with the optimized component parameters were tested in walking experiments. The prototypes can generate 6.16±1.47 W electric power with 11.9 W metabolic cost during 5 km/h walking. More generated power with much less metabolic cost was achieved compared with other knee-joint harvesters.

A Wearable Co-Located Neural-Mechanical Signal Sensing Device for Simultaneous Bimodal Muscular Activity Detection.

The co-located and concurrent measurement of both muscular neural activity and muscular deformation is considered necessary in many applications, such as medical robotics, assistive exoskeletons and muscle function evaluations. Nevertheless, conventional muscle-related signal perception systems either detect only one of these modalities, or are made with rigid and bulky components that cannot provide conformal and flexible interface. Herein, a flexible, easy-to-fabricate, bimodal muscular activity sensing device, which collects neural and mechanical signal at the same muscle location, is reported. The sensing patch includes a screen-printed sEMG sensor, and a pressure-based muscular deformation sensor (PMD sensor) based on a highly sensitive, co-planar iontronic pressure sensing unit. Both sensors are integrated on a super-thin (25 μm) substrate. The sEMG sensor shows a high signal-to-noise ratio of 37.1 dB, and the PMD sensor sensor exhibits a high sensitivity of 70.9 kPa -1. The responses of the sensor to three types of muscle activities (isotonic, isometric, and passive stretching) were analyzed and validated by ultrasound imaging. Bimodal signals during dynamic walking experiments with different level-ground walking speeds were also investigated. The application of the bimodal sensor was verified in gait phase estimation, and results show that the assembly of both modalities significantly reduce (p < 0.05) the average estimation error across all subjects and all walking speeds to 3.82%. Demonstrations show the potential of this sensing device for informative evaluation of muscular activities, and its abilities in human-robot interaction.

Prediction of Three-Directional Ground Reaction Forces during Walking Using a Shoe Sole Sensor System and Machine Learning.

We developed a shoe sole sensor system with four high-capacity, compact triaxial force sensors using a nitrogen added chromium strain-sensitive thin film mounted on the sole of a shoe. Walking experiments were performed, including straight walking and turning (side-step and cross-step turning), in six healthy young male participants and two healthy young female participants wearing the sole sensor system. A regression model to predict three-directional ground reaction forces (GRFs) from force sensor outputs was created using multiple linear regression and Gaussian process regression (GPR). The predicted GRF values were compared with the GRF values measured with a force plate. In the model trained on data from the straight walking and turning trials, the percent root-mean-square error (%RMSE) for predicting the GRFs in the anteroposterior and vertical directions was less than 15%, except for the GRF in the mediolateral direction. The model trained separately for straight walking, side-step turning, and cross-step turning showed a %RMSE of less than 15% in all directions in the GPR model, which is considered accurate for practical use.

Application of vibration to the soles increases long-range correlations in the stride parameters during walking

Temporal fluctuations in the stride parameters during human walking exhibit long-range correlations, but these long-range correlations in the stride parameters decrease due to aging or neuromuscular diseases. These observations suggest that any quantified index of the long-range correlation can be regarded as an indicator of gait functionality. Considering the effect of task-relevant sensory feedback on augmenting human motor performance, we devised shoes with active insoles that could deliver noisy vibration to the soles of feet and assessed their efficacy in enhancing the long-range correlations in the stride parameters for healthy young adults. The vibration could be wirelessly controlled using a smartphone. The actuators, control unit, and battery in the devised shoes were light and embedded in the shoes. By virtue of this compactness, the shoes could be easily used for daily walking outside a laboratory. We performed walking experiments with 20 healthy adults and evaluated the effects of sub- and supra-threshold vibration on long-range correlations in stride interval and length. We performed detrended fluctuation analysis to quantify the long-range correlation of temporal changes in stride interval and length. We found that supra-threshold vibration, applied to the soles with the amplitude of 130 % of the sensory threshold, significantly increased the long-range correlations in stride interval and length by 10.3 % (p = 0.009) and 10.1 % (p = 0.021), respectively. On the other hand, sub-threshold vibration with the amplitude of 90 % of the sensory threshold had no significant effect. These results demonstrate that additional somatosensory feedback through barely detectable vibrations, which are supplied by compact shoes with active insoles, can enhance the indices of “healthy” complexity of locomotor function.

