兼具安全性与柔顺性的步行康复训练机器人交互方法

提高弱机能群体使用助行机器人的柔顺性和安全性是人机交互领域重要的研究内容。本文提出一种能够兼顾柔顺性、安全性与便捷性的步行康复训练机器人非接触式柔顺控制方法。首先，分析自主研制的步行康复训练机器人结构、功能及工作模式。为准确识别使用者步态意图，研发了一种多通道近距离传感器，并结合机器人的机械结构，搭建了机载内嵌式双腿动态意图识别系统，实现了对双腿步态的实时检测。然后，为提高交互柔顺性，提出一种改进粒子滤波算法，解决了传统粒子滤波算法多次迭代过程中粒子退化问题。最后，通过引入步态速度补偿，设计了具有紧密跟踪人体步态功能的柔顺化控制方法并进行综合性实验。实验表明，本文提出的方法在确保人机交互安全性的基础上，可精确且柔顺地控制机器人的运动状态，从而紧密地跟随人体步态。该非接触式控制方法可以应用于具有类似结构的助行机器人，以及弱机能群体的日常助行与步行康复训练。     

助行机器人系统设计

提出了一种由行走意图引导和动力驱动的搀扶助行机器人系统ZJU Walker,该机器人系统能够为使用者提供身体支撑、行走辅助,并同时保证行走过程的安全性和舒适性.系统采用扭矩传感器作为人机接口感知使用者行走意图,并通过加速度传感器监测使用者行走步态,采用共享控制的方法结合行走意图以及由超声波传感器、红外测距传感器检测到的环境信息控制机器人的运动.介绍了机器人系统的总体框架、传感器系统以及运动控制算法的设计,并给出了实验数据以证明机器人系统的有效性.     

基于强化学习DDPG算法的轮式助行机器人控制方法

在使用轮式助行机器人辅助行走和康复训练过程中，机器人运动控制的稳定性和轨迹跟踪的准确性是人机交互的重要研究内容。本文将强化学习中的深度确定性策略梯度（DDPG）算法与比例积分微分（PID）控制器相结合，提出了一种轮式助行机器人轨迹跟踪方法。首先，对轮式助行机器人底盘的运动学模型进行了分析。其次，介绍了强化学习中的DDPG算法与PID控制器相结合的自适应PID控制器的实现原理和控制结构。最后进行了仿真实验。实验结果表明，与传统PID控制器相比，基于DDPG算法的PID控制器能在机器人系统跟踪期望轨迹时自适应调整参数，使机器人始终按照期望轨迹运动。同时，得益于强化学习的试错机制，控制器具有较强的抗干扰能力。     

基于多传感器的运动训练辅助机器人主动跟踪算法设计

针对运动训练辅助机器人对健美操运动员进行检测与跟踪的准确性问题,提出一种基于多传感器的运动训练辅助机器人主动跟踪算法。首先,对主动跟踪算法的总体方案进行设计,提出了基于视觉传感器的机器人主动跟踪方法和基于声纳传感器的机器人主动跟踪方法;然后,采用基于决策层的数据融合方法将两种跟踪方法获取的跟踪方案进行融合,彼此弥补获取最佳的跟踪方案;最后,通过实验测试提出的算法能否实现机器人对健美操运动员的主动跟踪。实验结果表明：设计的基于多传感器的运动训练辅助机器人主动跟踪算法能够让机器人对健美操运动员进行主动跟踪,且整个跟踪过程能够快速检测到目标并朝之靠拢,同时通过调整自身速度安全、平稳地对目标进行跟踪,能够实现辅助运动员进行训练的目的。     

基于二次判断的无线多传感器跌倒监测系统

通过研究跌倒事件,设计了一种基于多传感器的穿戴式跌倒监测系统.将加速度传感器、磁传感器和压力传感器相结合,采集相互独立的实时数据,并利用阈值和表决算法进行二次判断来提高系统的跌倒识别率.系统实时监测跌倒事件,并根据报警设置提醒误判或者通知家属以得到及时救助.实验结果表明,该系统有较高的识别率和可靠性,适合应用于跌倒监测系统.     

多传感器高斯混合PHD融合多目标跟踪方法

针对复杂环境下单传感器多目标跟踪方法效果不佳的问题,基于FISST（Finite set statistics）跟踪理论提出一种多传感器高斯混合PHD（Probability hypothesis density）多目标跟踪方法.首先,分析了FISST下多传感器PHD的形式化滤波器,在此基础上构建一种反馈式多传感器PHD融合跟踪框架;进一步利用高斯混合技术提出多传感器PHD跟踪方法;最后,通过解决多传感器后验PHD粒子匹配与融合问题提出三种算法.仿真实验表明,与常规高斯混合PHD跟踪算法相比,本文所提算法能够有效提高目标跟踪精度和鲁棒性.     

