基于堆叠深度卷积沙漏网络的步态识别

提出了一种基于堆叠深度卷积沙漏网络的步态识别方法。为了解决人体建模中关节点准确定位的问题，采用基于深度卷积的沙漏网络来提取步态图上的关节点坐标，并计算肘关节与膝关节的角度作为运动特征。为了解决行走速度变化带来的影响，采用动态时间规整（Dynamic Time Warping）对特征序列进行距离计算。通过最近邻分类器对结果进行准确分类。该方法在公共CASIA-B数据集与TUM-GAID数据集上进行了验证并与其他方法进行比较，结果表明该方法有较高的识别率。     

适应不同重力环境的仿壁虎机器人运动仿真

针对不同重力环境下仿壁虎机器人的运动稳定性、运动高效协调性等问题,基于四足机器人的步态规划现状和仿壁虎机器人自身特定的机械结构,设计了仿壁虎机器人在g、0、-g 3种环境下的足端轨迹和运动步态。在ADAMS仿真软件中研究了机器人的运动学和动力学特性,得到了仿壁虎机器人稳定爬行与脚掌黏附力、足端轨迹和运动步态的关系。探讨了仿真结果的合理性和局限性,为仿壁虎机器人在实际环境中的稳定运动奠定了理论基础。     

Terrain classification and adaptive locomotion for a hexapod robot Qingzhui

Frontiers of Mechanical Engineering - Legged robots have potential advantages in mobility compared with wheeled robots in outdoor environments. The knowledge of various ground properties and...     

Gait event detection algorithm based on smart insoles

Gait analysis is an effective clinical tool across a wide range of applications. Recently, inertial measurement units have been extensively utilized for gait analysis. Effective gait analyses require good estimates of heel‐strike and toe‐off events. Previous studies have focused on the effective device position and type of triaxis direction to detect gait events. This study proposes an effective heel‐strike and toe‐off detection algorithm using a smart insole with inertial measurement units. This method detects heel‐strike and toe‐off events through a time‐frequency analysis by limiting the range. To assess its performance, gait data for seven healthy male subjects during walking and running were acquired. The proposed heel‐strike and toe‐off detection algorithm yielded the largest error of 0.03 seconds for running toe‐off events, and an average of 0–0.01 seconds for other gait tests. Novel gait analyses could be conducted without suffering from space limitations because gait parameters such as the cadence, stance phase time, swing phase time, single‐support time, and double‐support time can all be estimated using the proposed heel‐strike and toe‐off detection algorithm.     

Effects of free-choice pasture access on lameness recovery and behavior of lame dairy cattle

Lameness is a common condition in dairy cows. Free-choice access to pasture may benefit lame cows by providing a softer and more comfortable lying and standing surface; however, the effects of this system on lameness have not yet been explored. We evaluated whether a 7-wk period of free-choice pasture access would improve lameness recovery and affect the lying behavior of lame dairy cows. Lactating Holstein cows, all clinically lame upon enrollment and housed inside a freestall barn, were pseudo-randomly allocated to 1 of 2 treatments (balancing for gait score, parity, and previous lameness history): free-choice access to pasture (n = 27; pasture) or indoor housing only (n = 27; indoor). Cows were gait scored weekly by an observer blind to treatment, using a 5-point numerical rating system (NRS 1 = sound, NRS 5 = severely lame), and hoof inspections were performed by professional trimmers at the start and end of the 7-wk period. Lying behavior was assessed using accelerometers. Cows were categorized as either having a sound period (NRS <2 over 2 consecutive weeks) or remaining lame. Cows spent, on average, 14.8 ± 10.0% (mean ± SD) of their total time on pasture, with much of this time spent outside at night. Over the 7-wk period, 42% of cows had at least one sound period (pasture: 55.6%, indoor: 26.9%), but this was more likely for cows with pasture access (odds ratio = 4.1; 95% confidence interval: 1.1–14.6%). Pasture cows also spent more total weeks sound compared with indoor cows (2.0 ± 0.34 vs. 0.81 ± 0.35 wk). Cows with pasture access lay down for less overall time than indoor cows (13.9 ± 0.29 vs. 12.7 ± 0.28 h/d) and spent more time standing on pasture (74%) than when indoors (47%). These results suggest that lame dairy cows will use pasture when provided with free-choice access, primarily at night, and that access to pasture aids in lameness recovery. We encourage future research to investigate longer-term effects on the recovery of hoof lesions and reoccurrence of lameness cases.     

双分支特征融合网络的步态识别算法

目的 在步态识别算法中,基于外观的方法准确率高且易于实施,但对外观变化敏感;基于模型的方法对外观变化更加鲁棒,但建模困难且准确率较低。为了使步态识别算法在获得高准确率的同时对外观变化具有更好的鲁棒性,提出了一种双分支网络融合外观特征和姿态特征,以结合两种方法的优点。方法 双分支网络模型包含外观和姿态两条分支,外观分支采用GaitSet网络从轮廓图像中提取外观特征;姿态分支采用5层卷积网络从姿态骨架中提取姿态特征。在此基础上构建特征融合模块,融合外观特征和姿态特征,并引入通道注意力机制实现任意尺寸的特征融合,设计的模块结构使其能够在融合过程中抑制特征中的噪声。最后将融合后的步态特征应用于识别行人身份。结果 实验在CASIA-B （Institute of Automation,Chinese Academy of Sciences,Gait Dataset B）数据集上通过跨视角和不同行走状态两种实验设置与目前主流的步态识别算法进行对比,并以Rank-1准确率作为评价指标。在跨视角实验设置的MT （medium-sample training）划分中,该算法在3种行走状态下的准确率分别为93.4%、84.8%和70.9%,相比性能第2的算法分别提升了1.4%、0.5%和8.4%;在不同行走状态实验设置中,该算法在两种行走状态下的准确率分别为94.9%和90.0%,获得了最佳性能。结论 在能够同时获取外观数据和姿态数据的场景下,该算法能够有效地融合外观信息和姿态信息,在获得更丰富的步态特征的同时降低了外观变化对步态特征的影响,提高了步态识别的性能。     

