Enabling Bipedal Locomotion with Robotic Assistive Devices through Learning and Control

October 29, 2021 11:00am-12:30pm

Location: Pettit Microelectronics Building, 102A&B Conference Room

Abstract

Lower-body exoskeletons and prostheses have the potential of restoring autonomy to millions of individuals with ambulatory disabilities, and thereby improving quality of life. However, achieving locomotive stability is challenging enough from a robotics and control perspective, let alone addressing the added complexity of satisfying subjective gait preferences of a human user. Thus, the goal of this talk is to discuss how theoretic approaches to bipedal locomotion, based upon nonlinear controllers with formal guarantees of stability, can be coupled with learning to achieve user-preferred stable locomotion.

In my talk, I will first discuss the theoretical underpinnings of achieving provably stable locomotion via nonlinear control theory, and apply this methodology to various dynamic robotic platforms experimentally. Then, I explore the unification of preference-based learning with this formal approach to locomotion to explicitly optimize user preference and comfort. Finally, I experimentally demonstrate the combined framework on a full lower-body exoskeleton, with both non-disabled subjects and subjects with complete motor paraplegia. This work, therefore, demonstrates the utility of coupling preference-based learning with control theory in a structured fashion with a view towards practical application. Ultimately, this result provides a formal approach for achieving locomotive autonomy with robotic assistive devices that has the potential to accelerate clinical implementation and enable the use of these devices in everyday life.

Biography

Maegan Tucker is currently a PhD Candidate in the Mechanical and Civil Engineering Department at the California Institute of Technology (Caltech). She received her Bachelor of Science in Mechanical Engineering from Georgia Tech in 2017. Her research is centered around developing systematic methods of achieving stable, robust, and natural bipedal locomotion on lower-body assistive devices, as well as developing human-in-the-loop methods to customize the experimental locomotion based on subjective user feedback.

Real-time Distributed Decision Making in Networked Systems

September 17, 2021 10-11am

BlueJeans: https://gatech.bluejeans.com/877658093/8250

Na Li

Gordon McKay professor

Electrical Engineering and Applied Mathematics

Harvard University

Abstract

Recent revolutions in sensing, computation, communication, and actuation technologies have been boosting the development and implementation of data-driven decision making, greatly advancing the monitoring and control of complex network systems. In this talk, we will focus on real-time distributed decision-making algorithms for networked systems. The first part will be on the  scalable multiagent reinforcement learning algorithms and the second part will be on the model free control methods for power systems based on continuous time zeroth-order optimization methods. We will show that exploiting network structure or underlying physical dynamics will facilitate the design of scalable real-time learning and control methods.

Biography

Na Li is a Gordon McKay professor in Electrical Engineering and Applied Mathematics at Harvard University.  She received her Bachelor degree in Mathematics from Zhejiang University in 2007 and Ph.D. degree in Control and Dynamical systems from California Institute of Technology in 2013. She was a postdoctoral associate at Massachusetts Institute of Technology 2013-2014.  Her research lies in control, learning, and optimization of networked systems, including theory development, algorithm design, and applications to real-world cyber-physical societal system. She received NSF career award (2016), AFSOR Young Investigator Award (2017), ONR Young Investigator Award(2019),  Donald P. Eckman Award (2019), McDonald Mentoring Award (2020), along with some other awards.

The Rational Selection of Goal Operations and the Integration of Search Strategies with Goal-Driven Marine Autonomy

September 9, 2021 1-2pm in Marcus Nanotechnology room 1117 – 1118

Video Recording: https://primetime.bluejeans.com/a2m/events/playback/2914884e-99a6-4d7f-9e95-81d16e95de96

Michael T. Cox

Research Professor

Department of Computer Science and Engineering

Wright State University, Dayton

Abstract

Intelligent physical systems as embodied cognitive systems must perform high-level reasoning while concurrently managing an underlying control architecture. The link between cognition and control must manage the problem of converting continuous values from the real world to symbolic representations (and back). To generate effective behaviors, reasoning must include a capacity to replan, acquire and update new information, detect and respond to anomalies, and perform various operations on system goals. But, these processes are not independent and need further exploration. This paper examines an agent’s choices when multiple goal operations co-occur and interact, and it establishes a method of choosing between them. We demonstrate the benefits and discuss the trade offs involved with this and show positive results in a dynamic marine search task.

