Article
Robotics
Fatemeh Zahedi, Dongjune Chang, Hyunglae Lee
Summary: This letter introduces a user-adaptive variable damping controller that improves the overall performance of coupled human-robot systems during physical interaction. Bayesian optimization is used to evaluate and optimize the controller performance, considering the uncertainty of human behaviors and noisy observations. Experiments with a robotic arm manipulator show that the adaptive control strategy significantly reduces energy expenditure and improves stability, agility, and user effort.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Shane Saunderson, Goldie Nejat
Summary: This letter proposes a novel hybrid hierarchical learning architecture for robot persuasive behaviors in social human-robot interaction. The architecture is able to adapt to both static and dynamic considerations of users, improving learning speed and robustness.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Cheng Fang, Luka Peternel, Ajay Seth, Massimo Sartori, Katja Mombaur, Eiichi Yoshida
Summary: The advancement of human modeling and robotics have common interests and interconnections. The principles used in robotics, such as multibody dynamics and control theory, have greatly benefited human modeling. With the development of safer and smarter robots, they actively participate in our lives and assist us. By combining human modeling and robotic methods in physical human-robot interaction, it can lead to improved human understanding and functional assistance.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Robotics
Mario Selvaggio, Marco Cognetti, Stefanos Nikolaidis, Serena Ivaldi, Bruno Siciliano
Summary: Sharing control of a robotic system with an autonomous controller allows humans to reduce cognitive and physical workload during tasks, and recent developments in inference and learning techniques have expanded the applications of shared control approaches. This enables robotic systems to seamlessly adapt their autonomy levels. This letter compiles the latest research results in shared control and shared autonomy, with a focus on physical human-robot interaction, discussing architectures and methods developed for shared control and shared autonomy. The letter concludes with a discussion on open issues.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Computer Science, Information Systems
Roman Michalik, Ales Janota, Michal Gregor, Marian Hrubos
Summary: This paper discusses an approach for controlling a cooperating YuMi robot using hand gestures recognized by a camera and artificial intelligence through a TCP/IP connection with Python. The program can be enhanced by integrating other IoT devices for robot control and data collection for specific applications.
Article
Engineering, Biomedical
Christian Tamantini, Francesca Cordella, Clemente Lauretti, Francesco Scotto di Luzio, Benedetta Campagnola, Laura Cricenti, Marco Bravi, Federica Bressi, Francesco Draicchio, Silvia Sterzi, Loredana Zollo
Summary: This paper presents a psychophysiological-aware control strategy for upper limb robot-aided orthopedic rehabilitation, which can adapt treatments to patients' needs. The strategy has three main features: i) generating point-to-point trajectories inside an adaptable workspace, ii) providing assistance in guiding patients' limbs, allowing them to move with spatial and temporal autonomy, and iii) tuning control parameters based on patients' kinematics performance and psychophysiological state. The strategy has been validated in a clinical setting and shown to have a positive impact on participants, leading to improved motor functions.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Review
Computer Science, Information Systems
S. M. Bhagya P. Samarakoon, M. A. Viraj J. Muthugala, A. G. Buddhika P. Jayasekara
Summary: An emerging trend of using service robots in various applications is seen as a promising effort to improve the quality of life. These robots are designed for non-expert users and often need to navigate in environments with humans. Therefore, it is important for these robots to exhibit human-friendly navigation behavior. This paper presents a review on Human-Robot Proxemics (HRP), including user studies and methods for establishing HRP awareness in service robots. The review identifies limitations in current state-of-the-art research and suggests potential future work. Additionally, it summarizes important HRP parameters and behavior from existing user studies, providing valuable data for developing HRP-aware behavior in service robots.
Article
Psychology, Multidisciplinary
Patrick P. Weis, Cornelia Herbert
Summary: This study investigated the impact of human-robot interaction on emotional concepts, finding that interacting with emotionless robots led to less positive emotional self-concept, while interacting with autonomous or emotional robots led to more positive emotional robot-concept. The results suggest that beliefs and interactions with telepresent robots can shape emotional concepts, with implications for well-being, performance, and interaction style.
