The state of the art in robotics - highlights from the ICRA 2015 conference
Published on Apr 23, 2015
The ICRA Conference is the largest robotics conference organized by the IEEE Robotics & Automation Society.
Organizer - IEEE Robotics and Automation Society
IEEE International Conference on Robotics and Automation, Theme: CONNECT+ building relationships and collaborations, May 13-17, 2024, Yokohama, Japan - 2024.ieee-icra.org
ICRA 2023, May 29 – June 2, 2023, London, United Kingdom
icra2023.org
International Conference on Robotics and Automation on Wikipedia
ICRA 2022, May 23-27, 2022, Philadelphia, Pennsylvania, USA
icra2022.org
facebook.com/IEEE.RAS.ICRA
twitter.com/ieee_ras_Icra
linkedin.com/company/ieee-ras-icra
ICRA 2021, May 30 – June 5, 2021, Xi’an International Convention and Exhibition Center, Xi’an, China and virtual
ICRA 2020, May 31 - August 31, 2020, online
icra2020.org
ICRA 2019, May 20 - 24, 2019, Montreal, Canada
icra2019.org
facebook.com/icra2019
twitter.com/icra2019
ICRA 2018, May 21 – 25, 2018, Brisbane, Australia
ICRA 2017, May 29 – June 3, 2017, Singapore
facebook.com/icra2017
twitter.com/ICRA2017
ICRA 2016, May 16 - 21, 2016, Stockholm, Sweden
ICRA 2015, May 26 - 30, 2015, Seattle, Washington, USA
ICRA 2014, May 31 - June 7, 2014, Hong Kong, China
icra2014.com
ICRA 2015 Wednesday Plenary: One Robot for Every Task - Daniela Rus, MIT
Published on May 27, 2015
One Robot for Every Task - Daniela Rus, MIT
Plenary - May 27th, 2015
Abstract: The digitization of practically everything coupled with advanced robotics promises a future with democratized use of machines and wide-spread customization. However, pervasive use of robots remains a hard problem. What are the gaps that can take us to a future where robots are common, they figure things out, they operate aware of each other, and they contribute to making the world a better place?
In this talk I will discuss challenges toward pervasive use of robots and recent developments in customizing robots. What if we could automatically design, fabricate, and program robots from an intuitive description of the task so that anyone could use a robot? What if robots could be better at figuring things out? What if robots could be more adept at interacting with each other and with people? I will describe recent results in automating and customizing the fabrication of robots and enhancing their reasoning and communication capabilities. By enabling on-demand creation of programmable robots, we can begin to imagine a world with one robot for every task.
Biography: Daniela Rus is the Andrew (1956) and Erna Viterbi Professor of Electrical Engineering and Computer Science and Director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT. Rus's research interests are in robotics, mobile computing, and big data. The key focus of her research is to develop the science of networked/distributed/collaborative robotics, by asking: how can many machines collaborate to achieve a common goal? Rus is a Class of 2002 MacArthur Fellow, a fellow of ACM, AAAI and IEEE, and a member of the NAE. She earned her PhD in Computer Science from Cornell University. Prior to joining MIT, Rus was a professor in the Computer Science Department at Dartmouth College.
Closing the Ring - Danny Halperin, Tel Aviv University
Published on May 27, 2015
Hard versus Easy in Robot Motion Planning: Closing the Ring
Danny Halperin, Tel Aviv University
Wednesday, May 27
13:50-14:20
WSCC 6A
Abstract: Early results in robot motion planning had forecast a bleak future for the field by showing that problems with many degrees of freedom are intractable. Then came sampling-based planners that have been successfully, and often easily, solving a large variety of problems with many degrees of freedom.
We strive to formally determine what makes a motion-planning problem with many degrees of freedom easy or hard. I'll describe our quest to resolve this (still wide open) problem, and some progress we have made in the context of multi-robot motion planning.
Biography: Dan Halperin received his Ph.D. in Computer Science from Tel Aviv University. He then spent three years at the Computer Science Robotics Laboratory at Stanford University. In 1996 he joined the Department of Computer Science at Tel Aviv University, where he is currently a full professor and for two years was the department chair. Halperin's main field of research is Computational Geometry and its Applications. A major focus of his work has been in research and development of robust geometric software, principally as part of the CGAL project and library. The application areas he is currently interested in include robotics and automated manufacturing, algorithmic motion planning, and 3D printing.
