Mark Yim - US grants

The University of Pennsylvania plans to become the fourth research site of the existing Industry / University Cooperative Research Center (I/UCRC) for Safety, Security, and Rescue Research Center (SSR-RC), composed of the University of South Florida as the lead university with the University of Minnesota as a partner. The University of Pennsylvania will follow the same policies as the existing center.

The main goal of the center and the research site is to create the infrastructure to facilitate engaging academic and industrial expertise for the direct and immediate benefit of our society at times and in situations during which it is most vulnerable. A planning meeting has been scheduled to determine the organization and viability of forming a research site for the existing I/UCRC.

The workshops supported by NSF as part of the Robotics: Science and Systems conference will focus on human-oriented robotics including rehabilitation, exoskeleton and prosthetics, human-robot interaction, robots manipulating in human environments, and socially assistive robotics. The breadth of human-oriented robotics is large, and is becoming more important for the viable transfer of robot technology to real human applications as well as understanding the science of the interaction between the two. The workshops will bring together a large number of researchers in these related fields. The NSF support will enable students to attend these workshops, learning issues in these growing fields and training them to be researchers. Robotics: Science and Systems is a new conference that brings together researchers working on algorithmic or mathematical foundations of robotics, robotics applications, and analysis of robotic systems.

The University of Pennsylvania has joined the multi-university Industry/University Cooperative Research Center for Safety, Security and Rescue Research located at the University of South Florida and the University of Minnesota. The I/UCRC will bring together industry, academe, and public sector users together to provide integrative robotics and artificial intelligence solutions in robotics for activities conducted by the police, FBI, FEMA, firefighting, transportation safety, and emergency response to mass casualty-related activities.

The need for safety, security, and rescue technologies has accelerated in the aftermath of 9/11 and a new research community is forming, as witnessed by the first IEEE Workshop on Safety, Security and Rescue Robotics. The Center is built upon the knowledge and expertise of multi-disciplinary researchers in computer science, engineering, industrial organization, psychology, public health, and marine sciences at member institutions.

PI: Daniela Rus
Institution: Massachusetts Institute of Technology, University of Washington,
Cornell University, University of Pennsylvania
Proposal Number: 0735953

EFRI-ARESCI: Controlling the Autonomously Reconfiguring Factory

This project, with investigators from the Massachusetts Institute of Technology, Cornell University, the University of Pennsylvania, and the University of Washington, seeks to establish new fundamental theories for understanding autonomously reconfigurable systems under conditions of uncertainty. Natural systems possess the remarkable ability to create deterministic structures and processes out of a huge variety of raw materials. They have extreme robustness with respect to the source of raw materials and high adaptability with respect to their behaviors, due in part to their stochastic nature. These properties are also desirable for engineered systems such as automated factories, cooperative robotic systems, and networked computational systems. However, currently the design and assembly of these systems relies on deterministic processes and supply chains, which makes them fragile with respect to fluctuations in supply and limited in their ability for structural reconfiguration and functional adaptation. The goal of this project is to explore, and physically demonstrate, a novel paradigm for robust construction and adaptive reconfiguration of physical systems from elementary components, under uncertainty and variability of material resources. The investigators envision a manufacturing process where the source and target are defined indirectly, and the path between them is subject to stochastic fluctuations requiring strategic decisions. The project addresses (1) the theoretical foundations of reconfiguring systems by examining distributed algorithms, control theory, and statistical physics approaches to modeling system behavior; (2) methods for analysis and synthesis by analyzing the information flow in these systems and the development of a synthetic design methodology; and (3) experimental validation by using the investigator's existing and new platforms to demonstrate construction and swarming tasks.

The goal of the proposed system is to be built on-the-fly and instantiated at a disaster site to provide support by creating physical structures and facilitating information flow for first responders. The system can also be instantiated in the context of construction and fabrication, bringing manufacturing processes to new levels of customization and robustness and automation. This study can lead to a better understanding of biological systems, which are self-organizing at many different levels. Finally, the proposed approaches to engineering and analyzing stochastic adaptive reconfiguring machines may generate hypotheses for neuroscientists, psychologists and biologists regarding the organizational and algorithmic nature of adaptation and robustness in complex systems.