Design and preliminary evaluation of a lower limb exoskeleton based on hydraulic actuator

PurposeThis paper aims to propose a novel system design and control algorithm of lower limb exoskeleton, which provides walking assistance and load sharing for the wearer.Design/methodology/approachIn this paper, the valve-controlled asymmetrical hydraulic cylinder is selected for driving the hip and knee joint of exoskeleton. Pressure shoe is developed that purpose on detecting changes in plantar force, and a fuzzy recognition algorithm using plantar pressure is proposed. Dynamic model of the exoskeleton is established, and the sliding mode control is developed to implement the position tracking of exoskeleton. A series of prototype experiments including benchtop test, full assistance, partial assistance and loaded walking experiments are set up to verify the tracking performance and power-assisted effect of the proposed exoskeleton.FindingsThe control performance of PID control and sliding mode control are compared. The experimental data shows the tracking trajectories and tracking errors of sliding mode control and demonstrate its good robustness to nonlinearities. sEMG of the gastrocnemius muscle tends to be significantly weakened during assisted walking.Originality/valueIn this paper, a structure that the knee joint and hip joint driven by the valve-controlled asymmetrical cylinder is used to provide walking assistance for the wearer. The sliding mode control is proposed to deal with the nonlinearities during joint rotation and fluids. It shows great robustness and frequency adaptability through experiments under different motion frequencies and assistance modes. The design and control method of exoskeleton is a good attempt, which takes positive impacts on the productivity or quality of the life of wearers.

Characterizing the variability of footstep-induced structural vibrations for open-world person identification

Person identification is important in providing personalized services in smart buildings. Many existing studies focus on closed-world person identification, which only identifies a fixed group of people who have training data; however, they assume everyone has pre-collected data, which is not practical in real-world scenarios when newcomers are present. To overcome this drawback, open-world person identification recognizes both newcomers and registered people, which opens up new opportunities for smart building applications that involve newcomers, such as smart visitor management, customized retail, personalized health monitoring, and public emergency assistance. To achieve this, structural vibration sensing has various advantages when compared with the existing sensing modalities (e.g., cameras, wearables, and pressure sensors) because it only needs sparsely deployed sensors mounted on the floor, does not require people to carry devices, and is perceived as more privacy-friendly. However, one fundamental challenge in analyzing footstep-induced structural vibration data is its high variability due to the structural heterogeneity and the footstep variations. Therefore, it is difficult to distinguish different people given this high variability within each person, and it is more challenging to recognize a new person as that data is unobserved before.In this paper, we characterize the variability in footstep-induced structural vibration to develop an open-world person identification framework. Specifically, we address three variability challenges in developing our method. First, the high variability within each person comes from multiple sources that are entangled in the vibration signals, and thus is difficult to be decomposed and reduced. Secondly, the distribution of features extracted from the vibration signals is irregularly shaped, and therefore is difficult to model. Moreover, the identity of the next person is correlated with the previous observations, which makes the identification process more complicated. To overcome these challenges, we first characterize multiple variability sources and design a transformation function that results in signal features that are less variable within one person and more separable between different people. We then develop a modified Chinese Restaurant Process (mCRP) for nonparametric Bayesian modeling to capture the irregularly shaped feature patterns both from local and global perspectives. Finally, we design an adaptive hyperparameter α that represents the prior probability of newcomers at each observation, which keeps updating depending on the time, location, and previous predictions. We evaluate our approach through walking experiments with 20 people across 2 different structures. With only 1 pre-recorded person at each structure, our method achieves up to 92.3% average accuracy with randomly appearing newcomers.

TRANSITION MOTION PATTERN CLASSIFICATION FOR LOWER LIMB EXOSKELETON IN STAIR SCENES BASED ON CNN AND GRU

Motion pattern classification is one of the important research fields in lower extremity exoskeleton robot, it refers to acquiring motion data from multiple sensors installed on the exoskeleton. We designed a wearable lower limb exoskeleton robot with multiple sensors mainly including force sensitive resistors (FSRs) inside smart shoes and encoders inside joints. The wearable robot was used to help people carry the heavy load in the scenes of ascending stairs and descending stairs. The experiments of stair walking were carried out by the subjects who wore the exoskeleton to ascend stairs and descend stairs for a designated time. Before or after the stair walking, the subject would turn to move on flat ground with the result that there existed four transition motions between the stair and flat ground walking. As known, there is less research focusing on the classification of transition motions. The aim of this paper is to classify these motion patterns through a learning algorithm. The convolutional neural network (CNN) and gated recurrent unit (GRU) framework were combined to improve the classification accuracy. Specifically, CNN was used to extract the features of the motion pattern, while GRU was used to extract the temporal correlation during walking. Experimental works showed that the proposed CNN-GRU possessed a significantly high prediction accuracy in motion pattern classification. Compared with CNN, GRU and LSTM-CNN models whose accuracy score does not exceed 93.22%, the proposed CNN-GRU gained a high accuracy of 95.51%.