Abstract

Autonomous micro aerial robots can operate in three-dimensional indoor and outdoor environments, and they have applications relevant to search and rescue operations, first response scenarios, and precision farming. I will provide an overview of our work and describe the challenges in developing small, agile robots. Specifically, I will discuss our recent work in the areas of control and planning, state estimation and mapping, and coordinating large teams of robots. 

Bio

Vijay Kumar is the UPS Foundation Professor at the University of Pennsylvania with appointments in the Departments of Mechanical Engineering and Applied Mechanics, Computer and Information Science, and Electrical and Systems Engineering.

Kumar is currently on sabbatical leave at the White House Office of Science and Technology Policy, where he serves as the assistant director for robotics and cyber-physical systems.

After receiving his Ph.D. from The Ohio State University in 1987, Kumar joined the faculty at the University of Pennsylvania, where he has held many leadership positions, including serving as the deputy dean for research in the School of Engineering and Applied Science from 2000 to 2004, and director of the GRASP Laboratory (a multidisciplinary robotics and perception laboratory) from 1998 to 2004. Kumar also served as chairman of the Department of Mechanical Engineering and Applied Mechanics from 2005 to 2008, followed by his tenure as deputy dean for education in the School of Engineering and Applied Science from 2008 to 2012.

Additionally, Kumar is a fellow of the American Society of Mechanical Engineers (2003), a fellow of the Institution of Electrical and Electronic Engineers (2005), and a member of the National Academy of Engineering (2013).

Kumar’s research interests are in robotics, specifically multi-robot systems and micro aerial vehicles. He has served on the editorial boards of the IEEE Transactions on Robotics and Automation, IEEE Transactions on Automation Science and Engineering, ASME Journal of Mechanical Design, ASME Journal of Mechanisms and Robotics and the Springer Tract in Advanced Robotics (STAR).

Among his numerous awards and honors, Kumar received the 1991 National Science Foundation Presidential Young Investigator award, the 1996 Lindback Award for Distinguished Teaching (University of Pennsylvania), the 1997 Freudenstein Award for significant accomplishments in mechanisms and robotics, the 2012 ASME Mechanisms and Robotics Award, the 2012 IEEE Robotics and Automation Society Distinguished Service Award, and a 2012 World Technology Network Award. Additionally, he has won best paper awards at DARS 2002, ICRA 2004, ICRA 2011, RSS 2011, and RSS 2013, and he has advised doctoral students who have won Best Student Paper Awards at ICRA 2008, RSS 2009, and DARS 2010.

Abstract

The DARPA Robotics Challenge (DRC) requires teams to integrate mobility, manipulation, and perception to accomplish several disaster-response tasks.

This talk describes the WPI-CMU DRC Team entry, the hardware choices, and software architecture that enable human-in-the-loop control of a 28 degree-of-freedom Atlas humanoid robot over a limited bandwidth link. We discuss our methods, results, and lessons learned from the DRC Trials tasks, focusing on driving. We were one of only seven teams to attempt the driving task, and the only team with an Atlas robot to successfully drive the course. The effectiveness of our system architecture was demonstrated as the WPI-CMU DRC Team scored 11 out of a possible 32 points, ranked 7th at the Trials, and was selected as a finalist for the DRC Finals.

Bio

Michael A. Gennert is the director of the Robotics Engineering Program at Worcester Polytechnic Institute, where he is a professor of both computer science and electrical and computer engineering. Previously, he has worked at the University of Massachusetts Medical Center, the University of California–Riverside, General Electric Ordnance Systems, and PAR Technology Corporation.

The author or co-author of more than 100 papers, Gennert’s research focuses on computer vision, image processing, scientific databases, and programming languages. He has ongoing projects in biomedical image processing, robotics, and stereo and motion vision. Gennert is a member of Sigma Xi, the NDIA Robotics Division, and the Massachusetts Technology Leadership Council Robotics Cluster. His is also a senior member of IEEE and ACM.

