Projects

An important problem in human-robot interaction with multiple robots is the ability to cooperatively manipulate objects while navigating complex environments. This scenario involves a collaboration between a human leader and a group of teleoperated and semi-autonomous agile-legged robots (i.e., synthetic actors) working together to manipulate and transport complex objects. This research project aims to enable these human-robot teams to achieve intelligent and robust cooperative manipulation and transportation in challenging settings like factories, homes, and offices. The project fosters a bidirectional sensorimotor interaction in which haptic gloves convey force feedback experienced by the robotic agents to the human, while electroencephalogram (EEG), electromyography (EMG), and hand position signals from the human are transferred to the robots' control algorithms for embodied reasoning. The project's overarching research goal is to establish a formal foundation to deploy a distributed planning and control approach for co-learning and co-adaptation of human-robot interaction with multiple robot agents in cooperative loco-manipulation. This work will have important societal impacts by deploying semi-autonomous legged robots that can effectively work together with humans to accomplish labor-intensive tasks, such as assembly and manufacturing. The developed co-learning and co-adaptation algorithms will allow teams of humans and synthetic actors to manipulate and transport heavy objects in challenging environments. Moreover, incorporating EEG and EMG into the researched data-driven models could lay the groundwork for developing multi-agent legged assistive devices to allow paralyzed individuals to perform daily activities. The integrated educational plan will have a profound impact by 1) creating hands-on educational activities on robot locomotion and programming for K-12 students and underrepresented minorities and 2) sponsoring senior design projects for undergraduate teams to be involved in research and experiments.

The research project will advance knowledge in the largely unexplored field of formation control and embodied reasoning (planning and control) of complex models of loco-manipulation in multi-agent human-robot interaction systems through four objectives: 1) Creation of data-driven dynamic prediction models for human intention based on deep learning techniques; 2) Creation of data-driven dynamical models for the complex network of multi-agent legged robots and the human operator (Co-learning); 3) Creation of human dynamics-aware and distributed data-driven predictive control algorithms for optimal control of the network of synthetic actors with the human in the loop for loco-manipulation (Co-adaptation); and 4) Experimental validation on a team of advanced quadrupedal robots for cooperative loco-manipulation and transportation tasks in the Principal Investigator's laboratory. This award has been co-funded by the Mind, Machine and Motor Nexus program and the Dynamics, Controls and System Diagnostics programs.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

Millions of people around the world suffer from pathological tremors, which significantly reduce the quality of their lives. To date, there is no permanent cure to pathological tremors. Existing treatments such as surgery and medications can be expensive. They can also be invasive and come with side effects. The aim of this project is to develop and implement a cost-effective and ergonomic wearable exoskeleton to mitigate tremors and provide movement assistance to tremor patients. The broader impacts of the project include improvement in the quality of life of patients suffering from pathological tremors, the inclusion of students from underrepresented groups, mentoring and training of undergraduate and graduate students, and integration of the research findings into classroom materials.

The development of the proposed technology will focus on novel neuromusculoskeletal analyses, wearable exoskeletons, and human-robot cooperative control theories, as well as their integration into rehabilitation exoskeletons for tremor alleviation. The primary objective is to gain a fundamental understanding of the interplay between tremor-related physical movements, cortical signals, and neuromuscular signals. The secondary objective is to develop a compact rehabilitation device embedded with a robust adaptive controller to suppress tremors and assist movement in daily life. To pursue these objectives, the research team will conduct a combination of theoretical, computational, and experimental analyses to investigate the dynamics of tremor. A model-based optimal control framework will be developed for tremor alleviation and movement assistance, and a wearable exoskeleton will be designed and manufactured for conducting experiments on tremor patients. The anticipated impacts of this project include a fundamental understanding of pathological tremor dynamics that furthers the development of better exoskeletons empowered by novel real-time tremor modeling and cooperative control algorithms. The proposed framework will suit exoskeletons designed not only for tremor alleviation, but also for other rehabilitation goals. The generic methods proposed for tremor modeling and cooperative control will also provide solutions applicable to other fields of robotics.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

This convergent research employs the joint perspectives of construction engineering, human factors psychology, and robot control and autonomy to advance the fundamental understanding of future construction progress monitoring work. Nearly $1.3 trillion worth of structures are constructed each year in the U.S., while more than 53% of typical construction projects are behind schedule, and more than 66% suffer from cost overruns. Construction progress monitoring incorporates a set of regular inspections of construction work to prevent schedule delays and unpredicted costs or rework. But currently, construction progress monitoring is a manual process with repetitive in-person visual inspections of construction work that has resulted in inconsistent, time-consuming, labor-intensive, and error-prone inspection. The main goal of this research is to provide a deeper basic understanding of the human-technology partnership in future progress monitoring work by enabling human inspectors to use their assistant legged robots with high mobility and agility capabilities to help them with performing progress monitoring tasks in dynamically changing job sites. This project will create new knowledge of future work with human-robot inspector teams that can also be applied to future inspection in other domains. Findings from this research can transform future construction by creating new career opportunities that will be inclusive of individuals with disabilities. The project will also provide opportunities for education and outreach plans for middle-school and high school students. Partnerships with industry stakeholders will specifically guide discovering potential social and economic consequences of the human-robot inspector teams in future construction work.

This research aims to (i) develop autonomous and resilient quadrupedal robots that can traverse dynamically changing and unstructured construction environments for monitoring construction progress in human-robot inspector team performance, (ii) develop a conceptual framework for human-in-the-loop and human-robot teaming in future construction progress monitoring leveraging aspects of psychology, human-centered design, and usability engineering, and (iii) rethink the future of construction progress monitoring work within a socio-technical evolution through fostering engagement with industry stakeholders. This research creates new knowledge in (a) designing intelligent control and motion planning algorithms that enable safe and agile cooperative tasks of quadrupedal robots and human inspectors in unstructured environments of construction sites, (b) identifying human-centered design strategies in construction progress monitoring utilizing methodologies of human factors psychology for effective human-robot inspector teaming, and (c) understanding the fundamental transformation that the future of construction progress monitoring will encounter in transitioning from manual processes to human-robot inspector teaming.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.