This SGER proposal concerns the accumulation and representation of skills and control knowledge by robots that interact with unstructured environments. There has been comparatively little work on representations that capture re-useable knowledge in robotics---an issue that lies at the heart of many future applications. Thus, this SGER represents a potentially transformative technology and addresses significant gaps in the state-of-the-art for which the payoff, despite the risk, is extremely high. We aim our 1 year study on learning techniques that accumulate knowledge related to grasping and manipulation. We shall extend pilot studies and build prototypes for self-motivated learning techniques and generative models for manipulation and multi-body contact relationships. The approach relies on learning to discover and exploit structure over the course of several staged learning episodes; from sensory and motor knowledge concerning the robot itself, to controllable relationships between the robot and external bodies, to multi-body contacts involved in tasks like stacking and insertion. The project has three principal technological goals: to advance the state-of-the-art of robotic manipulation and knowledge representation; to extend machine learning methods toward intrinsically motivated, cumulative, and hierarchical learning; and to advance computational accounts of the longitudinal processes of sensorimotor and cognitive development in humans and machines.

This Ethics Education in Science and Engineering project proposes to educate the next generation of product designers and product engineers on the ethical production of products. This proposal focuses on three particular aspects:
1) manufacturing life cycle issues (recycling, packaging, environmental impact) 2) impact on developing countries and emerging markets including humanitarian and environmental concerns 3) advancing technology in products such as privacy concerns or robots in the workplace. Students who have knowledge in all of these disciplines will be uniquely poised to understand the complex ethical issues for products that are often deeply coupled with business and engineering design concerns. This proposal will address this need by using a novel experiential learning approach to educate students in the three focus areas above. Students will experience developing products that impact life in developing countries and emerging market (Ghana, Bangladesh or South Africa) by going there and working with NGO?s and design firms. Students will experience both the creation side and the abuse side of advancing
technology. The impact of this program will extend beyond Penn?s graduate program in three ways. First, other universities have committed to follow successful practices as we discover them. Second, we have six committed local and international industry partners as well as another six NGO?s in process that will both supply context for our students as well as take the results of their work. Third, we will publish multimedia content of the projects and
coursework on the internet. As society begins to grapple with how to evaluate the impact of advancing technology in products and how to respond to them at the level of policy, we will need citizens who are expert in the engineering and well- versed in its ethical and social implications. The proposed program will establish a growing cohort of young product designers who will be familiar with the ethical frameworks and perspectives
that can be brought to bear on the analysis of problems, and be able to apply a methodology to solve problems. Broader impact. At the broadest level, the program will influence the development of manufacturing
techniques and ethics education, bringing awareness of the human impacts of existing manufacturing processes to the design table of the next generation of production processes. It will do so by seeding the next generation
of product designers with individuals who have thought deeply about the societal implications of their work and have learned the basics of ethical manufacturing and high technology product design in the increasingly
global context.

The goal of the project is the development of the theory, hardware and computational infrastructure that will enable automatically transforming user-defined, high-level tasks such as inspection of hazardous environments and object retrieval, into provably-correct control for modular robots. Modular robots are composed of simple individual modules; while a single module has limited capabilities, connecting multiple modules in different configurations allows the system to perform complex actions such as climbing, manipulating objects, traveling in unstructured environments and self-reconfiguring (breaking into multiple independent robots and reassembling into larger structures). The project includes (i) defining and populating a large library of perception and actuation building blocks both manually through educational activities and automatically through novel algorithms, (ii) creating automated tools to assign values to probabilistic metrics associated with the performance of library components, (iii) developing a grammar and automated tools for control synthesis that sequence different components of the library to accomplish higher level tasks, if possible, or provide feedback to the user if the task cannot be accomplished and (iv) designing and building a novel modular robot platform capable of rapid and robust self-reconfiguration.

This research will have several outcomes. First, it will lay the foundations for making modular robots easily controlled by anyone. This will enrich the robotic industry with new types of robots with unique capabilities. Second, the research will create novel algorithms that tightly combine perception, control and hardware capabilities. Finally, this project will create an open-source infrastructure that will allow the public to contribute basic controllers to the library thus promoting general research and social interest in robotics and engineering.

This Partnership For Innovation project develops and tests the use of service robots to monitor and improve health of the elderly. The growing elderly population coupled with low birth rates in the developed world is creating a crisis in healthcare. The number of senior citizens is outgrowing the number of working-age adults to care for them. In the U.S. alone, the number of seniors over age 65 is projected to double from year 2000 to 2030, reaching 71.5 million. With the scarcity of care options available, affordable robots are a welcome solution for assisting elders with small tasks that would normally be done by a caregiver. While helping elders with activities of daily living in an elder care facility, the system learns about them. It can then do things such as help ensure that they are eating or drinking healthily.

