Walking Direction Research Articles

A Privacy-Protecting Step-Level Walking Direction Detection Algorithm Based on Floor Vibration

We present an algorithm and measurement system to detect the walking direction of persons based on ground vibrations. The approach is privacy-preserving because it solely relies on piezoelectric sensors built into the floor. Therefore, our system can be used in areas where cameras are not allowed or cannot capture the entire area. We present and compare our two innovative methods to analyze the ground vibrations caused by footsteps: the multi-peaks average algorithm (MPAA) and the multi-peaks averaged feature with a deep neural network-based classifier (MPAF-DNNC). MPAA judges the walking direction of pedestrians by analyzing the time-space relationship of at least two consecutive footstep vibration signals from multiple sensors. MPAF-DNNC receives multi-peaks averaged feature as input and uses a deep neural network-based classifier to judge walking direction. Our experiments and evaluation show that our system can correctly determine the walking direction based on only 3 input step events and provides an average F1 score of 0.97. When more than 5 step events are inputted, the proposed system can correctly determine the walking direction with an average F1 score of 1.00.

Robust and reusable self-organized locomotion of legged robots under adaptive physical and neural communications.

Animals such as cattle can achieve versatile and elegant behaviors through automatic sensorimotor coordination. Their self-organized movements convey an impression of adaptability, robustness, and motor memory. However, the adaptive mechanisms underlying such natural abilities of these animals have not been completely realized in artificial legged systems. Hence, we propose adaptive neural control that can mimic these abilities through adaptive physical and neural communications. The control algorithm consists of distributed local central pattern generator (CPG)-based neural circuits for generating basic leg movements, an adaptive sensory feedback mechanism for generating self-organized phase relationships among the local CPG circuits, and an adaptive neural coupling mechanism for transferring and storing the formed phase relationships (a gait pattern) into the neural structure. The adaptive neural control was evaluated in experiments using a quadruped robot. The adaptive neural control enabled the robot to 1) rapidly and automatically form its gait (i.e., self-organized locomotion) within a few seconds, 2) memorize the gait for later recovery, and 3) robustly walk, even when a sensory feedback malfunction occurs. It also enabled maneuverability, with the robot being able to change its walking speed and direction. Moreover, implementing adaptive physical and neural communications provided an opportunity for understanding the mechanism of motor memory formation. Overall, this study demonstrates that the integration of the two forms of communications through adaptive neural control is a powerful way to achieve robust and reusable self-organized locomotion in legged robots.

HINNet: Inertial navigation with head-mounted sensors using a neural network

Human inertial navigation systems have been developing rapidly in recent years, and it has shown great potential for applications within healthcare, smart homes, sports, and emergency services. Placing inertial measurement units on the head for localisation is relatively new. However, it provides a very interesting option, as there are several everyday head-worn items that could easily be equipped with sensors. Yet, there remains a lack of research in this area and currently no localisation solutions have been offered that allow for free head-rotations during long periods of walking. To solve this problem, we present HINNet, the first deep neural network (DNN) pedestrian inertial navigation system allowing free head movements with head-mounted inertial measurement units (IMUs), which deploys a 2-layer bi-directional LSTM. A new ’peak ratio’ feature is introduced and utilised as part of the input to the neural network. This information can be leveraged to solve the issue of differentiating between changes in movements related to the head and those that are associated with the walking pattern. A dataset with 8 subjects totalling 528 min has been collected on three different tracks for training and verification. The HINNet could effectively distinguish head rotations and changes in walking direction with a distance percentage error of 0.46%, a relative trajectory error of 3.88 m, and a absolute trajectory error of 5.98 m, which outperforms the current best head-mounted Pedestrian Dead Reckoning (PDR) method.

