CPS Events
On the Role of Touch for Robustness and Generalisability in Robotic Manipulation
Abstract
Learning contact-rich, robotic manipulation skills is a challenging problem due to the high-dimensionality of the state and action space as well as uncertainty from noisy sensors and inaccurate motor control. In our research, we explore what representations of raw perceptual data enable a robot to better learn and perform these skills. Specifically for manipulation robots, the sense of touch is essential yet it is non-trivial to manually design a robot controller that combines different sensing modalities that have very different characteristics. I will present our set of research works that explore the question of how to best fuse the information from vision and touch for contact-rich manipulation tasks. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to deploy on real robots due to sample complexity. We use self-supervision to learn a compact and multimodal representation of visual and haptic sensory inputs, which can then be used to improve the sample efficiency of policy learning. I present experiments on a peg insertion task where the learned policy generalises over different geometry, configurations, and clearances, while being robust to external perturbations. While this work has shown very promising results on fusing vision and touch into a learned latent representation, this representation is also not interpretable. In follow-up work, we present a multimodal fusion algorithm that exploits a differentiable filtering framework for tracking the state of manipulated objects and therefore facilitating longer horizon planning. We also propose a framework where a robot can exploit information from failed manipulation attempts to recover and re-try. And finally, we show how exploiting multiple modalities helps to compensate for corrupted sensory data in one of the modalities. I will conclude this talk with a discussion of appropriate representations for multimodal sensory data.
Bio
Jeannette Bohg is an Assistant Professor of Computer Science at Stanford University. She was a group leader at the Autonomous Motion Department (AMD) of the MPI for Intelligent Systems until September 2017. Before joining AMD in January 2012, Jeannette Bohg was a PhD student at the Division of Robotics, Perception and Learning (RPL) at KTH in Stockholm. In her thesis, she proposed novel methods towards multi-modal scene understanding for robotic grasping. She also studied at Chalmers in Gothenburg and at the Technical University in Dresden where she received her Master in Art and Technology and her Diploma in Computer Science, respectively. Her research focuses on perception and learning for autonomous robotic manipulation and grasping. She is specifically interested in developing methods that are goal-directed, real-time and multi-modal such that they can provide meaningful feedback for execution and learning. Jeannette Bohg has received several awards, most notably the 2019 IEEE International Conference on Robotics and Automation (ICRA) Best Paper Award, the 2019 IEEE Robotics and Automation Society Early Career Award and the 2017 IEEE Robotics and Automation Letters (RA-L) Best Paper Award.
Fundamental Physics of Moving Clock Time Synchronization in a Weak Gravitational Field
Abstract
This talk will present the fundamental physics of near earth dynamic clocks and time synchronization. We begin by establishing basic clock behavior and reviewing established synchronization approaches between two stationary clocks in separated ground based laboratories. A discussion of different clock technologies that are in the literature will include comparisons of short term and long term stability including a relationship between stability and volume. Once clocks start moving in a gravitational field we must use General Relativity to understand the behavior of time as compared to other clocks that are either stationary or moving. We start with a one spatial and one time dimension to show how motion causes clocks to run at different rates and synchronization asymmetries that must be corrected. We then discuss the transformation of proper time to coordinate time just as done in GPS clocks. Then we’ll conclude by investigating the fundamentals of 4-dimensional dynamic clock synchronization of coordinate time.
Bio
Dr. Steven R. Wilkinson is a Principal Engineering Fellow on the Senior Technical Staff in RIS Engineering. Over his 24-year career at the company, he has mainly worked on development programs that involved new mission systems solutions that covered microwave and RF systems, electro-optical systems and is the company expert in time & frequency metrology. He has applied this expertise to position navigation and timing (PNT), communications, radar, and EO/IR sensing and imaging. He is currently the Principal Investigator on an effort that supports the National Radio Astronomy Observatory (NRAO) in two areas. Steven is the RIS planetary radar development technical lead, and is involved with the NRAO’s Next Generation Very Large Array (ngVLA) time and frequency effort. ngVLA is the future radio astronomy observatory that will replace the Very Large Array and the Very Long Baseline Array. Planetary radar will be a new capability for the NRAO and it will compliment current systems (Goldstone) to enhance our global planetary defense mission and solar system research. He received his undergraduate degree in physics from UC Berkeley and a PhD from the University of New Mexico.