In 1980, Gennert received his S.B. in Computer Science and his S.B and S.M. in Electrical Engineering, after which he then received his Sc.D. in Electrical Engineering in 1987, all from the Massachusetts Institute of Technology.

Abstract

Visual search for objects, locations, or events of interest is a central capability for a robot with real-world utility. This capability cannot be limited to yes-no detection; it must include an ability to measure, describe, and compare within the context of a task. We have been investigating this problem since the late 1980s and regardless of the prevailing trends in machine vision, learning, or robotics, have not found reason to ignore the roles of attention, nor a deep understanding of the computational nature of the problem. This presentation will briefly trace our journey. Along the way, we emphasize a number of major points, including the roots of our approach in issues of tractability, the design and evaluation of our subsumptive search algorithm, the development of the AIM saliency model, the confounding nature of sensor bias, the integration of saliency within the object search algorithm, and the need for an overarching framework for attentive behavior, which we have named “Cognitive Programs.”

Bio

John K. Tsotsos is the Distinguished Research Professor of Vision Science at York University, where he also holds the NSERC Tier I Canada Research Chair in Computational Vision. Tsotsos also holds adjunct appointments in the departments of Computer Science and Ophthalmology and Vision Sciences at the University of Toronto and at the Toronto Rehabilitation Institute. He was director of the highly respected Centre for Vision Research at York University from 2000 to 2006. His research efforts span the areas of computer vision, computational neuroscience, human vision, artificial intelligence, and robotics.

Tsotsos received the Canadian Image Processing and Pattern Recognition Society Award for Research Excellence and Service in 2006, and the first President’s Research Excellence Award given by York University, in 2009. He was elected a fellow of the Royal Society of Canada, Academy of Sciences, Division of Mathematics and Physical Sciences in 2010.

Prior to joining York University in 2000, Tsotsos was a professor and associate chair of Computer Science at the University of Toronto, where he began his academic career in 1980. Also, while at the University of Toronto, he was appointed to the Division of Cardiology, Faculty of Medicine, and was a fellow of the Canadian Institute for Advanced Research from 1985-1995. He has published more than 300 papers, six of which have received distinctions. His most recent research monograph, “A Computational Perspective on Visual Attention,” was published by the MIT Press in 2011.

Abstract

Established more than half a century ago, the fields of control and robotics are continuously evolving by expanding their scale-independent toolboxes into new domains of science and engineering. In this talk, we use examples from our recent research to highlight surprising findings from applying control and robotics tools to micro world, at one end of the scale size, and to human-robot interaction, at the other end. At small scales, manufacturing and physics constraints are pushing robots toward a higher degree of autonomy. Examples of these include microfactories and mobile microrobotic swarms that do not require human intervention. At larger scales, robot companions require a higher degree of interactivity, usability, and personalization. Examples of these include physical human-robot interaction and advanced communication methods with the sole purpose to solidify the adaptive relationship between robots and humans.

Bio

Dan O. Popa is an associate professor in the Electrical Engineering Department at The University of Texas at Arlington and leads the Next Generation Systems (NGS) research group. He received his B.A. and M.S. degrees from Dartmouth College where he was a Montgomery Scholar from 1990 to 1994. Popa received a Ph.D. from Rensselaer Polytechnic Institute (RPI) in 1998, where he focused his doctoral research on control and motion planning for nonholonomic systems and robots.

After receiving his Ph.D., Popa joined the Center for Automation Technologies at RPI and worked there as a research scientist until 2004. After moving to Texas in 2004, Popa has continued his research as an affiliated faculty member of UT–Arlington’s Research Institute (UTARI), formerly known as the Automation & Robotics Research Institute (ARRI).

Popa has a broad experience base, including research in modeling, simulation, and control of microsystems; design of multiscale robotic assembly systems; and control and adaptation aspects of human-robot interaction. He is the recipient of several prestigious awards, including the UT Regents Outstanding Teaching Award, and he is a member of IEEE, ASME, and the author of more than 100 refereed publications.