Evaluation of pollutant exposure using virtual walkers and large-eddy simulation: Application to an idealised urban neighbourhood

Urban air quality studies have primarily focused on pollutant dispersion; however, spatial or temporal concentrations collected at discretely distributed grid points (or fixed receptors) do not reflect the actual pollutant exposure of pedestrians. Using large-eddy simulation (LES) with virtual walkers implemented, this study investigates pollutant exposure of walking agents (or moving receptors) in an urban turbulent boundary-layer flow developed over an aligned building array under the influence of different wind directions. The spatial variability of the exposure risks are found to be better captured by the moving receptors than the fixed receptors along the same agent walking tracks. We demonstrate that the actual exposure can differ significantly from results interpreted from data recorded by the fixed receptors (corresponding to Eulerian estimates) and show that large discrepancies occur in avenues near the source, wherein dispersion of the point release has not occurred on larger spatiotemporal scales. In most scenarios, optimal evacuation routes are shown to be ones that deviate as much as possible from the dominant wind direction; however, one needs to decide the priority of moving to further avenues first or immediately adjusting the walking direction. The results should serve as a useful baseline reference for environmental health impact assessment and evacuation route planning against hazardous releases of air pollutants in more complex urban environments.

RadarPDR: Radar-Assisted Indoor Pedestrian Dead Reckoning

Pedestrian dead reckoning (PDR) is the critical component in indoor pedestrian tracking and navigation services. While most of the recent PDR solutions exploit in-built inertial sensors in smartphones for next step estimation, due to measurement errors and sensing drift, the accuracy of walking direction, step detection, and step length estimation cannot be guaranteed, leading to large accumulative tracking errors. In this paper, we propose a radar-assisted PDR scheme, called RadarPDR, which integrates a frequency-modulation continuous-wave (FMCW) radar to assist the inertial sensors-based PDR. We first establish a segmented wall distance calibration model to deal with the radar ranging noise caused by irregular indoor building layouts and fuse wall distance estimation with acceleration and azimuth signals measured by the inertial sensors of a smartphone. We also propose a hierarchical particle filter(PF) together with an extended Kalman filter for position and trajectory adjustment. Experiments have been conducted in practical indoor scenarios. Results demonstrate that the proposed RadarPDR is efficient and stable and outperforms the widely used inertial sensors-based PDR scheme.

Smoothness of Gait in Overweight (But Not Obese) Children Aged 6-10.

Excessive body mass represents a serious threat to the optimal psychophysical development of children, and it is known to be able to significantly affect their locomotor capabilities, making them more prone to the development of musculoskeletal disorders. However, despite the relevant number of existing studies, a clear gait pattern of overweight children has not been defined yet, particularly in the case of a mass excess that is relatively small (i.e., in those not obese). In the present study, we employed a wearable inertial measurement unit placed on the low back to derive spatio-temporal parameters and quantify the smoothness of gait (by means of harmonic ratio) from trunk accelerations acquired during gait trials carried out by 108 children aged 6-10 (46% males), stratified into two groups according to their body mass index (normal weight, n = 69 and overweight, n = 39). The results show that while gait speed, stride length, cadence and double support duration were found to be almost identical in the two groups, significant differences were observed in terms of harmonic ratio. In particular, overweight children exhibited a reduced harmonic ratio in the antero-posterior direction and higher harmonic ratio in the medio-lateral direction. While the significantly lower harmonic ratio in the antero-posterior direction is likely to be indicative of a loss of smoothness in the walking direction, probably due to a combination of factors associated with the altered movement biomechanics, the higher harmonic ratio in the medio-lateral direction might be associated with specific strategies adopted to increase lateral stability. Although further studies are necessary to elucidate the specific mechanisms that influence the smoothness of gait, it is noteworthy that harmonic ratios appear sensitive even to subtle change in locomotor control in overweight children characterized by apparently regular spatio-temporal parameters of gait and might be employed to assess the effectiveness of interventions designed to improve mobility functions.

Were timbers transported to Chaco using tumplines? A feasibility study

Between 850 and 1200 CE, approximately 200,000+ large timbers were transported >75 km to Chaco Canyon using only human power. Researchers have proposed various load-carriage methods, speculated about how many porters would be needed and their speed of transport, but none have conducted empirical investigations. Here, we explore the feasibility of long-distance timber transport using tumplines, a technology well-evidenced in Chaco’s archaeological record. Two authors trained themselves to use tumplines and together carried a 60 kg timber 25 km with the timber oriented transverse to the walking direction. Total elapsed time was <10 h and walking speed averaged 4.5 km/hr. Individual walking speed with a 30 kg tumpline load was only ∼10 % slower than the preferred unladen walking speed. Timber transport to Chaco using tumplines is clearly feasible. We close by considering the implications of tumpline timber transport on the socio-political dynamics of Chacoan society.

