Welcome to the 6th edition of Robo-Insight, our robotics news update! In this post, we are excited to share a variety of new developments in this field and highlight advances in robotics in areas such as medical assistance, prosthetics, robotic flexibility, joint motion, task performance, AI design, and home cleanliness.
Robots that can assist nurses
In the medical world, German researchers have developed a robotic system designed to help nurses alleviate the physical strain associated with treating patients. Nurses often face high physical demands when caring for bedridden patients, especially during tasks such as repositioning patients. Their work explores how robotic technology can support these tasks by remotely immobilizing patients in a lateral position. As a result, the system improved nurses' working posture by an average of 11.93% and was evaluated as user-friendly. This study highlights the potential for robotics to support caregivers in healthcare settings, improving both nurse working conditions and patient care.
Robots that enhance bionic hand control
Focusing on medical implications, researchers from numerous European institutions have recently achieved a breakthrough in robotic prosthetics technology by successfully implanting a neuromusculoskeletal prosthesis, a bionic hand directly connected to the user's nervous and skeletal system, into a person with the following conditions: – Elbow amputation. This accomplishment included surgical procedures to place titanium implants in the radius and ulna and transfer the severed nerves to free muscle grafts. These neural interfaces provide a direct connection between the prosthesis and the user's body, improving prosthetic function and improving quality of life. Their research demonstrates the potential of highly integrated prosthetic devices to improve the lives of amputees through reliable neural control and comfortable daily use.
Reinforcement learning in soft robotics
Focusing on soft robotics, researchers from the National Polytechnic Institut of Mexico and the Center for Advanced Studies at the Universidad Autónoma de Coahuila are working on reinforcement learning for motor control of pneumatically driven soft robots. proposed an approach using (RL). A continuum medium with various densities was modeled. The method involves a continuous-time Actor-Critic method designed to track the actions of 3D soft robots subjected to Lipschitz perturbations. Their study introduced a reward-based temporal difference mechanism and a discontinuous adaptation approach to the neural weights of the critical component of the system. The overall goal is to enable RL to control the complex, uncertain, and deformable properties of soft robots while ensuring the stability of real-time control, a critical requirement for physical systems. This research focuses on the application of RL to manage the unique challenges posed by soft robots.
A humanoid robot the size of a teenager.
Moving on to human-robot interaction, researchers at the University of Texas at Austin's Human-Centered Robotics Laboratory have launched a teenage-sized humanoid robot named DRACO 3, designed in collaboration with Apptronik. Tailored for practical use in the human environment, the robot has proximal actuation capabilities and uses a rolling contact mechanism in the lower extremity to enable a wide range of vertical postures. A Whole Body Controller (WBC) was developed to manage the DRACO 3's complex transmission. This study provides insight into the development and control of humanoids with rolling contact joints, with a focus on practicality and performance.
How Robots Affect Performance
Recently, researchers at the Technische Universität Berlin shifted their focus to psychology and investigated the phenomenon of social loafing in human-robot teams. Social loafing refers to reduced individual effort in a team environment compared to working alone. The study involved participants inspecting circuit boards for defects, with one group working alone and the other with a robotic partner. Despite the trustworthy robot marking defects on the board, participants working with a robot identified fewer defects compared to participants working alone, suggesting that social loafing is likely to occur in human-robot teams. This study highlights the challenges associated with human-robot collaboration and its impact on individual effort and performance.
Robot designed by AI
Northwestern University researchers have shifted their focus to robot design, developing an AI system that designs robots from scratch, allowing them to create walking robots in seconds, a task that took nature billions of years to evolve. These AI systems run on lightweight personal computers rather than relying on energy-hungry supercomputers or large data sets, offering the potential to rapidly design unique types of robots. The system works by iterating designs, assessing defects, and improving structures in seconds. This opens a new era of AI design tools that can act directly on the world for a variety of applications.
A customized robot for organizing your home
Finally, in the field of home robotics, researchers from Stanford, Princeton, Columbia University, and Google developed TidyBot, a one-armed robot designed to clean spaces based on personal preferences. TidyBot uses large-scale language models trained on Internet data to identify different objects and understand where to place them, making it highly customizable to suit different preferences. In real-world tests, the robot can correctly organize around 85% of items, significantly improving home organization. Although TidyBot still has room for improvement, researchers believe it holds great promise for making robots more versatile and useful in the home and other environments.
Ongoing developments in various fields highlight the flexibility and constantly evolving nature of robotics technology and open up new possibilities for integration into a wide range of industries. The gradual expansion of the field of robotics reflects a strong commitment and provides a glimpse into the potential consequences of these developments in the future.
source:
- Hinrichs, P., Seibert, K., Arizpe Gómez, P., Pfingsthorn, M., & Hein, A. (2023). A robotic system that immobilizes patients on their sides and reduces the physical burden on nurses. robotics, 12(5)
- Ortiz-Catalán, M., Zbinden, J., Millenaar, J., D'Accolti, D., Controzzi, M., Clemente, F., Cappello, L., Earley, E.J., Enzo Mastinu, Justyna Kolankowska, Munoz. -Novoa, M., Stewe Jönsson, Njel, C., Paolo Sassu, & Rickard Brånemark. (2023). A highly integrated bionic hand with neural control and feedback that can be used in everyday life. Scientific Robotics
- Pantoja-Garcia, L., Parra-Vega, V., Garcia-Rodriguez, R., & Vázquez-García, C.E. (2023). New actor-critical motor reinforcement learning for continuum soft robots. robotics, 12(5)
- Bang, S.H., Gonzalez, C., Ahn, J., Paine, N., & Sentis, L. (September 26, 2023). Control and evaluation of a humanoid robot with rolling contact joints in the lower body. Border.
- Cymek, D.H., Truckenbrodt, A., & Onnasch, L. (August 31, 2023). Lean back or recline? Exploring social loafing in human-robot teams.. Border.
- Instant evolution: AI designs new robots from scratch in seconds.. (n.d.). News.northwestern.edu.
- University, S. (October 3, 2023). The robot provides personalized room cleaning.. Stanford News.
Shaunak Kapur is a member of Robohub's volunteer team and a soon-to-be senior in high school (Texas). Shaun has been fascinated with robotics since he was young.
Shaunak Kapur is a member of Robohub's volunteer team and a soon-to-be senior in high school (Texas). Shaun has been fascinated with robotics since he was young.