Autonomous Continuum Manipulation - Jing Xiao, University of North Carolina
Published on May 27, 2015
Autonomous Continuum Manipulation
Jing Xiao, University of North Carolina
Wednesday, May 27
13:50-14:20
WSCC 6C
Abstract: Autonomous manipulation remains one of the most challenging tasks for robots, especially in cluttered environments with uncertainty. In this talk, I’ll introduce our related research work in autonomous manipulation using a continuum manipulator. Continuum manipulators are inspired by the invertebrate structures found in nature, such as an elephant trunk or octopus arm. As a continuum manipulator is deformable and passively compliant, it is more apt to work in a cluttered environment. My talk will be focused on autonomous grasping and inspection in real time in cluttered space, with extension to sensing-based autonomous manipulation in unknown environments.
Biography: Jing Xiao received her Ph.D. degree in Computer, Information, and Control Engineering from the University of Michigan, Ann Arbor, Michigan, USA. She is a Professor of Computer Science, College of Computing and Informatics (CCI), University of North Carolina at Charlotte, USA. She is also the Site Director of the U.S. National Science Foundation (NSF) Industry/University Cooperative Research Center (I/UCRC) on Robots and Sensors for the Human Well-being. She served as the Program Director of the Robotics and Human Augmentation Program at the NSF for two and half years (8/1998-12/2000). Jing Xiao’s research spans robotics, haptics, and intelligent systems. She has recently co-authored a monograph Haptic Rendering for Simulation of Fine Manipulation (Springer) and has over 130 publications in major robotics conferences, journals, and books and holds one patent. Jing Xiao is an IEEE Fellow. She has been elected twice as an AdCom Member of the IEEE Robotics and Automation Society (RAS) and currently serves as the Vice President for Member Activities of RAS.
Making Shakey - Peter Hart, SRI, retired
Published on May 27, 2015
Making Shakey
Peter Hart, SRI, retired
Wednesday, May 27
13:50-14:20
WSCC 6B
Abstract: Shakey, the world’s first mobile, intelligent robot, was developed at Stanford Research Institute (now SRI International) between 1966 and 1972. I worked on this project from the day it started until the day it ended (by which time I was the project leader). I’ll describe how the project got launched, how we approached this new world of robotics, what we actually did, and what the consequences have been for current technology and for modern life. Along the way, I’ll describe what the world was like back then, and how people reacted to the first real-world—i.e., non-fictional— robot.
Biography: Peter Hart has founded or led half a dozen companies and international research centers, and has invented or developed the theory of some of the most widely used procedures in modern computing. His technical writings have been cited over 74,000 times, which according to Google Scholar makes him the most- cited author in Robotics and the sixth most-cited author in Computer Science. He holds over 125 patents, and is a Fellow of the IEEE, the ACM, the AAAI, and the Rensselaer Alumni Association, and is a Member of the SRI Hall of Fame.
Technical Papers from AAAI 2015 and ICRA 2015
Published on May 27, 2015
Technical Papers from AAAI 2015 and ICRA 2015
In an attempt to bring the robotics and AI communities closer together again, the celebration will provide a forum for papers from the most recent robotics and AI flagship conferences. Eight papers from this ICRA 2015 have been selected to be presented alongside eight papers from AAAI 2015. These papers will be presented in the same way all papers at this conference are presented: including a brief oral presentation and an extensive interactive session.
Panel Discussion on the Relationship of AI & Robotics (Partial)
Published on May 27, 2015
Unfortunately there was a technical problem and the first part of the panel wasn't recorded. Our deep apologies!
Panel Discussion on the Relationship of AI & Robotics
The views of Peter Hart and James Kuffner will differ in many regards. These differences will serve as the starting point for a high-caliber panel discussion. In addition to the two keynote speakers, the panel includes the greats of robotics, vision, and AI:
Nils Nilsson, together with Peter Hart, was part of the Shakey project and has an early leader in AI; he continues to write monographs, including some of the earliest textbooks on AI.
Ruzena Bajcsy is one of the early visionaries at the intersection of robotics and vision, having pioneered the active vision paradigm, among many other things.
Rodney Brooks, the inventor of the subsumption architecture, has caused shifts of tectonic proportions in robotics, both in academia and in industry. He has greatly affected the development of robotics over the last thirty years.