Influence of Foot Morphology on the Center of Pressure Pattern in Patients with Down Syndrome

The primary aim of this study was to assess how different conformations of the foot in individuals with Down syndrome affected the CoP during walking, and the secondary aim was to evaluate the effect of an excess of mass in young adults and children with Down syndrome and flat foot. The greater investigation of these aspects will allow for more targeted rehabilitation treatments to improve a patient's quality of life. The tests were carried out on 217 subjects with Down syndrome, 65 children and 152 young adults, and on 30 healthy individuals, 19 children and 11 young adults. All subjects underwent gait analysis, and the group with Down syndrome was also assessed with baropodometric tests to evaluate foot morphology. The statistical analysis showed that within both the young adult and child groups, the CoP pattern in the anterior-posterior direction reflected a difficulty in proceeding in the walking direction compensated by a medio-lateral swing. The gait of children with Down syndrome was more impaired than that of young adults. In both young adults and children, a higher severity of impairment was found in overweight and obese female individuals. These results suggest that the sensory deficits and the development of hypotonic muscles and lax ligaments of the syndrome lead to morphological alterations of the foot that, combined with the physical characteristics of short stature and obesity, negatively impact the CoP pattern of people with Down syndrome during walking.

DeepStep: Direct Detection of Walking Pedestrian From Motion by a Vehicle Camera

Pedestrian detection has wide applications in intelligent transportation. It is essential to understand pedestrian&#x2019;s position and action instantaneously for autonomous driving. Most algorithms divide these tasks into sequential procedures where pedestrians are detected from shape-based features in video frames, and their behaviors are analyzed with frame tracking. Different from those, this work introduces a deep learning-based pedestrian detection method that only uses motion cues. The pedestrian motion, which is much different from that of static background and dynamic vehicles, is investigated in the spatial-temporal domain. The pedestrian leg movement forms a chain-type trace in the motion profile images even if the ego-vehicle moves. Instead of modeling walking actions based on kinematics, the chain structure is directly learned from a large pedestrian dataset in driving videos. This method works for the more challenging scenes observed on moving vehicles than those scenes from static cameras. The aim is to detect not only pedestrians promptly but also predict their walking direction in the driving space. Since a video is reduced to temporal images, real-time performance is achieved with a high mean average precision and a low false-positive rate on a publicly available dataset.

A Learning-Free Method for Locomotion Mode Prediction by Terrain Reconstruction and Visual-Inertial Odometry.

This research introduces a novel, highly precise, and learning-free approach to locomotion mode prediction, a technique with potential for broad applications in the field of lower-limb wearable robotics. This study represents the pioneering effort to amalgamate 3D reconstruction and Visual-Inertial Odometry (VIO) into a locomotion mode prediction method, which yields robust prediction performance across diverse subjects and terrains, and resilience against various factors including camera view, walking direction, step size, and disturbances from moving obstacles without the need of parameter adjustments. The proposed Depth-enhanced Visual-Inertial Odometry (D-VIO) has been meticulously designed to operate within computational constraints of wearable configurations while demonstrating resilience against unpredictable human movements and sparse features. Evidence of its effectiveness, both in terms of accuracy and operational time consumption, is substantiated through tests conducted using open-source dataset and closed-loop evaluations. Comprehensive experiments were undertaken to validate its prediction accuracy across various test conditions such as subjects, scenarios, sensor mounting positions, camera views, step sizes, walking directions, and disturbances from moving obstacles. A comprehensive prediction accuracy rate of 99.00% confirms the efficacy, generality, and robustness of the proposed method.

