Alessandro Filippeschi

Vibrotactile perception assessment for a rowing training system

This paper presents a vibrotactile methodology for a rowing training system. Since hands trajectories are fundamental in the rowing gesture, it is completely necessary to search and develop new technologies and techniques that can interact and help the user to perform a better movement. These methodologies must be as natural as possible in order to guarantee the transparency in the feedback of the system. Therefore this paper presents an analysis of visual, visual-tactile and tactile training strategies to understand the importance in the order and the period of time when each one is applied. Data analysis shows the importance of combining visual and tactile feedbacks to obtain the best results in the improvements of the user skills.

Survey of Motion Tracking Methods Based on Inertial Sensors: A Focus on Upper Limb Human Motion

Motion tracking based on commercial inertial measurements units (IMUs) has been widely studied in the latter years as it is a cost-effective enabling technology for those applications in which motion tracking based on optical technologies is unsuitable. This measurement method has a high impact in human performance assessment and human-robot interaction. IMU motion tracking systems are indeed self-contained and wearable, allowing for long-lasting tracking of the user motion in situated environments. After a survey on IMU-based human tracking, five techniques for motion reconstruction were selected and compared to reconstruct a human arm motion. IMU based estimation was matched against motion tracking based on the Vicon marker-based motion tracking system considered as ground truth. Results show that all but one of the selected models perform similarly (about 35 mm average position estimation error).

A novel 7 degrees of freedom model for upper limb kinematic reconstruction based on wearable sensors

Wearable motion tracking systems have gained large popularity in the last decades because of their effectiveness in many fields, from performance assessment to human-robot interaction. Among all the approaches, those based on inertial sensors have been widely explored. Since inertial sensors are affected by measurements drift, they need to be aided by other sensors, thus requiring sensor measurements to be fused. The most used sensor fusion techniques are based on Kalman filter. In particular, the Extended Kalman Filter (EKF) and the Unscented Kalman Filter (UKF) are used because of the non linearity characterizing most of the models. They often aim at reconstructing human motion by estimating limbs orientation, involving humans kinematics to constrain relative motion of the limbs. These models often neglect part of the degrees of freedom (DoFs) that characterize human upper limbs, especially when modeling humerus motion with respect to the chest. In this paper we present a novel 7 DoFs model which represents a trade-off between modeling accuracy and complexity for the human upper limb. In particular, we model the human shoulder girdle taking into account also the humerus heads elevation and the retraction due to the scapulas and the clavicles motions. The model exploits inertial sensors measurements by means of an Unscented Kalman filter to reconstruct human movements. The system performance is validated firstly against a reconstruction based on an optical tracking system. Secondly, the 5 DoFs model extracted form the 7 DoFs one was checked to have state of the art performance and used to estimate the improvement of position estimation that are obtained by extending the model to 7 DoFs.

Integration of multimodal technologies for a rowing platform

This paper presents the integration of multimodal technologies to measure and transmit different variables and stimuli involved in the human motion analysis, both for the training and for the transfer of users skills achieved by means of a mechatronic rowing platform. Although the mechanical design is the core of this project, this paper describes the integration and interaction of two multimodal systems (the human being and the rowing platform). These systems works together using different sensors and methodologies directly integrated to the human body to obtain detailed information related to the synchronization and correlation among the trajectories, Proximal distance coupling, velocities, muscular activation and muscular force, transversal force in the oars and head position acquired through digital image processing and machine learning techniques. This information is evaluated and used in the rendering section through audio-tactile stimuli for the acceleration learning process

Energy management using virtual reality improves 2000-m rowing performance

Abstract Elite-standard rowers tend to use a fast-start strategy followed by an inverted parabolic-shaped speed profile in 2000-m races. This strategy is probably the best to manage energy resources during the race and maximise performance. This study investigated the use of virtual reality (VR) with novice rowers as a means to learn about energy management. Participants from an avatar group (n = 7) were instructed to track a virtual boat on a screen, whose speed was set individually to follow the appropriate to-be-learned speed profile. A control group (n = 8) followed an indoor training programme. In spite of similar physiological characteristics in the groups, the avatar group learned and maintained the required profile, resulting in an improved performance (i.e. a decrease in race duration), whereas the control group did not. These results suggest that VR is a means to learn an energy-related skill and improve performance.

Structuring a virtual environment for sport training: A case study on rowing technique

The advancements in technology and the possibility of their integration in the domain of virtual environments allow access to new application domains previously limited to highly expensive setups. This is specifically the case of sport training that can take advantage of the improved quality of measurement systems and computing techniques. Given this the challenge that emerges is related to the way training is performed and how it is possible to evaluate the transfer from the virtual setup to the real case. In this work we discuss the aspect of system architecture for a VE in sport training, taking as a case study a rowing training system. The paper will address in particular the challenges of training technique in rowing.

Sensor fusion for complex articulated body tracking applied in rowing

This paper presents a sensor fusion model for integrating wearable inertial measures with sensors in the environment. This approach is designed and tested to support body motion tracking of rowing in indoor and outdoor environments. This paper presents the approach based on a complex kinematic model and Unscented Kalman filtering. The approach is validated in an indoor setup based on the SPRINT rowing system by comparison against results obtained from a commercial motion capture system, thus providing future directions for the assessment of rowers’ performance on an instrumented boat.

Preliminary design of rowing simulator for in-door skill training

In this paper we report on the preliminary design of a rowing simulator to be integrated in a VR sport training system for rowing. The proposed simulator aims at bringing in an indoor location the specific features and situations of outdoor rowing, by means of an enhanced Virtual Environment (VE) that combines visual, haptic, acoustic flows to proprio- and exteroception of user status. This paper describes the experimental activities carried out on in-door rowing to characterize the main features of the stroke gesture, the design and analytical study of a fluidodynamic dissipator for force rendering and an overview of graphic simulation and of the overall system architecture.

Encountered haptic Augmented Reality interface for remote examination

This paper presents an interaction system for haptic based remote palpation and in general remote examination. In particular the proposed approach combines 3D representation of the remote environment with encountered haptic feedback aiming at high transparency and natureleness of interaction. The paradigm is described as interaction design and system implementation.

Boat Dynamics and Force Rendering Models for the SPRINT System

The skills professional rowing indoor training (SPRINT) system is designed to support rowing training. The system includes a configurable instrumented rowing apparatus that supports sculling and sweep rowing and that is coupled with a virtual reality display and haptic feedback. Herein, the system has been updated with models that aim at improving force rendering and at simulating the rowing dynamics. These new models support the rendering of vertical and horizontal forces on the hands and they estimate the effects that actions performed on SPRINT would produce on an actual rowing shell. A proof of concept evaluation with one expert and one intermediate rower included a comparison of data gathered on an actual boat and with SPRINT. Outputs of the boat dynamics model showed to be consistent when compared both with the literature and on-boat data. Moreover, these preliminary data suggest boat dynamics output to be useful to discriminate expertise. In addition, subjective ratings of kinematic features and force rendering by expert and intermediate rowers indicated that they find SPRINT suitable for training.