Article
Robotics
Geoffrey Clark, Heni Ben Amor
Summary: This article presents an imitation learning strategy for extracting ergonomically safe control policies in physical human-robot interaction scenarios. The approach focuses on reducing the risk of injuries and musculoskeletal disorders by anticipating the ergonomic effects of a robot's actions on a human partner. The study introduces ensemble Bayesian interaction primitives and model-predictive control strategy to achieve ergonomic and safe movement regimes.
IEEE TRANSACTIONS ON ROBOTICS
(2023)
Article
Engineering, Electrical & Electronic
Sravan Kumar Challa, Akhilesh Kumar, Vijay Bhaskar Semwal, Nidhi Dua
Summary: This paper proposes an LSTM-based human gait trajectory generator, which analyzes human gait data captured by a low-cost and markerless motion capture sensor system, extracts significant features, and utilizes the Rao-3 metaheuristic optimization algorithm to select important hyperparameters for optimal performance. The stability of the generated gait trajectories is validated through standard evaluation measures and verified on a robot simulator.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Multidisciplinary
Marina Raglianti, Mauro Bologna, Bernardo Tellini
Summary: In this paper, we analyze the human walk movement using a combined deterministic-stochastic model based on a random walk framework. By studying different movement classes using the Laban Effort subcategories, we investigate how deterministic and stochastic forces work together to determine the act of moving and how the stochastic component relates to observed movement changes over time. Our study focuses on analyzing random times of walk movement changes, constructing a waiting time distribution, and implementing a dichotomic stochastic force. We present observed walk trajectories from an experimental analysis involving volunteers to demonstrate the relationship between their walks and measured random times. Finally, we simulate trajectories of a virtual character to showcase our model results.
Article
Chemistry, Analytical
Stefan Grushko, Ales Vysocky, Dominik Heczko, Zdenko Bobovsky
Summary: This study extends the previous approach of improving mutual perception during human-robot collaboration by introducing spatial tactile feedback. Through two user studies, it was demonstrated that the enhanced notification system improved user awareness of the robot's movement plan and was favored by a majority of participants over previous versions.
Review
Mathematics, Applied
Katarina Bod'ova, Richard Kollar, Mario Miglierini
Summary: In this study, the role of intrinsic noise in human walking without orientational cues was investigated. The experiments confirmed veering walking patterns modeled by a stochastic mean reverting process involving walkers' bias and noise. Three parameter regimes corresponding to different walker dynamics were identified, with faster walkers having smaller angular noise but no correlation between angular bias and speed. The level of angular noise was found to be uniform across the studied population.
PHYSICA D-NONLINEAR PHENOMENA
(2022)
Article
Chemistry, Multidisciplinary
Mitsuhiko Kimoto, Takamasa Iio, Masahiro Shiomi, Katsunori Shimohara
Summary: This study proposes a robot conversation strategy using interactive methods to improve indicated object recognition, which proves to be more effective than directly requesting clarifications.
APPLIED SCIENCES-BASEL
(2021)
Article
Multidisciplinary Sciences
Ghiles Mostafaoui, R. C. Schmidt, Syed Khursheed Hasnain, Robin Salesse, Ludovic Marin
Summary: This paper investigates the bodily synchronization between humans and robots in Human Robot Interaction (HRI). The study explores unintentional rhythmic entrainment and synchronization in HRI and compares the stability of coordination under different conditions. The findings suggest that unintentional entrainment is present in HRI, bi-directional coupling produces more stable coordination, and intentional coordination is more stable than unintentional coordination. The study provides a foundation for modeling future social robots involving unintentional and bidirectional synchronization.
Article
Engineering, Biomedical
Tiange Zhang, David J. Braun
Summary: This study proposes a human-driven robot exoskeleton system that can assist humans in accelerating and maintaining high walking speeds, especially when carrying heavy loads. The exoskeleton system utilizes mechanically adaptive spring limbs that emulate the load-bearing mechanics of a bicycle, thus enhancing human weight-bearing and fast-walking abilities.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2022)
Article
Computer Science, Information Systems
Mizuki Takeda, Kaiji Sato, Yasuhisa Hirata, Takahiro Katayama, Yasuhide Mizuta, Atsushi Koujina
Summary: With the aging of the population, there is an increasing demand for care robots to assist the elderly, but cost constraints and anxiety issues remain barriers to widespread adoption. To address the higher functionality required of care robots, this study proposes a CoG candidate calculation method for improved user state estimation during walking and stand-to-sit movements, as well as an anomaly detection method.
Article
Robotics
Connor Esterwood, Kyle Essenmacher, Han Yang, Fanpan Zeng, Lionel P. Robert
Summary: The personality of a robot has an impact on the acceptance of humans. This study conducts a comprehensive meta-analysis of the literature on human-robot interaction, providing insights into the relationship between robot personality and human acceptance. It also identifies gaps in the existing literature and suggests opportunities for future research.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Agriculture, Dairy & Animal Science
Hao-Yu Shih, Mandy B. A. Paterson, Fillipe Georgiou, Clive J. C. Phillips
Summary: We studied 370 human-dog interactions in an animal shelter where volunteers walked shelter dogs, considering canine demographics and behavioural assessments. Relaxed dogs during shelter assessments displayed less reactivity on the leash, while socialised and relaxed dogs showed more positive body language. The volunteers utilized fewer verbal cues and body language with these dogs during walks.
Article
Engineering, Electrical & Electronic
Temitayo Olugbade, Liang He, Perla Maiolino, Dirk Heylen, Nadia Bianchi-Berthouze
Summary: Given the importance of affective touch in human interactions, technology designers are increasingly incorporating this modality into interactive technology. In this survey, the researchers review how affective touch is investigated to enhance and support the human experience with or through technology. They examine its applications in human-computer interaction, human-robot interaction, and real-human-virtual-human interaction, discussing the challenges, findings, and potential for advancing affective touch technology and recognition systems. The researchers also raise ethical issues related to responsible innovation in this growing area.
PROCEEDINGS OF THE IEEE
(2023)
Article
Automation & Control Systems
Dmitry Popov, Anatol Pashkevich, Alexandr Klimchik
Summary: This work focuses on developing an adaptive technique for physical interaction between humans and robots, and conducting experimental validation. The proposed technique utilizes deep residual neural networks and dedicated finite state machines to switch between different robot states based on interaction parameters and characteristics. It ensures human operator safety and improves collaboration performance by implementing various scenarios. Through the use of proprioceptive sensors, the technique selects an appropriate robot reaction strategy based on the parameters of human-robot interaction, classifying interactions into predefined categories. The efficiency of the technique was confirmed through an experimental study involving the collaboration between an industrial manipulator and a human operator.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Longxiang Wang, Chin-Yin Chen, Chongchong Wang, Kaichen Ying, Yanbiao Li, Guilin Yang
Summary: When the stiffness of the environment or people suddenly increases, the robot is prone to instability. This paper proposes an improved observer stabilization method to eliminate the influence of high-frequency noise and reduce misdiagnosis, and ensure the stable operation of the adaptive algorithm by updating the initial environment stiffness.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Automation & Control Systems
Konstantinos Alevizos, Charalampos P. Bechlioulis, Kostas J. Kyriakopoulos
Summary: In this article, the concept of bounded energy collision is introduced for safe interaction in physical human-robot collaboration. The proposed method, which is based on energy dissipation, implements a variable damping strategy to control collision impact and can be used with any physical human-robot interaction strategy that combines indirect force control and estimation of human motion intention. Extensive experimental studies clarify and verify the proposed scheme.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)