An Optimization Method Combining RSSI and PDR Data to Estimate Distance between Smart Devices for COVID‐19 Contact Tracing

Distance estimation methods arise in many applications, such as indoor positioning and COVID‐19 contact tracing. The received signal strength indicator (RSSI) is favored in distance estimation. However, the accuracy is not satisfactory due to the signal fluctuation. Besides, the RSSI‐only method has a large‐ranging error because it uses fixed parameters of the path loss model. Here, we propose an optimization method combining RSSI and pedestrian dead reckoning (PDR) data to estimate the distance between smart devices. The PDR may provide high accuracy of walking distance and direction. Moreover, the parameters of the path loss model are optimized to dynamically fit the complex electromagnetic environment. The proposed method is evaluated in outdoor and indoor environments and compared with the RSSI‐only method. The results show that the mean absolute error is reduced up to 0.51 m and 1.02 m, with an improvement of 10.60% and 64.55% for outdoor and indoor environments, respectively, compared with the RSSI‐only method. Consequently, the proposed optimization method has better accuracy of distance estimation than the RSSI‐only method, and its feasibility is demonstrated through real‐world evaluations.

Supplemental Material for Adaptation to Walking Direction in Biological Motion

Supplemental Material for Adaptation to Walking Direction in Biological Motion

Algorithm and Examples of an Agent-Based Evacuation Model

This research establishes a “detect-decide-action” agent-based evacuation model based on the social force model, introducing an active steering force into the basis of the dynamic equation with the combination of the behavioral decision model and the probability model. In the AEM, the detection algorithm is used to identify pedestrians or obstacles within the detection radius to provide the next walking direction and apply the active steering force. The obstacle avoidance algorithm is the core of the “action” link. This research focuses on the establishment of the following and bypassing algorithm when moving in the same direction, and the algorithm of a detour when moving in the opposite direction, applying C++ programming language to achieve the basic evacuation behavior simulation of avoiding pedestrians and obstacles in the actual scene. The results show that compared with the grid model and the general social force model, the agent model (AEM) solves the problem of the distortion of evacuation behavior to some extent, and the pedestrian is more flexible in the choice of evacuation path.

Does attention influence who you follow in a crowd? Tracking neighbors vs. following your friends

Does attention increase the influence of neighbors in a crowd? Rio, Dachner, & Warren’s (2018) model assumes ensemble perception of crowd motion, and yet it seems that we can follow our friends and ignore others. We adapted the Multiple Object Tracking paradigm to test whether selective attention to a subset of the crowd spontaneously influences following behavior. In Experiment 1, the participant walked with a virtual crowd 9 neighbors, viewed in an HMD. At the beginning of each trial, a target set of 2-6 neighbors, or all 9 neighbors (control), blinked on and off; participants were instructed to attend to and track those neighbors as they walked with the crowd. The heading (walking direction) of targets or distractors was perturbed (±20°) midway through the trial. As a tracking check, a randomized memory probe appeared at the end of the trial. Participant heading, speed, facing direction (yaw angle) and probe responses were recorded. A linear mixed effects regression revealed that participant heading was influenced by the number of turning neighbors (χ2(1) = 17.19, p < 0.001), but not by attention to targets. Rather, participant heading was statistically equivalent to the average heading direction of the crowd (BF01 = 11.90), consistent with ensemble perception. Probe responses were highly accurate, indicating that participants successfully tracked targets. In Experiment 2, we tested whether participants can follow a group of “friends” when explicitly instructed to do so. Participants were first trained to recognize a set of avatar friends, which replaced blinking targets; otherwise the design was the same. In this case, participants fully segmented friends from a crowd of strangers and exclusively followed them (χ2(1) = 59.27, p<0.001), breaking ensemble perception. Subsequent experiments are investigating whether this “friend” effect is due to task-relevant attention (explicit instructions to follow targets) or grouping by familiarity.

