Invited Talk 1: Geometric Theory of Slender Soft Robots
By: Professor Federico Renda
Abstract: Many modern robotic systems feature continuous deformable elements whose dynamics cannot be neglected. Those include robots with highly deformable links, continuum and soft robots for medical applications and industrial inspection, rigid robots manipulating linear deformable objects such as strings and cables, and many more. A solid theoretical understanding of the mechanics and dynamics of this class of robots is essential to execute advanced optimization, control, and learning algorithms that can ultimately unlock their full potential. In this talk, I will present a unified geometric theory of hybrid soft-rigid robots that can be seen as the direct extension of the geometric theory of rigid robots to this new class of systems. I will discuss various strategies to reduce the order of the resulting dynamic model, exploring the implications of different strain discretizations and the benefits of an optimal linear parametrization based on data. To validate the theory, I will showcase several experimental and simulation results underpinned by the fast MATLAB toolbox SoRoSim that we developed for this purpose.
Bio: Dr. Federico Renda is an Associate Professor in the Department of Mechanical and Nuclear Engineering at Khalifa University in Abu Dhabi, UAE. Before joining Khalifa University, he was a Post-Doctoral Fellow at the BioRobotics Institute of Scuola Superiore Sant’Anna, where he received his Ph.D. degree in 2014. He obtained his B.Sc. and M.Sc. degrees in Biomedical Engineering from the University of Pisa, Italy, in 2007 and 2009, respectively. Dr. Renda has been a visiting professor at the National University of Singapore (NUS), the National Institute for Research in Digital Science and Technology (INRIA, Lille), and others. He has been appointed as Associate Editor and Program Committee Member of important robotics journals and conferences, such as the International Journal of Robotics Research (IJRR) and the International Conference on Robotics and Automation (ICRA), to name a few. Dr. Renda’s research interests encompass the study of multibody dynamical systems, including modeling and control of complex soft and underwater robots. His research is applied to the agile motion of highly deformable manipulators as well as underwater swarm robotics for persistent surveillance of large submerged structures.
Invited Talk 2: Geometric Locomotion
By: Professor Ross Hatton
Abstract: Differential geometry and Lie group theory provide insight into the locomotion of undulating systems through a vocabulary of lengths, areas, and curvatures. In particular, curvature forms and Lie brackets of the system’s constraint distribution combine these geometric concepts to describe the effects of cyclic changes in the locomotor's shape, such as the gaits used by swimming or crawling systems. Surprisingly, effective application of these geometric tools depends on the coordinate representation in which they are expressed. This dependence can be traced to a truncation of the Baker-Campbell-Hausdorff series, and can be managed by transforming the system coordinates into a "generalized Coulomb gauge” on the special Euclidean group. Using the coordinate-optimized system representation allows for intuitive geometric understanding of optimal gait geometry and efficient gradient optimization calculations for large-amplitude system motions. Additionally, it makes geometric techniques useful beyond the "clean" ideal systems on which they have traditionally been developed, and can provide insight into the motion of systems with considerably more complex dynamics, such as locomotors in granular media.
Bio: Ross L. Hatton is an Associate Professor of Robotics, Mechanical Engineering, and Mathematics at Oregon State University, where he directs the Laboratory for Robotics and Applied Mechanics. He received PhD and MS degrees in Mechanical Engineering from Carnegie Mellon University, following an SB in the same from Massachusetts Institute of Technology. His research focuses on understanding the fundamental mechanics of locomotion and sensory perception, making advances in mathematical theory accessible to an engineering audience, and on finding abstractions that facilitate human control of unconventional locomotors.
Invited Talk 3: Completeness of Metrics, Stabilization and Control
By: Professor Anthony Bloch
Abstract: In this talk, I will discuss a mathematical technique based on modifying the underlying Riemannian metric of a mechanical system that can be useful for controlling and stabilizing such systems. In particular, this technique can be applied to the problem of obstacle avoidance for a robotic system. The theory is based on some mathematical results on the completeness of Riemannian geodesics used so as to modify the evolution near a boundary. This work is joint with Jose Acosta and David Martin and builds on earlier work on controlled Lagrangians by Bloch, Leonard, and Marsden.
Bio: Anthony M. Bloch is the Alexander Ziwet Collegiate Professor of Mathematics at the University of Michigan where he has served as graduate and department chair. He received a B.Sc. (Hons) in Applied Mathematics and Physics from the University of the Witwatersrand, Johannesburg, in 1978, an M. S. in Physics from the California Institute of Technology in 1979, an M. Phil in Control Theory and Operations Research from Cambridge University in 1981 and a Ph.D. in Applied Mathematics from Harvard University in 1985. His main research interests are in dynamics, differential equations, and control. He has received various awards including a Presidential Young Investigator Award, a Guggenheim Fellowship and a Simons Fellowship, and is a Fellow of the American Mathematical Society, the Institute of Electrical and Electronics Engineers, and the Society for Industrial and Applied Mathematics. He was a Senior Fellow of the Michigan Society of Fellows and a member of the Institute for Advanced Study. He was Editor-in-Chief of the SIAM Journal of Control and Optimization and is currently Editor-in-Chief of the Journal of Nonlinear Science as well as Series Editor for Springer Publishing.