Biography

Michael T. Cox is a Research Professor in the Department of Computer Science and Engineering at Wright State University, Dayton and was the founding Director of Autonomy Research at Parallax Advanced Research. Dr. Cox is a former DARPA/I2O program manager and has held senior research positions at Raytheon BBN Technologies, the CMU School of Computer Science, and the University of Maryland Institute for Advanced Computer Studies. He has interests in autonomous systems, mixed-initiative planning, computational metacognition, and case-based reasoning. His research group developed the Metacognitive Integrated Dual-Cycle Architecture (MIDCA) and was instrumental in the development of a high-level approach to autonomy called goal-driven autonomy. He graduated summa cum laude in Computer Science (1986) from Georgia Tech and holds a PhD in Computer Science (1996) from the same.

DCL Student Symposium 2021 Overview

The 2021 Georgia Tech Decision and Control Laboratory (DCL) Student Symposium was held virtually during April 15th-16th.  In spite of the virtual format, all sessions enjoyed lively participation and interaction.

This two-day event presented 3 plenary talks and 35 posters. The videos for poster sessions can be found on DCL youtube channel https://www.youtube.com/channel/UCY79pFXOrnSmV33aq83GG1g.

In addition, a special event “Students’ Farewell Brunch with Magnus” was held for students to express their gratitude for Dr. Magnus Egerstedt, and what he represents to the graduate research community in robotics and controls at Georgia Tech.

We are very grateful to the support and guidance from Decision and Control Laboratory (DCL) and Georgia Tech.  Due to the hard work of the student organizing committee and participation of graduate students in DCL, the student symposium was successful  in spite of the COVID situation. 

Plenary Talk 3 given by Dr. Dawn Tilbury
Special Event for Dr. Magnus Egerstedt
Virtual Interactions

Plenary Talk 3: A Multi-agent Distributed Control Approach to Complex Manufacturing Systems

April 16, 2021 – 1:00 pm, Plenary talk 3 for DCL Student Symposium 2021

Bluejeans link: https://primetime.bluejeans.com/a2m/live-event/hehxxuty

Dawn M. Tilbury

University of Michigan, Ann Arbor

Abstract

Many manufacturing systems today have been optimized for mass production, making the same products over and over again with high quality and low cost. There is an increased demand for customized or even personalized production, which can be possible while utilizing many of the same machines currently existing on plant floors. However, the control systems must be completely redefined. The Internet of Things and networked control systems are key enabling technologies to realize this vision.

Decentralized control strategies, specifically agent-based control, can be used to enable customized and personalized production, while improving the flexibility and responsiveness of manufacturing systems. A manufacturing plant floor has both resource agents, representing the processing and material handling resources available, as well as product agents, representing the parts that traverse through the factory, being transformed from raw materials to finished products. Agents each have their own goals, and make decisions based on these goals, their communications with each other, and information available from the physical system. This presentation will cover our recent work on product agents, and discuss how this decentralized approach can lead to improved productivity. Implementation on a small-scale automated testbed will be presented.

Biography

Dr. Dawn M. Tilbury received the B.S. degree in Electrical Engineering, summa cum laude, from the University of Minnesota in 1989, and the M.S. and Ph.D. degrees in Electrical Engineering and Computer Sciences from the University of California, Berkeley, in 1992 and 1994, respectively. In 1995, she joined the faculty of the University of Michigan, Ann Arbor, where she is currently Professor of Mechanical Engineering with a joint appointment in Electrical Engineering and Computer Science. Her research interests lie broadly in the area of control systems, including applications to robotics and manufacturing systems. She has published more than 150 articles in refereed journals and conference proceedings. She was elected Fellow of the IEEE in 2008 and Fellow of the ASME in 2012, and is a Life Member of SWE. Since June of 2017, she has been the Assistant Director for Engineering at the National Science Foundation.