Blurring Boundaries: Weakening 3rd-order Motion Reduces Locomotor Responses When Following A Crowd

Collective motion in human crowds can emerge from pedestrians locally following their neighbors. Previously we showed that the visual-motor system relies on 3rd-order motion (tracking boundary features), not 1st-order motion (motion energy) (Lu & Sperling, 1995), to follow a crowd. We used the reverse-phi illusion to put 1st- and 3rd-order motion in conflict. Here we show that weakening 3rd-order motion by blurring object boundaries reduces both heading and speed responses, when in conflict with 1st-order motion. Participants (n=12) wore a wireless head-mounted display (101ºH x 105ºV, 90 Hz) and were asked to “walk with” a crowd of virtual objects as if they are real people. The ‘crowd’ consisted of 9 rectangles (1.6mV x 0.5mH) mapped with a Julesz texture. The ‘crowd’ initially moved forward at 1.2 m/s, then was briefly perturbed (heading perturbation: ±20˚, translation left or right; speed perturbation: ±0.2 m/s, optical expansion or contraction). During the perturbation, object texture underwent constant 4-frame reverse-phi motion so 1st-order texture motion was in the same or opposite direction as 3rd-order boundary motion (Same/Opposite Condition). Object boundaries were blurred at three different levels (Zero, Small, Large). The participant’s walking direction and speed were recorded. In the Opposite condition, locomotor responses progressively decreased as object boundaries were more blurred (heading: 15.3˚, 13.2˚, 12.1˚; speed: 0.072, 0.041, 0.039 m/s, respectively), consistent with reliance on 3rd-order motion. In the Same condition, on the other hand, responses increased with more blur (heading: 16.4˚, 17.1˚, 18.3˚; speed: 0.105, 0.119, 0.121 m/s, respectively), likely because texture motion was faster than boundary motion. Linear mixed effects models found significant main effects and interactions for all comparisons. The results confirm that following a crowd is dominated by 3rd-order motion of bounded ‘figures’, although 1st-order motion can also influence responses when 3rd-order motion is weak.

Synthesizing the optimal gait of a quadruped robot with soft actuators using deep reinforcement learning

Quadruped robots have the advantages of traversing complex terrains that are difficult for wheeled robots. Most of the reported quadruped robots are built by rigid parts. This paper proposes a new design of quadruped robots using soft actuators driven by tendons as the four legs. Compared to the rigid robots, the proposed soft quadruped robot has inherent safety, less weight and simpler mechanism for fabrication and control, but the corresponding challenge is that the accurate mathematical model applicable to model-based control design of the soft robot is difficult to derive by dynamics. To synthesize the optimal gait controller of the soft-legged robot, the paper makes the following contributions. First, the flexible components of the quadruped robot are modeled with different finite element and lumped parameter methods. The model accuracy and computation efficiency are analyzed. Second, soft actor–critic methods and curriculum learning are applied to learn the optimal gaits for different walking tasks. Third, The learned gaits are implemented in an in-house robot to transport hand tools. Preliminary results show that the robot can walk forward and correct the walking directions.

Passive infrared sensor dataset and deep learning models for device-free indoor localization and tracking

Location estimation or localization is one of the key components in IoT applications such as remote health monitoring and smart homes. Amongst device-free localization technologies, passive infrared (PIR) sensors are one of the promising options due to their low cost, low energy consumption, and good accuracy. However, most of the existing systems are complexly designed and difficult to deploy in real life, in addition, there is no public dataset available for researchers to benchmark their proposed localization and tracking methods. In this paper, we propose a system and a dataset collected from our PIR system consisting of commercial-of-the-shelf (COTS) sensors without any modification. Our dataset includes profile data of 36 classes that have over 1,000 samples of different walking directions and test data consisting of multiple scenarios with a sequence length of over 2,000 timesteps. To evaluate our system and dataset, we implement various deep learning methods such as CNN, RNN, and CNN–RNN. Our results prove the applicability and feasibility of our system and illustrate the viability of deep learning methods for PIR-based localization and tracking. We also show that our dataset can be converted for coordinate estimation so that deep learning methods and particle filter approaches can be applied to estimate coordinates. As a result, the best performer achieves a distance error of 0.25 m.