Invited Talk 4: Coupled Lie-Poisson Neural Networks (CLPNets): Data-Based Computing of Coupled Hamiltonian Systems
By: Professor Vakhtang Putkaradze
Abstract: Physics-Informed Neural Networks (PINNs) have received much attention recently due to their potential for high-performance computations for complex physical systems. The idea of PINNs is to approximate the equations and boundary and initial conditions through a loss function for a neural network. PINNs combine the efficiency of data-based prediction with the accuracy and insights provided by the physical models. However, applications of these methods to predict the long-term evolution of systems with little friction, such as many systems encountered in space exploration, oceanography/climate, and many other fields, need extra care as the errors tend to accumulate, and the results may quickly become unreliable. We provide a solution to the problem of data-based computation of Hamiltonian systems utilizing symmetry methods, paying special attention to systems that come from the discretization of continuum mechanics systems. For example, for simulations, a continuum elastic rod can be discretized into coupled elements with dynamics depending on the relative position and orientation of neighboring elements. For data-based computing of such systems, we design the Coupled Lie-Poisson neural networks (CLPNets). We consider the Poisson bracket structure primary and require it to be satisfied exactly, whereas the Hamiltonian, only known from physics, can be satisfied approximately. By design, the method preserves all special integrals of the bracket (Casimirs) to machine precision. We present applications of CLPNets applications for several particular cases, such as coupled rigid bodies or elastically connected elements. CLPNets yield surprising robustness for increasing the dimensionality of the system, enabling the computing of dynamics for a high number of dimensions (up to 18) using networks with a small number of parameters (one to two hundred) and only one to two thousand data points used for learning.
Bio: Prof Vakhtang Putkaradze received his PhD from the University of Copenhagen, Denmark, and held faculty positions in New Mexico, Colorado State University, and, most recently, at the University of Alberta, where he was a Centennial Professor between 2012-2019. From 2019 to 2022, he led the science and tech part of the Transformation Team at ATCO Ltd, first as a Senior Director and then Vice-President. He is now back at the University of Alberta, where he is currently studying applications of geometric mechanics to neural networks, in particular, efficient computations of Hamiltonian systems using data-based techniques. His main topic of interest is using geometric methods in mechanics and various applications. He has received numerous prizes and awards for research and teaching, including Humboldt Fellowship, Senior JSPS fellowship, CAIMS-Fields industrial math prize and G. I. Zaslavsky prize.
Invited Talk 5: From State Estimation on Lie Groups to Affordance Learning and Robot Imagination
By: Professor Gregory S. Chirikjian
Abstract: Today’s robots are very brittle in their intelligence. This follows from a legacy of industrial robotics where robots pick and place known parts repetitively. For humanoid robots to function as servants in the home and in hospitals they will need to demonstrate higher intelligence and must be able to function in ways that go beyond the stiff prescribed programming of their industrial counterparts. A new approach to service robotics is discussed here. The affordances of broad classes of common objects such as chairs, cups, etc., are defined. When a new object is encountered, it is scanned and a virtual version is put into a simulation wherein the robot ``imagines’’ how the object can be used. In this way, robots can reason about objects that they have not encountered before. After affordances are assessed, the robot then takes action in the real world, resulting in real2sim2real transfer. As part of this broad framework, probabilistic methods on Lie groups are used. These mathematical methods were developed originally by the presenter for mobile robot state estimation, and have been adapted recently to one-shot learning of affordances from demonstration. Videos of physical demonstrations will illustrate the effectiveness of this paradigm. Future plans will be discussed, including the integration of large language models.
Bio: A native of Maryland, Gregory S. Chirikjian received undergraduate degrees from Johns Hopkins University in 1988, and a Ph.D. degree from the California Institute of Technology, Pasadena, in 1992. From 1992 until 2021, he served on the faculty of the Department of Mechanical Engineering at Johns Hopkins University, attaining the rank of full professor in 2001. Additionally, from 2004-2007, he served as department chair. Starting in January 2019, he moved the National University of Singapore, where he served as Head of the Mechanical Engineering Department, where he hired 14 new professors. Since January 2024 he has served as the ME chair at the University of Delaware, where he has hired 2 new professors so far. Chirikjian’s research interests include robotics, applications of group theory in state estimation, information-theoretic inequalities, and applied mathematics more broadly. He is a 1993 National Science Foundation Young Investigator and a 1994 Presidential Faculty Fellow. In 2010 he became a fellow of the IEEE. From 2014-15, he served as a program director for the US National Robotics Initiative, which included responsibilities in the Robust Intelligence cluster in the Information and Intelligent Systems Division of CISE at NSF. Chirikjian is the author of more than 250 journal and conference papers and the primary author of three books, including Engineering Applications of Noncommutative Harmonic Analysis (2001) and Stochastic Models, Information Theory, and Lie Groups, Vols. 1+2. (2009, 2011). In 2016, an expanded edition of his 2001 book was published as a Dover book under a new title, Harmonic Analysis for Engineers and Applied Scientists.
Invited Talk 6: The use of Differential Geometry and Topology in Natural Dynamic Analysis and High Performance Control
By: Professor Alin Albu-Schäffer
Abstract:
Bio: Alin Albu-Schäffer received his M.S. in electrical engineering from the Technical University of Timisoara, Romania in 1993 and his Ph.D. in automatic control from the Technical University of Munich in 2002. Since 2012 he is the head of the Institute of Robotics and Mechatronics at the German Aerospace Center (DLR). Moreover, he is a professor at the Technical University of Munich, holding the Chair for "Sensor Based Robotic Systems and Intelligent Assistance Systems" at the School of Computation, Information and Technology. His personal research interests include robot design, modeling and control, nonlinear control, flexible joint and variable compliance robots, impedance and force control, physical human-robot interaction, bio-inspired robot design and control. He received several awards, including the IEEE King-Sun Fu Best Paper Award of the Transactions on Robotics in 2012 and 2014; several ICRA and IROS Best Paper Awards as well as the DLR Science Award. He was strongly involved in the development of the DLR light-weight robot and its commercialization through technology transfer to KUKA. He is the coordinator of euROBIN, the European network of excellence on intelligent robotics, IEEE Fellow and RAS-AdCom member.