Modular Architectures for Autonomous Vehicles Guidance and Control
Abstract
Highly autonomous systems, such as autonomous vehicles are expected to exhibit complex behaviors in a changing and often unpredictable environment. As such they require an equally complex reasoning system to provide guidance and control (G&C). The overall decision problem involves continuous dynamics, related to the physical system, and discrete dynamics, related to rules such as traffic rules. Due to such a hybrid nature and to the different time scales involved, the overall problem is too computationally complex to be solved in real-time as a whole in production-grade embedded platforms. In this talk we describe modular architectures that decompose the G&C problem into tractable sequences of sub-problems, while retaining safety properties for the integrated control architecture. These result in G&C architectures for autonomous vehicles that are flexible, expandable, and provably safe and robust, and yet appropriate for the embedded platforms typical of automotive, aerospace, robotics. Several tests on a scaled testbench for autonomous driving system development will be presented to demonstrate the concept.
Bio
Stefano Di Cairano received the Master (Laurea), and the PhD in Information Engineering in ’04 and ’08, respectively, from the University of Siena, Italy. He has been visiting student at the Technical University of Denmark and at the California Institute of Technology. During 2008–2011, he was with Powertrain Control R&A, Ford Research and Adv. Engineering, Dearborn, MI. Since 2011, he is with Mitsubishi Electric Research Laboratories, Cambridge, MA, where he is now the Senior Team Leader of Control for Autonomy, and a Distinguished Researcher. His research is on optimization-based control strategies for complex mechatronic systems, in automotive, factory automation, transportation systems and aerospace. His research interests include model predictive control, constrained control, particle filtering, hybrid systems, optimization. Dr. Di Cairano is an author in more than 200 peer reviewed papers in journals and conference proceedings and an inventor in more than 50 patents. He was the Chair of the IEEE CSS Technical Committee on Automotive Controls, the Chair of IEEE CSS Standing Committee on Standards and an Associate Editor of the IEEE Transactions on Control Systems Technology. He is currently the Vice-Chair of the IFAC Technical Committee on Optimal Control, an Executive member of the IFAC Committee on Industry, and the Chair of the Technology Conferences Editorial Board.
Electrification of aircraft design
Abstract
Aircraft design is a discipline as well as a process that utilizes various aspects of science and technology in order to create flying machines. A good aircraft design will be a tradeoff between competing requirements, such as speed, range, and comfort, while satisfying a number of safety constraints.
In the past, aircraft design has taken leaps forward with introduction of technologies such as jet engines and composite materials. An electrification revolution is currently underway in aviation. This is primarily driven by the availability of high energy density batteries, and the change is not unlike the one in the automotive field. The larger coming leap, however, is the increasing automation of operation of air vehicles that will eventually lead to their full autonomy.
In this talk, I will give a brief overview of the evolution of technologies and considerations that have shaped aircraft design. Special consideration will be given to electric aircraft propulsion and the ways in which it has been utilized in some of the early electric aircraft. I will give a brief overview of the current Joby electric vertical take off and landing vehicle and the high level design considerations that affected its creation. I will then focus on how various interconnected electric and electronic systems are becoming a key consideration already in the early conceptual design of aircraft, taking on the same importance as the more traditional aerospace disciplines. I will explain how modeling and simulation can be leveraged in order to test and verify complex designs before any parts are built. I will make a case for how automated system control is central in order to meet the safety demands placed on future electric air vehicles.
Bio
Gregor Veble Mikić obtained his Ph.D. in physics from the University of Ljubljana, Slovenia, in 2001, in the field of quantum chaos. After a post-doctoral stint at the Universita degli Studi d`Insubria, Como, Italy, between 2001 and 2003, he became an assistant at the University of Ljubljana from 2003 to 2007. In 2007 he became assistant professor of physics at the University of Nova Gorica, Slovenia, later associate professor in 2013. In parallel, he took on the role of head of research at Pipistrel d.o.o. Ajdovscina, Slovenia from 2007 to 2015. During this period, he led the design of the Panthera general aviation aircraft, and was responsible for the aerodynamics and performance of the Taurus G4, the aircraft that won the NASA Green Flight Challenge sponsored by Google competition in 2011 as a first 4 seat fully electric aircraft. In 2015 he joined Joby Aviation as chief aerodynamicist and head of flight physics group, where amongst other things he was responsible for aerodynamic design of Joby's electric vertical take-off and landing aircraft. He received the AIAA 2016 Piper General Aviation Award, which is awarded for outstanding contributions leading to the advancement of general aviation.
Design and Analysis of AI-Based Cyber-Physical Systems using Formal Scenarios