基于多传感器的可变形机器人自主控制方法研究

将GPS、电子罗盘、倾角仪、码盘传感器应用到可变形机器人自主运动控制中。针对可变形机器人自身结构特点，提出了一种基于多传感器信息融合的可变形机器人在野外环境中自主控制的方法。该方法主要实现了在非结构环境中机器人的自主变形、自主避障和自主导航定位的功能。实验验证了该方法的有效性。     

扫地机器人增强位姿融合的Cartographer算法及系统实现

Cartographer是谷歌在2016年开源的一个可以在多传感器配置下实现低计算资源消耗的SLAM算法框架.本文针对原有Cartographer中位姿融合不准确,存在延迟的问题,首先设计了一种基于位姿增量的多传感器位姿融合方法;随后针对扫地机器人Player平台,设计并实现基于增强Cartographer算法的多模块SLAM系统;最后通过Cartographer数据集的实验分析和真实场景的实际测试,本论文验证了增强Cartographer算法的有效性以及SLAM系统在Player机器人平台上的可用性.     

基于加速度传感器的老年人跌倒检测装置设计

为了提供老年人安全保障和保护用户隐私,设计了一种基于加速度传感器的跌倒检测装置.针对独居老人的特点,结合微传感器、数字信号处理以及无线传输等技术,利用人体运动产生的加速度,提出了一种鲁棒的跌倒算法.该装置在人体佩戴实验中,可以区分出正常人体活动与跌倒事件,自动发出跌倒报警信号,从而使用户在尽可能短的时间内得到医疗救护.     

基于三轴加速度传感器的人体跌倒检测系统设计与实现

为了满足老年人的护理需求,减少老年人因跌倒造成的身心伤害,提出了一种基于三轴加速度传感器的人体跌倒检测系统。该系统主要基于姿态测量特性,利用姿态角作为跌倒判断标准;并且考虑到噪声影响和跌倒检测系统对检测正确率的高要求,利用Kalman滤波算法来提高算法精确度。实验结果表明该系统在人体前后、侧向跌倒和跌倒后迅速站起的情况下可以100%报警,达到人体正常跌倒情况的检测标准。     

Reinforcement learning-based shared control for walking-aid robot and its experimental verification

A walking-aid robot is an assistive device for enabling safe, stable and efficient locomotion in elderly or disabled individuals. In this paper, we propose a reinforcement learning-based shared control (RLSC) algorithm for intelligent walking-aid robot to address existing control problems in cooperative walking-aid robot system. Firstly, the intelligent walking-aid robot and the human walking intention estimation algorithm are introduced. Due to the limited physical and cognitive capabilities of elderly and disabled people, robot control input assistance is provided to maintain tactile comfort and a sense of stability. Then, considering the robot’s ability to autonomously adapt to different user operation habits and motor abilities, the RLSC algorithm is proposed. By dynamically adjusting user control weight according to different user control efficiencies and walking environments, the robot can improve the user’s degree of comfort when using the device and automatically adapting to user’s behaviour. Finally, the effectiveness of our algorithm is verified by experiments in a specified environment.     

Intelligent mobile walking-aids: perception,control and safety

Robot-assisted walking has become a popular research field for helping mobility-limited people to walk more easily. Different from other walking-aid devices (e.g. exoskeletons and prosthesis), intelligent mobile walking-aids (IMWs) are invented for helping the visually impaired or people in need (e.g. the elderly) to walk in daily life. This paper reviews various related literatures on IMWs and dwells on three kinds of perception systems and perception algorithms of IMWs to explain how IMWs understand the user's motion states or tendency. Besides, the control strategies of IMWs under the normal case concerned are classified and compared. The safety measures for preventing the user from abnormal cases (e.g. encountering obstacles, the user's stumbling and falling, faults of IMWs) are introduced in detail as well. The performance of current safety measures for the user's fall detection and prevention has been evaluated and concluded. At the end of the article, the discussion and perspective of IMWs are presented.     

HMM-based state classification of a user with a walking support system using visual PCA features

The improvement of safety and dependability in systems that physically interact with humans requires investigation with respect to the possible states of the user’s motion and an attempt to recognize these states. In this study, we propose a method for real-time visual state classification of a user with a walking support system. The visual features are extracted using principal component analysis and classification is performed by hidden Markov models, both for real-time fall detection (one-class classification) and real-time state recognition (multi-class classification). The algorithms are used in experiments with a passive-type walker robot called “RT Walker” equipped with servo brakes and a depth sensor (Microsoft Kinect). The experiments are performed with 10 subjects, including an experienced physiotherapist who can imitate the walking pattern of the elderly and people with disabilities. The results of the state classification can be used to improve fall-prevention control algorithms for walking support systems. The proposed method can also be used for other vision-based classification applications, which require real-time abnormality detection or state recognition.     

