Analyzing human motion is an active research area, with various applications. In this work, we focus on human motion analysis in the context of physical rehabilitation using a robot coach system. Computer-aided assessment of physical rehabilitation entails evaluation of patient performance in completing prescribed rehabilitation exercises, based on processing movement data captured with a sensory system, such as RGB and RGB-D cameras. As 2D and 3D human pose estimation from RGB images had made impressive improvements, we aim to compare the assessment of physical rehabilitation exercises using movement data obtained from both RGB-D camera (Microsoft Kinect) and estimation from RGB videos (OpenPose and BlazePose algorithms). A Gaussian Mixture Model (GMM) is employed from position (and orientation) features, with performance metrics defined based on the log-likelihood values from GMM. The evaluation is performed on a medical database of clinical patients carrying out low back-pain rehabilitation exercises, previously coached by robot Poppy.
Several modern vehicles provide the option to select a driving mode. However, the literature contains no empirical studies that investigate how driving modes affect the vehicle's dynamic behaviour in regular on-road driving. We examined for which CAN-bus signals the differences between Renault's Multi-Sense® comfort and sport modes are most apparent. We gathered data on a 26.3 km route containing a rural and highway section. A single person drove the route four times in comfort mode and four times in sport mode. By statistically analysing and ordering 887 CAN-bus signals, we found strong differences between the two modes for rear-wheel angle, engine torque, longitudinal acceleration, and vertical motion. Parameter identification of a quarter car model identified a 3.5 times higher damping coefficient for the sport mode compared to the comfort mode. Due to four wheel steering, compared to the comfort mode, the sport mode yielded a higher lateral acceleration and yaw rate for a given steering wheel angle and driving speed. In conclusion, this study provides quantitative insight into the extent to which the Multi-Sense driving modes impact the vehicle's lateral, longitudinal, and vertical dynamic behaviour. The results and the analysis methods help guide future driving mode designs.
Research related to regulatory focus theory has shown that the way in which a message is conveyed can increase the effectiveness of the message. While different research fields have used this theory, in human-robot interaction (HRI), no real attention has been given to this theory. In this paper, we investigate it in an in the wild scenario. More specifically, we are interested in how individuals react when a robot suddenly appears at their office doors. Will they interact with it or will they ignore it? We report the results from our experimental study in which the robot approaches 42 individuals. Twenty-nine of them interacted with the robot, while the others either ignored it or avoided any interaction with it. The robot displayed two types of behavior (i.e., promotion or prevention). Our results show that individuals that interacted with a robot that matched their regulatory focus type interacted with it significantly longer than individuals that did not experience regulatory fit. Other qualitative results are also reported, together with some reactions from the participants.
Some robots for human-robot interaction are designed with female or male physical appearance. Other robots are endowed with no gender characteristics, namely genderless robots, such as Pepper and NAO robot. A robot with male or female physical appearance should possess the mapped speech gender style during a natural human-robot interaction, which can be learned from humans' male or female speech. In this paper, we make a new trial to synthesis gender-free speeches for physically genderless robots, which is promising in order to improve a more natural human-robot interaction with genderless robots. Our gender style-controlled speech synthesizer takes the speech text and gender style embedding as inputs to generate speech audio. A speech gender encoder network is used to extract the embedding of the speech gender style with female and male speeches as input. Based on the distribution of the female and male gender style embedding, we explore the gender-free speech style embedding space where we sample some gender-free embedding vectors to generate genderless speech audio. This is a preliminary work where we show how the genderless speech audio wave will be synthesized from text.
The world population is growing older. Global aging is occurring at a rate never seen before, it is expected that in 2040 there will be three times more people over the age 85 than there are today. Even if nursing homes and other care facilities can provide assistance, space and staff shortages are already becoming an issue. One of the aims of this work is to show the benefits of robot's physical embodiment in human-robot social interactions. The social therapist robot tries to provide customized cognitive stimulation by playing a music game with the participant. The results of the pilot study over a 6 month period depict a more efficient, natural, and preferred interaction with the robot rather than with the simulated robot.