WAFR 2022

Motion planning around obstacles with convex optimization

Russ Tedrake

Abstract: In this talk, I'll describe a new approach to planning that strongly leverages both continuous and discrete/combinatorial optimization. The framework is fairly general, but I will focus on a particular application of the framework to planning continuous curves around obstacles. Traditionally, these sort of motion planning problems have either been solved by trajectory optimization approaches, which suffer with local minima in the presence of obstacles, or by sampling-based motion planning algorithms, which can struggle with derivative constraints and in very high dimensions. In the proposed framework, called Graph of Convex Sets (GCS), we can recast the trajectory optimization problem over a parametric class of continuous curves into a problem combining convex optimization formulations for graph search and for motion planning. The result is a non-convex optimization problem whose convex relaxation is very tight — to the point that we can very often solve very complex motion planning problems to global optimality using the convex relaxation plus a cheap rounding strategy. I will describe numerical experiments of GCS applied to a quadrotor flying through buildings and robotic arms moving through confined spaces. On a seven-degree-of-freedom manipulator, GCS can outperform widely-used sampling-based planners by finding higher-quality trajectories in less time, and in 14 dimensions (or more) it can solve problems to global optimality which are hard to approach with sampling-based techniques.

Bio: Russ Tedrake is the Toyota Professor at the Massachusetts Institute of Technology (MIT) in the Department of Electrical Engineering and Computer Science, Mechanical Engineering, and Aero/Astro, and he is a member of MIT’s Computer Science and Artificial Intelligence Lab (CSAIL). He is also the Vice President of Robotics Research at Toyota Research Institute (TRI). He received a B.S.E. in Computer Engineering from the University of Michigan in 1999, and a Ph.D. in Electrical Engineering and Computer Science from MIT in 2004. Dr. Tedrake is the Director of the MIT CSAIL Center for Robotics and was the leader of MIT's entry in the DARPA Robotics Challenge. He is a recipient of the NSF CAREER Award, the MIT Jerome Saltzer Award for undergraduate teaching, the DARPA Young Faculty Award in Mathematics, the 2012 Ruth and Joel Spira Teaching Award, and was named a Microsoft Research New Faculty Fellow. His research has been recognized with numerous conference best paper awards, including ICRA, Robotics: Science and Systems, Humanoids, Hybrid Systems: Computation and Control, as well as the inaugural best paper award from the IEEE RAS Technical Committee on Whole-Body Control.

An important and longstanding component of the WAFR program is the open problem session, in which members of the WAFR community share open problems that they find impactful (important, interesting, useful, beautiful, etc.).

The WAFR 2022 organizing committee is soliciting open problem suggestions. We will pick three or four problems to become part of this year's open problem session.

If your open problem suggestion is selected for the session, then you will be expected to prepare a short three minute overview talk (chalk talk and/or presentation) motivating/describing the open problem. After your introduction WAFR participants will discuss the problem and its potential solutions.

Open problems discussed in years past have been solved by the community and papers describing the solution have even been submitted to (and presented at) subsequent WAFR conferences.

Please use this link to submit ideas for an open problem that you would like to discuss at WAFR!

The Missing Skill

Hadas Kress-Gazit

Abstract: To enable robots to perform complex tasks — interact with people, react to events, change their task — we must focus on specifications (what the robot should do), skills (what it can do), and composition (how the robot will do what it should do, given what it can do). There is extensive work on all three of these themes; in this talk I will focus on finding the “missing skill(s)” — given a task, if the robot’s set of skills is not enough to achieve it, how can we automatically identify and create additional skills that will enable the robot to achieve the task.

Bio: Hadas Kress-Gazit is the Geoffrey S.M. Hedrick Sr. Professor at the Sibley School of Mechanical and Aerospace Engineering at Cornell University. She received her Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania in 2008 and has been at Cornell since 2009. Her research focuses on formal methods for robotics and automation and more specifically on synthesis for robotics — automatically creating verifiable robot controllers for complex high-level tasks. Her group explores different types of robotic systems including modular robots, soft robots and swarms and synthesizes (pun intended) ideas from different communities such as robotics, formal methods, control, hybrid systems and computational linguistics. She is an IEEE Fellow and has received multiple awards for her research, teaching and advocacy for groups traditionally underrepresented in STEM. She lives in Ithaca with her partner and two kids.

Remembering Jean-Paul Laumond: Steve LaValle.

Water, Earth, Fire, and Air: What Basic Elements Form the Foundation of Robotics?

Oliver Brock

Abstract: What once was the foundation of physics, today seems quaint. Over the centuries, most scientific disciplines have experienced disruptive changes to their foundation. These changes are, in fact, a characteristic of mature scientific disciplines. Looking at robotics: What are the chances that what we consider the foundation today, will remain forever? If the history of science is an indication, the chances are close to zero. One might argue that the foundation of robotics is changing already through the advent of new methods and technologies, most recently, for example, through deep learning or depth cameras. But these methods and technologies are applied within a conceptualization of robotics that remains unchanged. One might also argue that robotics is not starting from scratch but is building on centuries of advances in other disciplines. But the foundations of these disciplines are tailored to the problems addressed in these disciplines. We have imported them and structured robotics accordingly. If robotics should evolve as a scientific discipline, it might be worth examining the implicit assumptions we have imported along with the foundations of other disciplines — and the resulting consequences. In this talk, I will attempt to evaluate the current foundation of robotics and speculate about possible changes and what future advances they might enable.

Bio: Oliver Brock is the Alexander-von-Humboldt Professor of Robotics in the School of Electrical Engineering and Computer Science at the Technische Universität Berlin, a German "University of Excellence". He received his Ph.D. from Stanford University in 2000 and held postdoctoral positions at Rice University and Stanford University. He was an Assistant and Associate Professor in the Department of Computer Science at the University of Massachusetts Amherst before moving back to Berlin in 2009. The research of Brock's lab, the Robotics and Biology Laboratory, focuses on robot intelligence, mobile manipulation, interactive perception, grasping, manipulation, soft material robotics, interactive machine learning, deep learning, motion generation, and the application of algorithms and concepts from robotics to computational problems in structural molecular biology. Oliver Brock directs the Research Center of Excellence "Science of Intelligence". He is an IEEE Fellow and was president of the Robotics: Science and Systems Foundation from 2012 until 2019.

This session will include presentations on NSF funding opportunities of interest to the robotics community. The cross-Directorate robotics core program Foundational Research in Robotics (FRR) was founded in 2020 to eliminate artificial distinctions between the engineering and computer science elements of robotics, and to support a broad base of community-driven innovation in robotics. NSF program officers will present the goals of the FRR program and provide an overview of other robotics-relevant NSF programs.

It was recently announced that the National Robotics Initiative (NRI) — which has been NSF's flagship robotics program for over a decade — will be sunset. NSF program officers will also discuss the implications of the NRI sunset on support for robotics at NSF and offer guidance for prospective researchers. NSF remains committed to supporting and growing a thriving robotics research community. The FRR program will now provide a single home for foundational research in robotics across NSF. FRR welcomes proposals on a broad spectrum of foundational research in robotics, including the topics of collaborative robotics and integration in robotics that were previously supported by NRI.

Following the presentations, NSF program officers will take questions from the audience. More information about the robotics programs at NSF can be found at the Robotics@NSF website.

Join in a tour of the Maryland Robotics Center labs including live demos of indoor and outdoor navigation with ground robots, legged robots, and aerial robots.

The lab tours will happen concurrently with the Q&A session with NSF program managers. Participants can choose to attend either of the sessions.