Maria Kyrarini

Human-Robot Synergy For Cooperative Robots

This paper presents two human-robot cooperative application scenarios of the project MeRoSy (Human-Robot Synergy) funded by the German Federal Ministry of Education and Research. The first scenario relates to the human-robot cooperation in an industrial application, while the second one refers to the robotic workplace assistance for people with disabilities. The presented scenarios reflect different aspects of human-robot interaction, among others different novel possibilities for human-robot interaction depending on different physical abilities of human co-worker. Beside the consideration of the human-robot cooperative technologies in two MeRoSy scenarios, this paper considers also the identification and classification of the ethical, legal and social implications (ELSI) in the context of human-robot cooperation.

Comparison of vision-based and sensor-based systems for joint angle gait analysis

Gait analysis has become recently a popular research field and been widely applied to clinical diagnosis of neurodegenerative diseases. Various low-cost sensor-based and vision-based systems are developed for capturing the hip and knee joint angles. However, the performances of these systems have not been validated and compared between each other. The purpose of this study is to set up an experiment and compare the performances of a sensor-based system with multiple inertial measurement units (IMUs), a vision-based gait analysis system with marker detection, and a markerless vision-based system on capturing the hip and knee joint angles during normal walking. The obtained measurements were validated with the data acquired from goniometers as ground truth measurement. The results indicate that the IMUs-based sensor system gives excellent performance with small errors, while vision systems produce acceptable results with slightly larger errors.

Monitoring of gait performance using dynamic time warping on IMU-sensor data

In this paper, a novel method for monitoring the changes in gait joint angle trajectories recorded using the low-cost and wearable Inertial Measurement Units (IMU) is presented. The introduced method is based on Dynamic Time Warping (DTW), an algorithm commonly used for evaluating the similarity of two time series which may vary in time and speed. DTW is employed as the measure of distance between two gait trajectories taken in different time instances, which could be used as an intuitive and effective measure for the evaluation of gait performances. The experimental results presented in the paper demonstrate that the proposed method is applicable for clinically relevant applications and is consequently adaptable to patients with diseases characterized with gait disorders and to different walking scenarios. The proposed method was firstly validated by applying the DTW-based measure on gait trajectories of five healthy subjects recorded while simulating different levels of walking disabilities. Then proposed measure was applied to estimate the distance between the “healthy” gait trajectories and gait trajectories of three patients with Parkinsons disease (PD) while performing single-task and dual-task overground walking. Also, the proposed measure was demonstrated as an effective measure for monitoring the changes in gait patterns of a PD patient before and after medication-based treatment. This result indicates potential use of proposed method for effective pharmacological management of PD.

Comparison of Dynamic Vision Sensor-Based and IMU-based systems for ankle joint angle gait analysis

Gait analysis is an important research field in neurodegenerative disease diagnosis. Various IMU-based and vision-based methods have been developed for measuring joint angles during walking process. Dynamic Vision Sensor (DVS) is a neuromorphic engineering product which outputs sequences of events describing the level of brightness change at the pixel level in an asynchronized manner, instead of discrete frames at a predefined frame rate. Due to its microsecond level resolution, DVS is regarded possessing a huge potential to dramatically increase the speed of sensing pipeline for various applications which traditional CMOS camera cannot fulfill. Hence, in this paper we introduce a novel system for gait analysis application; DVS and special markers are used to detect the ankle joint during walking and a method is developed to calculate the desired angle. Further, the robust locally weighted regression is employed as signal smoothing method to reduce the amount of noise. In order to evaluation its performance, an Inertial Measurement Unit (IMU)-based sensory system is also examined and compared in the same experiment and goniometer is used for providing the ground truth. By comparing the captured ankle joint angle trajectories using Dynamic Time Warping (DTW), DVS-based system appears to have higher accuracy in terms of ankle joint angle detection than IMU-based system.

RGB-D Camera based 3D Human Mouth Detection and Tracking Towards Robotic Feeding Assistance

In this paper, an RGB-D camera based framework for the recognition and tracking of the human mouth for the purpose of autonomous r obotic feeding is presented. The method employs the state-of-the-art face detection algorithm to acquire the 2D facial landmarks, and the corresponding 3D position of the human mouth is calculated using the depth information. In addition, a 3D point cloud visualizer of the human face with marked facial landmarks is provided for the purpose of visualization. The proposed system is applied in real-time vision-based robot control. Experiments indicate the validity of the proposed work in localising the mouth of different subjects served by the robot with a cup of water.

Head Gesture-based Control for Assistive Robots

Development of assistive robotics to enable people with disabilities to work is a challenging topic. Hands-free interfaces can support a person with severe motor impairments to control robotic manipulators. The paper focuses on developing a head gesture interface, which enables the end-user to control a dual-arm industrial robot. A motion sensor is located on the head of the end-user. Support vector machine is used to recognize the head gestures and an intuitive Graphical User Interface is developed to help the user to navigate through different control modes. To evaluate the proposed framework, an industrial pick and place task was performed.

Skill robot library: Intelligent path planning framework for object manipulation

Commonly used path planning techniques for object manipulation are computationally expensive and time-consuming. In this paper, a novel framework called Skill Robot Library (SRL), which has competence to store only the keypoints of a path rather than complete, is presented. The path can be computed with path planner or taught by a human using kinesthetic teaching. Additionally, when the environment is static and only the requested new start and goal positions are changed with respect to the start and goal positions of the stored path, the SRL can retrieve and modify the stored path. The SRL forwards the final path to the robot for reproduction. Experimental results achieved with a six degrees of freedom robotic arm are presented together with performance evaluation of the SRL and the path planner is demonstrated via a series of experiments.