基于参数化最优的仿人机器人倒地运动控制

针对仿人机器人的倒地运动控制,用经典的参数化优化方法求得最优控制函数的一个近似解．然后, 利用参数化控制及强化技术,基于几个分段的常数去逼近最优解,再将最优控制问题转化为一系列参数优化问题． 利用该方法提出了仿人机器人倒地优化控制算法,并与遗传算法进行了比较．最后,通过仿真对算法进行了验证．     

自主柔性变形蛇形机器人控制系统设计

针对搜救机器人对多信息获取与处理、远程监控与运动控制的实时高性能需求,设计了以ARM微处理器STM32为核心、多传感器融合的自主柔性变形蛇形机器人控制系统,实现了机器人的远程监控与运动控制、多传感器环境信息采集等功能。整个控制系统具有良好的扩展性、硬件可裁剪性。通过模拟灾难废墟场景实验,结果表明：蛇形机器人控制系统可实现多信息的实时准确无线通信,在不同的环境中,具有良好的多步态运动稳定性和自主移动性能。     

Direction-changing fall control of humanoid robots: theory and experiments

Humanoid robots are expected to share human environments in the future and it is important to ensure the safety of their operation. A serious threat to safety is the fall of such robots, which can seriously damage the robot itself as well as objects in its surrounding. Although fall is a rare event in the life of a humanoid robot, the robot must be equipped with a robust fall strategy since the consequences of fall can be catastrophic. In this paper we present a strategy to change the default fall direction of a robot, during the fall. By changing the fall direction the robot may avoid falling on a delicate object or on a person. Our approach is based on the key observation that the toppling motion of a robot necessarily occurs at an edge of its support area. To modify the fall direction the robot needs to change the position and orientation of this edge vis-a-vis the prohibited directions. We achieve this through intelligent stepping as soon as the fall is predicted. We compute the optimal stepping location which results in the safest fall. Additional improvement to the fall controller is achieved through inertia shaping, which is a principled approach aimed at manipulating the robot’s centroidal inertia, thereby indirectly controlling its fall direction. We describe the theory behind this approach and demonstrate our results through simulation and experiments of the Aldebaran NAO H25 robot. To our knowledge, this is the first implementation of a controller that attempts to change the fall direction of a humanoid robot.     

Obstacle avoidance with translational and efficient rotational motion control considering movable gaps and footprint for autonomous mobile robot

This paper presents a sensor-based real-time obstacle avoidance method for an autonomous omnidirectional mobile robot based on simultaneous control of translational and efficient rotational motion considering movable gaps and the footprint. Autonomous mobile service robots that have been developed in recent years have arms that work and execute tasks. Depending on the task using moving parts, the shape of the robot (i.e., the footprint) changes. In this study, to improve the safety and possibility of reaching a goal even through a narrow gap with unknown obstacles, a sensor-based real-time obstacle avoidance method with simultaneous control of translational and efficient rotational motion (without unnecessary rotational motion) based on the evaluation of movable gaps and the footprint is proposed. To take account of the anisotropy footprint of the robot, multiple-circle robot model is proposed. In this paper, a novel control method based on fuzzy set theory is presented. To verify the effectiveness of the proposed method, several simulations and experiments are carried out.

     

Adaptive Polar-Space Motion Control for Embedded Omnidirectional Mobile Robots with Parameter Variations and Uncertainties

This paper presents an adaptive polar-space motion controller for trajectory tracking and stabilization of a three-wheeled, embedded omnidirectional mobile robot with parameter variations and uncertainties caused by friction, slip and payloads. With the derived dynamic model in polar coordinates, an adaptive motion controller is synthesized via the adaptive backstepping approach. This proposed polar-space robust adaptive motion controller was implemented into an embedded processor using a field-programmable gate array (FPGA) chip. Furthermore, the embedded adaptive motion controller works with a reusable user IP (Intellectual Property) core library and an embedded real-time operating system (RTOS) in the same chip to steer the mobile robot to track the desired trajectory by using hardware/software co-design technique and SoPC (system-on-a-programmable-chip) technology. Simulation results are conducted to show the merit of the proposed polar-space control method in comparison with a conventional proportional-integral (PI) feedback controller and a non-adaptive polar-space kinematic controller. Finally, the effectiveness and performance of the proposed embedded adaptive motion controller are exemplified by conducting several experiments on steering an embedded omnidirectional mobile robot.     

Real-time compliance control of an assistive joint using QNX operating system

An assistive robot is a novel service robot, playing an important role in the society. For instance, it can amplify human power not only for the elderly and disabled to recover/rehabilitate their lost/impaired musculoskeletal functions but also for healthy people to perform tasks requiring large forces. Consequently, it is required to consider both accurate position control and human safety, which is the compliance. This paper deals with the robot control compliance problem based on the QNX real-time operating system. Firstly, the mechanical structure of a compliant joint on the assistive robot is designed using Solidworks. Then the parameters of the assistive robot system are identified. The software of robot control includes data acquisition and processing, and control to meet the compliance requirement of the joint control. Finally, a Hogan impedance control experiment is carried out. The experimental results prove the effectiveness of the method proposed.