Pedestrian Trajectory Prediction in Heterogeneous Traffic using Facial Keypoints-based Convolutional Encoder-decoder Network

Future pedestrian trajectory prediction offers great prospects for many practical applications such as unmanned vehicles, building evacuation design and robotic path planning. Most existing methods focus on social interaction among pedestrians but ignore the fact that heterogeneous traffic objects (cars, dogs, bicycles, motorcycles, etc.) have significant influence on the future trajectory of a subject pedestrian. Also, the walking direction intention of a pedestrian may be referred by his/her facial keypoints. Considering this, this work proposes to predict a pedestrian's future trajectory by jointly using neighboring heterogeneous traffic information and his/her facial keypoints. To fulfill this, an end-to-end facial keypoints-based convolutional encoder-decoder network (FK-CEN) is designed, in which the heterogeneous traffic and facial keypoints are input. After training, FK-CEN is evaluated on 5 crowded video sequences collected from the public datasets MOT-16 and MOT-17. Experimental results demonstrate that it outperforms state-of-the-art approaches, in terms of prediction errors.

Emotional characteristic analysis of human gait while real-time movie viewing.

Emotion recognition is useful in many applications such as preventing crime or improving customer satisfaction. Most of current methods are performed using facial features, which require close-up face information. Such information is difficult to capture with normal security cameras. The advantage of using gait and posture over conventional biometrics such as facial features is that gaits and postures can be obtained unobtrusively from faraway, even in a noisy environment. This study aims to investigate and analyze the relationship between human emotions and their gaits or postures. We collected a dataset made from the input of 49 participants for our experiments. Subjects were instructed to walk naturally in a circular walking path, while watching emotion-inducing videos on Microsoft HoloLens 2 smart glasses. An OptiTrack motion-capturing system was used for recording the gaits and postures of participants. The angles between body parts and walking straightness were calculated as features for comparison of body-part movements while walking under different emotions. Results of statistical analyses show that the subjects' arm swings are significantly different among emotions. And the arm swings on one side of the body could reveal subjects' emotions more obviously than those on the other side. Our results suggest that the arm movements together with information of arm side and walking straightness can reveal the subjects' current emotions while walking. That is, emotions of humans are unconsciously expressed by their arm swings, especially by the left arm, when they are walking in a non-straight walking path. We found that arm swings in happy emotion are larger than arm swings in sad emotion. To the best of our knowledge, this study is the first to perform emotion induction by showing emotion-inducing videos to the participants using smart glasses during walking instead of showing videos before walking. This induction method is expected to be more consistent and more realistic than conventional methods. Our study will be useful for implementation of emotion recognition applications in real-world scenarios, since our emotion induction method and the walking direction we used are designed to mimic the real-time emotions of humans as they walk in a non-straight walking direction.

L-DOPA enhances neural direction signals in younger and older adults

Previous studies indicate a role of dopamine in spatial navigation. Although neural representations of direction are an important aspect of spatial cognition, it is not well understood whether dopamine directly affects these representations, or only impacts other aspects of spatial brain function. Moreover, both dopamine and spatial cognition decline sharply during age, raising the question which effect dopamine has on directional signals in the brain of older adults. To investigate these questions, we used a double-blind cross-over L-DOPA/Placebo intervention design in which 43 younger and 37 older adults navigated in a virtual spatial environment while undergoing functional magnetic resonance imaging (fMRI). We studied the effect of L-DOPA, a dopamine precursor, on fMRI activation patterns that encode spatial walking directions that have previously been shown to lose specificity with age. This was done in predefined regions of interest, including the early visual cortex, retrosplenial cortex, and hippocampus. Classification of brain activation patterns associated with different walking directions was improved across all regions following L-DOPA administration, suggesting that dopamine broadly enhances neural representations of direction. No evidence for differences between regions was found. In the hippocampus these results were found in both age groups, while in the retrosplenial cortex they were only observed in younger adults. Taken together, our study provides evidence for a link between dopamine and the specificity of neural responses during spatial navigation. Significance StatementThe sense of direction is an important aspect of spatial navigation, and neural representations of direction can be found throughout a large network of space-related brain regions. But what influences how well these representations track someone’s true direction? Using a double-blind cross-over L-DOPA/Placebo intervention design, we find causal evidence that the neurotransmitter dopamine impacts the fidelity of direction selective neural representations in the human hippocampus and retrosplenial cortex. Interestingly, the effect of L-DOPA was either equally present or even smaller in older adults, despite the well-known age related decline of dopamine. These results provide novel insights into how dopamine shapes the neural representations that underlie spatial navigation.