Plenary Talk 2: A Systems Approach to Electrified Mobility

April 15, 2021 – 1:00 pm, Plenary talk 2 for DCL Student Symposium 2021

Bluejeans link: https://primetime.bluejeans.com/a2m/live-event/hehxxuty

Andrew G. Alleyne

University of Illinois at Urbana–Champaign

Abstract

We live in an increasingly electrified world. For stationary applications such as industry and manufacturing, this statement has been obvious since the start of the 20th century as steam and belt drives in factories gradually gave way to electric motors for machining, conveyor lines, and all manner of other industrial applications. For domestic stationary applications, modern conveniences blossomed as electrification grew starting in the middle of the 20th century. Lighting, air-conditioning, cooking and cleaning, as well as many types of in-home entertainment were fueled by growing abilities to provide relatively cheap electrical power over long distances.

Now, a fifth of the way through the 21st century, we are seeing electrification rise in the mobile domain. The progress has been steady for several decades but it is really during the past several years that electrified mobility has seen a rapid growth at the level of individual consumer. Interestingly, this growth cuts across widely varying modes of mobility; from individual bicycles to on-highway vehicles to large ships and aircraft.

This talk will detail some of the trends in mobility domains and will discuss some of the technical challenges. For mobility systems, the power density is a key metric of performance that dictates viability of technology for use in the transport of goods and people. Of high relevance to Decision and Control audience that cross-cuts departments, we will discuss the interplay between modes of power distribution within electrified mobility systems. This includes the flow of power in the mechanical, electrical, and thermal domains. Several examples of challenges will be raised along with some solutions and open questions across the broad spectrum of Mechanical Engineering fields. In particular, we will demonstrate examples where the integration of different fields, in a systems-level approach, can afford significant advantages in power density.

Biography

Dr. Andrew G. Alleyne (F’17) received the B.S.E. degree from Princeton University, Princeton, NJ, USA, in 1989, and the M.S. and Ph.D. degrees from the University of California at Berkeley, Berkeley, CA, USA, in 1992 and 1994, respectively. He held visiting professorships at TU Delft, Delft, The Netherlands, the University of Colorado, Boulder, CO, USA, ETH Zu?rich, Zu?rich, Switzerland, and Johannes Kepler University, Linz, Austria. He is currently the Ralph and Catherine Fisher Professor with the University of Illinois at Urbana–Champaign, Urbana, IL, USA, and the Director of the NSF ERC on Power Optimization for Electro-Thermal Systems (POETS). He works the modeling, simulation, and control of nonlinear mechanical systems. His academic record includes supervision of over 80 M.S. and Ph.D. students and over 400 conferences and journal publications. Dr. Alleyne is a fellow of American Society for Mechanical Engineers (ASME). He serves on the Scientific Advisory Board of the U.S. Air Force and the National Academies Board on Army Research and Development. Recognitions include the IEEE CSS Distinguished Lecturer, a Fulbright, the Gustus Larson Award, the Charles Stark Draper Award, and the Henry Paynter Outstanding Investigator Award.

Plenary Talk 1: Guiding Vector Fields for Robot Navigation

April 15, 2021 – 10:00 am, Plenary talk 1 for DCL Student Symposium 2021

Bluejeans link: https://primetime.bluejeans.com/a2m/live-event/hehxxuty

Ming Cao

University of Groningen, Netherlands

Abstract

In robot navigation tasks, such as UAV highway traffic monitoring, it is important for a mobile robot to follow a prescribed desired path. However, most of the existing path following navigation algorithms cannot guarantee global convergence to desired paths or enable following self-intersected desired paths due to the existence of singular points, where navigation algorithms return unreliable or even no solutions. In this talk, I show how to deal with this issue when using vector-field guided path-following (VF-PF). Conventional VF-PF algorithms generate a vector field of the same dimension as that of the space where the desired path lives. By contrast, we propose a novel method to transform self-intersected or simple closed desired paths to non-self-intersected and unbounded (precisely, homeomorphic to the real line) counterparts in a higher-dimensional space; correspondingly, we construct a singularity-free guiding vector field in a higher-dimensional space. I will also show the results of our outdoor experiments with a fixed-wing airplane in a windy environment to follow both 2D and 3D desired paths.