The project consists of two main parts: development of a low-cost mobile manipulator capable of a limited set of elder-relevant manipulation tasks (e.g., picking up dropped items or filling a water glass); and development of a data-driven service system that analyzes the use of the robot over time to monitor elder health via service requests and pro-actively offer assistance as needed. One key to making this system viable is maintaining effectiveness at low cost. This work builds on a commercial low-cost mobile robot platform being developed at Savioke and adds manipulation capabilities via a novel low-cost expanding prismatic joint arm under development at the University of Pennsylvania. This mobile manipulator robot will be used to perform service tasks, such as delivering water to elders. The data gathered by these robots and how elders use them in the field will provide information about how robots can help create a larger data-driven health monitoring system.

The partners at the inception of the project include University of Pennsylvania, both the School of Engineering and Applied Science as well as the School of Medicine (Philadelphia, PA) and Savioke (Sunnyvale, CA, a small business concern) along with broader context partner, "LIFE"--Living Independently For Elders (Philadelphia, PA, a non-profit organization).

This project is to design, develop, and freely distribute novel, affordable, modular hardware and accompanying software platforms for enabling non-contact human-robot interaction (HRI) research. Such research is a significant portion of HRI today, and encompasses a broad spectrum of computing challenges and compelling application domains, including education, training, rehabilitation, and health. The goal of this project is to significantly increase access to hardware to a large body of researchers, so that computing advances can be applied to physical systems and evaluated in real-world environments, in order to drive progress in the computing community.

Advances in sensor and communication technologies have facilitated progress in computing research on physical platforms. The field of human-robot interaction in particular has grown significantly and actively brings together an interdisciplinary community of researchers across computing, robotics, and social science. However, progress has been limited by the lack of affordable, general-purpose, modular hardware platforms with available low-level software that would enable large numbers of computing researchers to enter the field and develop and test algorithms, as well as conduct statistically significant user studies by deploying systems in the real world and collecting user data to inform further computational research in HRI.

The objective of this award is to organize the annual Principal Investigators (PI) meeting for the National Robotics Initiative (NRI), which was launched in 2011. The PI meeting brings together the community of researchers, companies, and program officers who are actively engaged in the NRI to provide cross-project coordination in terms of common intellectual challenges, methods for education and training, best practices in terms of transition of results, and a centralized and lasting repository illustrating the research ideas explored and milestones achieved by the NRI projects. The meeting will be two days during late fall 2016 in the vicinity of Washington DC. The format will include short presentations by all the attending PIs, a poster session, keynote speeches, and panel discussions. Invitations to the meeting will include all PIs with active NRI grants, program managers with robotics-related programs, and members of the press.

The broader impact/commercial potential of this PFI project addresses the healthcare crisis of the growing elderly population coupled with low birth rates where the number of older adults is outgrowing the number of working-age adults to care for them. With the scarcity of care options available, robots are a welcome solution for assisting elders with small tasks that would normally be done by a caregiver. These robots would serve in an estimated 17,000 elder care facilities nationwide. Robots will be able to identify elders and personalize their assistance while monitoring health parameters. Critically, this work will aim to understand how a robot capable of assistance in simple activities of daily living should behave to aid elders in a community long term care setting including the acceptance and willingness to receive assistance from the robot.

The proposed project addresses three research areas: 1) Robot Design for Elderly: How can we develop a useful affordable robot system for the elder-care community? What is the elder-care community preference for humanoid robot forms over non-humanoid in a robot that provides assistance? 2) Robot Behavior for Elderly: How will the elderly react to an autonomous robot that can recognize individuals, call them by name and provide services? What effects will different designs have on the interaction such as form-factor, motions, expressiveness and modalities of interaction? 3) Robotic Health Tracking of Elderly: As interactions with the robot occur in social settings, the robot can log data such as requests for water delivery from the robot, distance walked by the elders etc. What factors affect the quality of data can be obtained and how useful will this data be to clinicians? These questions will be answered by building a low cost robot using a variety of technologies developed from NSF-funded programs, then validating the performance with tests in an elder-care facility.

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.

While flying robots are becoming commonplace, swarms of them have the potential to be useful in a wide variety of cases such as surveillance and informational displays. Currently, flying swarms of robots have difficulty interacting with humans due to two factors: their almost ubiquitous reliance on external sensing, such as GPS or motion-capture systems, and their inherent danger to humans due to their use of hazardous high-speed propellers. The project will address these two factors by designing and creating a novel swarm of over 200 flying robots that are safe to operate around people. They will use only on-board sensing to interact with each other and humans and can operate in a wide range of unstructured environments. The swarm capabilities will be demonstrated in two scenarios: autonomous 3D shape formation, where the swarm self-assembles a user-specified shape, and a second scenario where a human uses their hands to move the swarm into a desired shape.