Popa also serves as associate editor for the IEEE journal Transaction on Automation Science and Engineering (T-ASE), Springer’s Journal of Micro-Bio Robotics, and he is an active member of the IEEE Robotics and Automation Society (RAS) Committee on Micro-Nano Robotics and the ASME Committee on Micro-Nano Systems (MNS).

Abstract

Surveillance video is practically never used because there are too many hours of video for people to watch. Most attempts to deal with the overflow of surveillance video involve the development of automatic video understanding, including object recognition and activity understanding. Video synopsis is complementary to video understanding. After objects are detected, video synopsis changes the time of display of each object so that more objects are “packed” into a shorter time. The resulting video is a shorter summary of the original, where the objects are shown more densely. While video synopsis can reduce, on average, an hour of video into a minute, the synopsis loses causality, resulting in the possibility of objects that appear together in the original video appearing at different times in the synopsis, and vice versa. Video synopsis is an excellent tool for browsing video, and when used in conjunction with the results of video, an excellent method for understanding tools.

Bio

Shmuel Peleg received his Ph.D. in computer science from the University of Maryland in 1979. In 1981, he joined the faculty at the Hebrew University of Jerusalem where he is a professor of computer science. Peleg served as the first chairman of the Institute of Computer Science at the Hebrew University from 1990 to 1993.

The author of more than 140 technical papers in computer vision and image processing, Peleg also holds 18 U.S. patents. His technologies have provided the technical foundations for several startup companies, including BriefCam Ltd., which creates short summaries of long surveillance video capable of summarizing many hours of surveillance video into minutes of footage. He has also served as an editor and committee member of numerous international journals and conferences, and he recently served as a co-general-chair of CVPR 2011 and a program co-chair of ICCP 2013.

Abstract
Recent advances in computation, sensing, and hardware enable robotics to perform an increasing percentage of traditionally manual tasks in manufacturing. Yet, often the assembly mechanic cannot be removed entirely from the process. This provides new economic motivation to explore opportunities where assembly mechanics and industrial robots may work in close physical collaboration. In this talk, I present adaptive work-sharing and scheduling algorithms to collaborate with industrial robots on two levels: one-to-one human robot teamwork, and factory-level sequencing and scheduling of human and robotic tasks. I discuss our recent work developing adaptive control methods that incorporate high-level, person-specific planning and execution mechanisms to promote predictable, convergent team behavior. We apply human factors modeling coupled with statistical methods for planning and control to derive quantitative methods for assessing the quality and convergence of learnt teaming models, and to perform risk-sensitive robot control on the production line. I also discuss computationally efficient methods for coordinating human and robotic sequencing and scheduling at the factory-level. Tight integration of human workers and robotic resources involves complex dependencies. Even relatively small increases in process time variability lead to schedule inefficiencies and performance degradation. Our methods allow fast, dynamic computation of robot tasking and scheduling to respond to people working and coordinating in shared physical space, and provide real-time guarantees that schedule deadlines and other operational constraints will be met.

Bio
Julie Shah is an assistant professor in the Department of Aeronautics and Astronautics and leads the Interactive Robotics Group of the Computer Science and Artificial Intelligence Laboratory. Shah received her SB (2004) and SM (2006) from the Department of Aeronautics and Astronautics at MIT, and her PhD (2010) in Autonomous Systems from MIT. Before joining the faculty, she worked at Boeing Research and Technology on robotics applications for aerospace manufacturing. She has developed innovative methods for enabling fluid human-robot teamwork in time-critical, safety-critical domains, ranging from manufacturing to surgery to space exploration. Her group draws on expertise in artificial intelligence, human factors, and systems engineering to develop interactive robots that emulate the qualities of effective human team members to improve the efficiency of human-robot teamwork. This work was recognized by the Technology Review as one of the 10 Breakthrough Technologies of 2013, and has received international recognition in the form of best paper awards and nominations from the International Conference on Automated Planning and Scheduling, the American Institute of Aeronautics and Astronautics, the IEEE/ACM International Conference on Human-Robot Interaction, and the International Symposium on Robotics.