Biography

Dr. Ming Cao has since 2016 been a professor of networks and robotics with the Engineering and Technology Institute (ENTEG) at the University of Groningen, the Netherlands, where he started as an assistant professor in 2008. He received the Bachelor degree in 1999 and the Master degree in 2002 from Tsinghua University, Beijing, China, and the Ph.D. degree in 2007 from Yale University, New Haven, CT, USA, all in Electrical Engineering. From September 2007 to August 2008, he was a Postdoctoral Research Associate with the Department of Mechanical and Aerospace Engineering at Princeton University, Princeton, NJ, USA. He worked as a research intern during the summer of 2006 with the Mathematical Sciences Department at the IBM T. J. Watson Research Center, NY, USA. He is the 2017 and inaugural recipient of the Manfred Thoma medal from the International Federation of Automatic Control (IFAC) and the 2016 recipient of the European Control Award sponsored by the European Control Association (EUCA). He is a Senior Editor for Systems and Control Letters, an Associate Editor for IEEE Transactions on Automatic Control, and was an associate editor for IEEE Transactions on Circuits and Systems and IEEE Circuits and Systems Magazine. He is a member of the IFAC Conference Board and a vice chair of the IFAC Technical Committee on Large-Scale Complex Systems. His research interests include autonomous agents and multi-agent systems, complex networks and decision-making processes.

Objective Learning for Autonomous Systems

April 9, 2021 – 2:00 pm in Bluejeans: https://bluejeans.com/851024140

Shaoshuai Mou

Purdue University

Abstract

Autonomous systems especially those driven under optimal control are usually associated with objective functions to describe their goals/tasks in specific missions. Since they are usually unknown in practice especially for complicated missions, learning such objective functions is significant to autonomous systems especially in their imitation learning and teaming with human. In this talk we will introduce our recent progress in objective learning based on inverse optimal control and inverse optimization, especially their applications in human motion segmentation, learning from sparse demonstrations, and learning with directional corrections. We will also present an end-to-end learning framework based on Pontryagin Principle, feedbacks and optimal control, which is able to treat solving inverse optimization, system identification, and some control/planning tasks as its special modes.

Biography

Dr. Shaoshuai Mou is an Assistant Professor in the School of Aeronautics and Astronautics at Purdue University. Before joining Purdue, he received a Ph.D. in Electrical Engineering at Yale University in 2014 and worked as a postdoc researcher at MIT for a year after that. His research interests include multi-agent autonomy and learning, distributed algorithms for control and optimization, human-machine teaming, resilience & cybersecurity, and also experimental research involving autonomous air and ground vehicles. Dr. Mou co-direct Purdue’s new Center for Innovation in Control, Optimization and Networks (ICON), which consists of more than 50 faculty and aims to integrate classical theories in control/optimization/networks with recent advance in machine learning/AI/data science to address fundamental challenges in autonomous and connected systems. For more information, please refer to https://engineering.purdue.edu/ICON

Guidelines for Poster Submission, DCL Student Symposium 2021

For the DCL poster design, please feel free to choose any template/design available on the internet or provided by MS PowerPoint or even create your own poster design. Due to Covid-19, the DCL 2021 Symposium will be held virtually on  “SpatialChat” online platform.  

Consequently, participants must adhere to the poster font and dimension specification listed below to ensure the legibility of the posters on the Spatial Chat platform.  Smaller font sizes that sufficed in physical poster presentation settings will appear as too small on Spatial Chat. You can find two poster examples below, “Physical Poster” and “Virtual Poster”. The first one was designed to be presented in a physical presentation setting while the second was designed for virtual presentation setting. Those poster examples give the reader an idea of how the font size and dimensionality aspects of the poster affects the readability and visibility of the poster when presented on an online virtual platform. Finally, please find attached a poster template file, ‘posterTmp.ppt,’ that participant could use. 

Poster design specifications: 

  • Poster size: A0 (Landscape) 118.9 cm (width) by 84.1 cm (height). 
  • Title font-size: 100. 
  • Section headings font-size: 70. 
  • Paragraph text font-size: 45. 
  • Images and figures are preferred to be in vector graphics format to avoid pixilation. 
  • Final poster file must in an image format, e.g., JPG or SVG. However, export your poster as .SVG to avoid pixilation. 
Physical Poster
Virtual Poster