Manuela Veloso and
Ben Kuipers both are current prolific and recognized leaders who successfully run research endeavors at the intersection of robotics and AI; they will be able to provide today's perspective on both fields.
The panel will be moderated by the IEEE RAS president, Raja Chatila.
The year 2015 marks the 50th anniversary of the Shakey project. Conducted at the Stanford Research Institute (now SRI), this project in many ways paved the way for today's research in robotics and AI. Many accomplishments of this project are still today considered seminal in our community.
Interestingly, in 1965 there was no significant distinction between research in AI, robotics, computer vision, and machine learning. Relevant activities were conducted within a single project, by researchers collaborating very closely. Over the past decades, there has been a trend in this area toward specialization, leading to a significant separation of the subfields: we now have separate conferences for AI, robotics, vision, and machine learning. Recently, many prominent researchers have voiced the belief that we need to reverse this separation to make progress towards artificial intelligent robotic systems.
We hope that the Celebration of the 50th Anniversary of Shakey will mark the beginning of a new era; an era in which robotics and AI continuously move closer together and mutually benefit from this development. We hope that you will come and participate and build relationships that lead to joint research efforts. We hope you will join us to learn about the past and to shape the future!
Overview
The afternoon will feature two keynotes connecting historical perspectives with visions about the future of robotics and AI in two keynote presentations and a panel discussion on the relationship between AI and robotics and how it should evolve to make progress towards the goals shared by these communities. In an attempt to bring the robotics and AI communities closer together, the celebration will include presentations of papers from ICRA 2015 and papers from AAAI 2015, the flagship AI conference.
Robotics in Education in Africa - Ayorkor Korsah, Ashesi University College
Published on May 27, 2015
Robotics in Education in Africa
Ayorkor Korsah, Ashesi University College
Wednesday, May 27
17:30-18:00
WSCC 6C
Abstract: In 2006, a collaboration between Ashesi University College in Ghana and Carnegie Mellon University in the U.S. resulted in the first university-level robotics course to be run in Ghana. At the time, only one high school robotics club in the country was known, and it was not clear how active the club was. Today, there are several educational robotics programs in Ghana, including one that has helped establish robotics clubs in numerous schools in all regions of the country. Gradually, robotics is coming into the consciousness and catching the imagination of the younger generation. This talk discusses the relevance, impact, and prospects of robotics in education in Africa, particularly in countries like Ghana with currently low levels of industrialisation.
Biography: G. Ayorkor Korsah is an Assistant Professor in the Computer Science Department at Ashesi University College, Ghana, where she teaches courses in programming, data structures and algorithms, and AI robotics. She holds Bachelors and Masters degrees in computers science and engineering from Dartmouth College, and a Ph.D. in Robotics from Carnegie Mellon University. Ayorkor's research and professional interests range from designing algorithms for robot path-planning and team coordination to exploring the role of technology in education in developing communities. In 2012, she co-founded, along with Ken Goldberg, the African Robotics Network (AFRON), aimed at promoting communication and collaborations to enhance robotics- related education, research, and industry on the continent. Along with a team of Ashesi University faculty and students, she also runs the annual Ashesi Innovation Experience (AIX), an enrichment program involving leadership training, design, entrepreneurship and robotics, for high school students.
Imagining a Cloud-enabled Shakey - James Kuffner, Google Research
Published on May 27, 2015
Imagining a Cloud-enabled Shakey
James Kuffner, Google Research
Wednesday, May 27
Abstract: High-performance cloud computing has dramatically transformed how individuals and businesses manage data. What if the Shakey project had been developed during the present era of the internet, cloud computing, and modern data centers? This talk explores the technology and legacy of Shakey within the context of Cloud Robotics, and examines the long-term prospects for the future development of robot intelligence based on search, distributed computing, and big data.
Biography: James Kuffner is an Engineering Director at Google and an Adjunct Associate Professor at the Robotics Institute, Carnegie Mellon University. He received a Ph.D. from the Stanford University Dept. of Computer Science Robotics Laboratory in 1999. He was a Japan Society for the Promotion of Science (JSPS) Postdoctoral Research Fellow at the University of Tokyo working on software and planning algorithms for humanoid robots. He joined the faculty at Carnegie Mellon University's Robotics Institute in 2002. He has published over 100 technical papers and received the Okawa Foundation Award for Young Researchers in 2007.
Социальные закладки