水田土壤上典型步态及其参数对足式机器人能耗的影响

通过ABAQUS建立了足式机器人单腿有限元模型和土壤有限元模型,进行了有限元动力学仿真,探究水田土壤环境下足式机器人典型步态（矩形、修正摆线、椭圆、零冲击）及其参数对单位能耗的影响规律,并在自主研发的足　地作用机理试验台上,设计了与仿真试验参数相同的实际试验,验证了仿真试验结果的正确性。结果表明,椭圆步态能耗性能最好,在步高H=40 mm时,椭圆步态最小单位能耗比矩形、修正摆线、零冲击步态最小单位能耗分别减小12.5%、11%、12%。仿真试验与实际试验机械腿行走足迹比较吻合。仿真试验与实际试验得到的机械腿膝关节和髋关节扭矩吻合程度较好。     

一种轮腿复合型机器人的步态研究与越障性能分析

为实现地面移动机器人在复杂地形下的环境探索需求,结合轮式机器人的高速特性和足式机器人对地形适应性强的特征,提出一种轮幅型轮腿复合型机器人,并针对其在移动过程中的振动问题以及爬梯过程中的越障问题,对机器人进行步态研究及性能分析。从静力学分析中得出机器人轮腿结构以不同姿态着地时的受力情况,结合实际情况中机器人运动约束对机器人在前进、转向和越障等任务中的步态进行分析,并基于动力学仿真ADAMS软件建立动力学模型来模拟机器人不同步态下的振动情况以及越障性能。研究结果表明,结合本文提出的步态控制方法,该轮腿复合型机器人在复杂地形环境中具有较好的行进效率和越障能力。     

An intermittent control model of flexible human gait using a stable manifold of saddle-type unstable limit cycle dynamics

Stability of human gait is the ability to maintain upright posture during walking against external perturbations. It is a complex process determined by a number of cross-related factors, including gait trajectory, joint impedance and neural control strategies. Here, we consider a control strategy that can achieve stable steady-state periodic gait while maintaining joint flexibility with the lowest possible joint impedance. To this end, we carried out a simulation study of a heel-toe footed biped model with hip, knee and ankle joints and a heavy head-arms-trunk element, working in the sagittal plane. For simplicity, the model assumes a periodic desired joint angle trajectory and joint torques generated by a set of feed-forward and proportional-derivative feedback controllers, whereby the joint impedance is parametrized by the feedback gains. We could show that a desired steady-state gait accompanied by the desired joint angle trajectory can be established as a stable limit cycle (LC) for the feedback controller with an appropriate set of large feedback gains. Moreover, as the feedback gains are decreased for lowering the joint stiffness, stability of the LC is lost only in a few dimensions, while leaving the remaining large number of dimensions quite stable: this means that the LC becomes saddle-type, with a low-dimensional unstable manifold and a high-dimensional stable manifold. Remarkably, the unstable manifold remains of low dimensionality even when the feedback gains are decreased far below the instability point. We then developed an intermittent neural feedback controller that is activated only for short periods of time at an optimal phase of each gait stride. We characterized the robustness of this design by showing that it can better stabilize the unstable LC with small feedback gains, leading to a flexible gait, and in particular we demonstrated that such an intermittent controller performs better if it drives the state point to the stable manifold, rather than directly to the LC. The proposed intermittent control strategy might have a high affinity for the inverted pendulum analogy of biped gait, providing a dynamic view of how the step-to-step transition from one pendular stance to the next can be achieved stably in a robust manner by a well-timed neural intervention that exploits the stable modes embedded in the unstable dynamics.     

Kinetic changes in gait during low magnitude military load carriage

Indian infantry soldiers carry smaller magnitudes of loads for operational requirements. The ground reaction forces (GRFs) and impulse responses of 10 healthy male Indian infantry soldiers were collected while they walked carrying operational loads between 4.2 and 17.5 kg (6.5–27.2% of mean body weight (BW)) and a control condition of no external load (NL). The GRF and impulse components were normalised for BW, and data for each load condition were compared with NL in each side applying one-way analysis of variance followed by Dunnett's post hoc test. Right foot data were compared with corresponding left foot GRF data for all load conditions and NL. There were significant increases in vertical and anteroposterior GRFs with increase in load. Left and right feet GRF data in corresponding load conditions were significantly different in anteroposterior plane. No significant change was observed in the temporal components of support phase of gait. Changes in impulse parameter were observed in the anteroposterior and vertical planes while carrying load greater than 23 and 16.6% of BW for the right foot and left foot, respectively. Result indicates that smaller magnitudes of loads produced kinetic changes proportional to system weight, similar to heavier loads with the possibility of increased injury risk. Observed smaller asymmetric changes in gait may be considered as postural adjustment due to load. Unique physical characteristics of Indian soldiers and the probable design shortcomings of the existing backpack might have caused significant changes in GRF and peak impulse during smaller load carriage.