This project investigates aspects of flying UAVs and their control to allow the creation of large flying swarms that are not reliant on external positioning, can safely interact with humans, and where the swarm has infinite endurance. The UAV uses a novel single actuator design to enable the low-cost creation of the swarm, as well as facilitate lightweight UAVs for human safety. The UAVs employ an infrared transceiver on a rapidly spinning chassis to sense bearing, elevation, and distance to neighboring UAVs, as well as transmit data to them. They also have a time-of-flight range finder to sense passive objects nearby. This sensing will be used to control the position of the individuals with respect to their neighbors and to enable swarm behaviors controlled through natural human interaction. The endurance of the swarm is extended by having UAVs take turns participating in the swarm shape, and then fly back to the base station to recharge. This cycle of swarming and then charging is repeated and staggered amongst the swarm so there are always UAVs participating in the swarm behavior.

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 project will create knowledge to realize a new class of active soft robots that can dynamically evolve three-dimensional soft protuberances from a nominally planar surface. These moving shapes will be capable of gently and safely positioning and manipulating heavy but delicate objects that are resting on the surface. Soft robots are ideal for interactions with humans because they safely deform upon contact, much as biological soft tissue does. This project will enable active soft robotic surfaces able to track and manipulate human-sized objects in three-dimensional space without high contact forces. In 2018 patient handling injuries accounted for 25% of healthcare-related worker's comp claims and back injuries to workers cost the US healthcare industry $8.6 billion. The results of this project will advance the goal of assisting the safe and comfortable handling of patients, to enhance the quality of healthcare and reduce injuries in the nursing workforce. By preventing injury and reducing nurses' work load this project will address the grand challenge of providing care to our aging population. The project will promote an educational program to build the cross-disciplinary literacy of engineering and nursing students, by giving each experience in the other?s work domain and deepening their understanding of current healthcare capabilities and challenges.

This research project will make fundamental advances to soft robotic capabilities through three innovations: 1. electrically addressable polymers that modulate the stiffness of inflated elastomers, 2. real-time shape sensing, contact detection, and shape prediction using Gaussian curvature, and 3. a hierarchical control policy that, rather than attempting precise control of the deformable robot, achieves desired motion of the manipulated object through contact points. This project builds from strengths of the assembled team to overcome fundamental challenges in soft robotics research, including shape-controlled actuation with high strain and large forces, soft robotic sensing and proprioception, modeling and estimating the infinite dimensional state of stretchable materials while interacting with external objects, and control strategies to manipulate external objects with continuous, compliant, and re-configurable elastomeric surfaces.

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.

Production of complex structures via a swarm of simple, distributed agents is ubiquitous in biology (e.g., ant colonies, cellular formation of tissues), yet technological limitations have traditionally prevented this approach in manufacturing. In contrast, traditional manufacturing, from machining and casting to modern approaches such as roll-to-roll or additive manufacturing, require a deterministic plan which is executed in a series of precise, sequential steps. With miniaturization of robotics and novel inverse design tools, it is now feasible that the distributed, swarm approach used in nature could become an essential future manufacturing platform. The advantages of this approach include (1) the ability to produce complex multimaterial, multiscale structures without predetermined steps and (2) extreme robustness to manufacturing errors. This Future Manufacturing Seed Grant (FMSG) will establish the theoretical foundation and the practical tools necessary to pave the way for this nascent area of research and to understand its feasibility. In addition to the technical aspects of this work, this research could lead to a new area of manufacturing with beneficial economic and workforce implications. In conjunction with mid-sized and large manufacturing firms the researchers will therefore seek insight about how this new manufacturing paradigm would require changes to manufacturing curricula for the training and retraining of future manufacturing workers. This project will lead to the training of diverse graduate and undergraduate students and to outreach to K-12 students and the general public.

The objective of this seed grant is to provide the framework and foundation for a new paradigm for future manufacturing in which multiple simple agents operate based on local information (e.g., temperature, light, pre-existing structure) to modify or manufacture complex structures based on simple local design rules. The feasibility of this new approach will be examined, and suitable vocabulary, processing formalization, design rules, etc., will be developed to establish this paradigm as a new, transformational area of research. The work will address the following key questions: How do local design rules map to different structural features, and ultimately to global mechanical properties (e.g., stiffness, strength, mass, Poisson's ratio) and combinations of properties (e.g., maximal specific toughness for a structure of minimal mass)? How do different design rules affect the rate of convergence toward optimal properties? The answers to these questions will also be incorporated in an inverse design framework, allowing local rules to be generated based on the desired properties. This grant is co-funded by the division of Civil, Mechanical and Manufacturing Innovation (CMMI) and the division of Industrial Innovation and Partnerships (IIP).

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.