COMPUTERS IN HUMAN BEHAVIOR
(2022)
Article
Robotics
Nuria Pena Perez, Jonathan Eden, Ekaterina Ivanova, Etienne Burdet, Ildar Farkhatdinov
Summary: By perturbing the haptic and visual feedback of the right hand, the effort distribution between the two hands can be altered. Visual disturbance was more effective in causing participants to rely solely on their unperturbed hand.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Tsung-Ren Huang, Yu-Wei Liu, Shin-Min Hsu, Joshua O. S. Goh, Yu-Ling Chang, Su-Ling Yeh, Li-Chen Fu
Summary: Personal psychological variables are valuable for personalized human-robot interactions. This study demonstrated the validity of embedding psychological test questions into casual conversations for user profiling, with strong correlation in young adults but only moderate in older populations. It suggests caution when applying this testing method to older adults or other special populations.
INTERNATIONAL JOURNAL OF SOCIAL ROBOTICS
(2021)
Article
Robotics
Marta Lagomarsino, Marta Lorenzini, Merryn Dale Constable, Elena De Momi, Cristina Becchio, Arash Ajoudani
Summary: This letter investigates the possibility of applying the cognitive science principle of humans acting coefficiently as a group to human-robot cooperative tasks, aiming to promote more seamless and natural interaction. A modelling approach is proposed to capture the implicit indicators of human comfort and discomfort, as well as robot energy consumption, in order to measure human-robot coefficiency. Reinforcement learning is then employed to adapt and learn the combination of robot interaction parameters that maximize such coefficiency. The results demonstrate that by acting coefficiently, the robot can meet individual preferences, improve human comfort, and foster trust in the robotic partner.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Computer Science, Interdisciplinary Applications
Luca Gualtieri, Erwin Rauch, Renato Vidoni
Summary: This study presents a systematic methodology for static allocation of assembly tasks between humans and robots, considering a human-centric approach and requirements in terms of technical feasibility, safety and ergonomics, quality, and economics. It helps manufacturers overcome technical barriers and implement more sustainable, high-quality, and efficient manufacturing processes.
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING
(2023)
Article
Engineering, Mechanical
Di Shi, Wuxiang Zhang, Wei Zhang, Linhang Ju, Xilun Ding
Summary: The study proposes a human-centered adaptive control method for a lower limb rehabilitation robot, which overcomes errors and uncertainties by establishing human-robot interaction and dynamic models, and designing an adaptive controller to ensure system stability.
MECHANISM AND MACHINE THEORY
(2021)
Article
Robotics
Robin Jeanne Kirschner, Henning Mayer, Lisa Burr, Nico Mansfeld, Saeed Abdolshah, Sami Haddadin
Summary: In this study, the Expectable Motion Unit (EMU) is proposed to prevent sudden, uncontrolled motions in human-robot interaction (HRI). By establishing a mapping between robot velocity, robot-human distance, and the relative frequency of involuntary motions (IM), the robot's speed during task execution is limited in real-time. The EMU is integrated into a holistic safety framework that considers both physical and psychological safety knowledge.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Robotics
Luis F. C. Figueredo, Rafael Castro Aguiar, Lipeng Chen, Samit Chakrabarty, Mehmet R. Dogar, Anthony G. Cohn
Summary: This study presents a new metric for calculating quality index in human manipulation and physical human-robot collaboration, addressing the gap in current research. The proposed solution combines pre-computation of biomechanics, ergonomics, muscle assessment, and joint constraints to simplify manipulability assessment for various applications. Numerical evidence shows that the analysis greatly outperforms previous results in terms of computing time without compromising performance.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Management
Jens Witkowski, Rupert Freeman, Jennifer Wortman Vaughan, David M. Pennock, Andreas Krausee
Summary: In this paper, two novel forecasting competition mechanisms are introduced, aiming to incentivize truthful reporting and select the most accurate forecaster. The first mechanism guarantees the selection of the most accurate forecaster with higher probability than any other. The second mechanism selects the best forecaster with probability approaching one as the number of events grows.
MANAGEMENT SCIENCE
(2023)
Review
Chemistry, Multidisciplinary
Philippe Schwaller, Alain C. Vaucher, Ruben Laplaza, Charlotte Bunne, Andreas Krause, Clemence Corminboeuf, Teodoro Laino
Summary: New data-driven technologies have revolutionized chemical reaction tasks, including reaction prediction, optimization, and catalyst design. Accurate prediction of chemical reactivity has transformed the R&D processes and accelerated discovery in academia and the chemical and pharmaceutical industries.
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE
(2022)
Article
Biochemical Research Methods
William Poole, Ayush Pandey, Andrey Shur, Zoltan Tuza, Richard Murray
Summary: This paper introduces a new software package called BioCRNpyler, which aims to support the rapid development and exploration of mathematical models of biochemical networks and circuits. BioCRNpyler allows users to generate large complex models using very few lines of code in a modular way. It uses a powerful representation of biochemical circuits, defining their parts, underlying biochemical mechanisms, and chemical context independently. Developed in Python, it is accessible to beginners and customizable for advanced users. Ultimately, BioCRNpyler can accelerate the computer automated design of biochemical circuits and model-driven hypothesis generation in biology.
PLOS COMPUTATIONAL BIOLOGY
(2022)
Article
Physics, Nuclear
Johannes Kirschner, Mojmir Mutny, Andreas Krause, Jaime Coello de Portugal, Nicole Hiller, Jochem Snuverink
Summary: Tuning machine parameters of particle accelerators is a challenging task that is difficult to automate. This study proposes and evaluates a step-size limited variant of safe Bayesian optimization on two research facilities of the PSI. Promising experimental results were reported, tuning up to 16 parameters subject to 224 constraints.
PHYSICAL REVIEW ACCELERATORS AND BEAMS
(2022)
Article
Multidisciplinary Sciences
Chelsea Y. Hu, Richard M. Murray
Summary: In this study, the researchers validate the effectiveness of layered control in improving system performance using a synthetic biomolecular network in living cells. The findings also contribute to the understanding of genetic feedback control architectures in nature.
NATURE COMMUNICATIONS
(2022)
Article
Multidisciplinary Sciences
Rory L. Williams, Richard M. Murray
Summary: The authors developed a terminal differentiation gene circuit in E. coli to improve the evolutionary stability of burdensome engineered functions. This strategy allows cells to express burdensome functions while limiting their proliferation to prevent the propagation of advantageous loss-of-function mutations. Terminal differentiation increases the duration and yield of high-burden expression and can be further improved with strategic redundancy.
NATURE COMMUNICATIONS
(2022)
Article
Multidisciplinary Sciences
John P. Marken, Richard M. Murray
Summary: Engineered consortia are a major research focus for synthetic biologists, and DNA messaging is a promising candidate for implementing complex communication. The authors develop a framework for addressable and adaptable DNA messaging using plasmid conjugation in E.coli. Their system can bias the transfer of messages and dynamically update recipient lists to control information flow. This work lays the foundation for engineering previously-inaccessible levels of complexity into biological systems.
NATURE COMMUNICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Fatemeh Aghlmand, Chelsea Y. Hu, Saransh Sharma, Krishna Pochana, Richard M. Murray, Azita Emami
Summary: Integrating silicon chips and live bacterial biosensors in a miniaturized cell-silicon system has great potential in smart medicine and environmental sensing. This study presents a fully integrated fluorescence sensor in 65-nm standard CMOS, which enables efficient detection of fluorescent proteins and improves sensitivity and signal-to-noise ratio. The sensor can measure the dynamics of fluorescence signals and the growth of live E. coli cells, and distinguish between two biochemical signals by detecting different fluorescent proteins. Proof of concept shows bidirectional communication between living cells and the CMOS chip using optogenetics. This integrated system provides a promising platform for future closed-loop therapeutics.
IEEE JOURNAL OF SOLID-STATE CIRCUITS
(2023)
Article
Management
Jens Witkowski, Rupert Freeman, Jennifer Wortman Vaughan, David M. Pennock, Andreas Krausee
Summary: This paper initiates the study of incentive-compatible forecasting competitions and introduces two novel mechanisms with the objectives of incentivizing truthful reporting and selecting the most accurate forecaster. The mechanisms are easy to implement and can be applied to problems such as ranking forecasters and hiring accurate forecasters for future events.
MANAGEMENT SCIENCE
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Mojmir Mutny, Johannes Kirschner, Andreas Krause
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Philippe Wenk, Gabriele Abbati, Michael A. Osborne, Bernhard Scholkopf, Andreas Krause, Stefan Bauer
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Johannes Kirschner, Ilija Bogunovic, Stefanie Jegelka, Andreas Krause
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Mojmir Mutny, Michal Derezinski, Andreas Krause
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108
(2020)
Article
Automation & Control Systems
Pragnya Alatur, Kfir Y. Levy, Andreas Krause
JOURNAL OF MACHINE LEARNING RESEARCH
(2020)