Robotics Colloquium

The Robotics Colloquium features talks by invited and local researchers on all aspects of robotics, including control, perception, machine learning, mechanical design and interaction. The colloquium is held Fridays between 1:30-2:30pm. Special seminars outside this schedule are indicated with * below. Check schedule below for location. Refreshments are served.

If you would like to give a talk in upcoming Robotics Colloquia, please contact Maya Cakmak (mcakmakatcs). If you would like to get regular email announcements and reminders about the robotics colloquium speakers, please sign up to the Robotics@UW mailing list.

 
(UPCOMING) Spring 2018 Organizers: Dieter Fox, Maya Cakmak, Siddhartha S. Srinivasa, Sam Burden
03/30/2018
TBA TBA
04/06/2018
CSE 305
David Rollison
Hebi Robotics
TBA abstract
04/13/2018
CSE 305
Michael A. Goodrich
Brigham Young University
TBA abstract
04/20/2018
CSE 305
Dmitry Berenson
University of Michigan
TBA abstract
04/27/2018
CSE 305
Karen Liu
Georgia Tech
TBA abstract
05/04/2018
TBA TBA
05/11/2018
CSE 305
TBA TBA
05/18/2018
CSE 305
Devin Balkcom
Dartmouth College
TBA abstract
05/25/2018
TBA TBA
06/01/2018
Dan Koditschek
UPenn
TBA abstract
 
Winter 2018 Organizers: Dieter Fox, Maya Cakmak, Siddhartha S. Srinivasa, Kat Steele
01/12/2018
No talk
01/18/2018
CSE 691
(10 AM)
Allison Okamura
Stanford University
Let’s be Flexible: Soft Haptics and Soft Robotics abstract
01/19/2018
HUB 250
(1 PM)
David Reinkensmeyer
UC Irvine
Robotic-assisted movement training after stroke: Why does it work and how can it be made to work better? abstract
01/26/2018
CSE 305
Stefanos Nikolaidis
CMU/University of Washington
Mathematical Models of Adaptation in Human-Robot Collaboration abstract
02/02/2018
No talk
02/07/2018
CSE 305
(3 PM)
Peter Trautman
1-Dimensional Joint Probability Distributions: the Duality of Shared Control and Crowd Navigation Solutions abstract
02/09/2018
EEB 037
Amir Rubin
Paracosm
SLAM and 3D-reconstruction for Real World Use Cases abstract
02/16/2018
CSE 305
Emel Demircan
California State University
Human Movement Understanding abstract
02/23/2018
CSE 305
Kris Hauser
Duke University
The Space of Spaces: Understanding the Structure Between Motion Planning Problems abstract
03/02/2018
CSE 305
Marco Pavone
Stanford University
Planning and Decision Making for Autonomous Spacecraft and Space Robots abstract
03/09/2018
CSE 305
Yu Xiang
UW/NVidia
Perceiving the 3D World from Images and Videos abstract
 
Autumn 2017 Organizers: Dieter Fox, Maya Cakmak, Siddhartha S. Srinivasa, Kat Steele, Sam Burden
09/29/2017
MEB 238
3:30 PM
Michael Tolley
University of California San Diego
ME colloquium: Soft Robotics abstract
10/06/2017
CSE 305
Geoffrey A. Hollinger
Oregon State University
Marine Robotics: Planning, Decision Making, and Learning abstract
10/13/2017 DUB retreat
No talk
10/20/2017
CSE 305
Byron Boots
Georgia Institute of Technology
Learning Perception and Control for Agile Off-Road Autonomous Driving abstract
10/27/2017
CSE 691
Tucker Hermans
University of Utah
Learning and Planning for Autonomous Multi-fingered Robot Manipulation abstract
11/03/2017
CSE 305
Joydeep Biswas
University of Massachusetts Amherst
Deploying Autonomous Service Mobile Robots, And Keeping Them Autonomous abstract
11/10/2017 No talk
11/17/2017
CSE 691
Oren Salzman
Carnegie Mellon University
The Provable Virtue of Laziness in Motion Planning abstract
11/24/2017 Thanksgiving
No talk
12/01/2017 No talk
12/08/2017
CSE 305
Yigit Menguc
Oregon State University
Material Robotics: Soft active materials, bioinspired mechanisms, and additive manufacturing abstract
 
Spring 2017 Organizers: Aaron Walsman, Sam Burden, Maya Cakmak, Dieter Fox
03/31/2017
CSE 305
Richard Vaughan
Simon Fraser University
Simple, Robust Interaction Between Humans and Teams of Robots abstract
04/07/2017
CSE 691
Oussama Khatib
Stanford
Ocean One: A Robotic Avatar for Oceanic Discovery abstract
04/14/2017
CSE 305
Debadeepta Dey
Microsoft Research
Learning via Interaction for Machine Perception and Control abstract
04/21/2017
CSE 303 (11 AM)
Eric Eaton
University of Pennsylvania
Efficient Lifelong Machine Learning: an Online Multi-Task Learning Perspective abstract
04/21/2017
CSE 305
Katsu Ikeuchi
Microsoft Research
e-Intangible Heritage, from Dancing robots to Cyber Humanities abstract
04/28/2017
CSE 691
Henrik Christensen
UC San Diego
Object Based Mapping abstract
05/05/2017
CSE 305
Alberto Rodriguez
MIT
Reactive Robotic Manipulation abstract
05/12/2017
CSE 305
Charlie Kemp
Georgia Tech
Mobile Manipulators for Intelligent Physical Assistance abstract
05/19/2017
CSE 305
Karol Hausman
University of Southern California
Rethinking Perception-Action Loops abstract
05/26/2017
CSE 305
Silvia Ferrari
Cornell University
Neuromorphic Planning and Control of Insect-scale Robots abstract
06/02/2017
 
No Colloquium (ICRA)    
 
Winter 2017 Organizers: Sam Burden, Maya Cakmak, Dieter Fox
01/06/2017 No colloquium    
01/13/2017
 
Matt Rueben
Oregon State University
Privacy Sensitive Robotics abstract
01/20/2017
2:30-5:00pm
Frontiers of Science
Savery Hall 260
   
01/27/2017 Ross Hatton
Oregon State University
Snakes & Spiders, Robots & Geometry abstract
02/03/2017 Avik De
University of Pennsylvania
Anchored Behaviors from Template Compositions abstract
02/10/2017 No talk    
02/17/2017 Sonia Chernova
Georgia Institute of Technology
Reliable Robot Autonomy through Learning and Interaction abstract
02/24/2017 No talk    
03/03/2017 No talk    
03/10/2017 No talk    
 
Fall 2016 Organizers: Sam Burden, Maya Cakmak, Dieter Fox, Sawyer Fuller
10/07/2016
CSE 305
David Remy
University of Michigan
Gaits and Natural Dynamics in Robotic Legged Locomotion abstract
10/14/2016
 
IROS 2016 and DUB retreat
No talk
   
10/21/2016 Industry Affiliates Week
Check out talks and posters by robotics students
   
10/28/2016
CSE 305
Emo Todorov
University of Washington
Goal-directed Dynamics abstract
11/04/2016
CSE 305
Sean Andrist
Microsoft Research
Gaze Mechanisms for Situated Interaction with Embodied Agents abstract
11/11/2016
 
Veterans day
No talk
   
11/18/2016
CSE 305
Nick Roy
MIT
Planning to Fly (and Drive) Aggressively abstract
11/25/2016
 
Thanksgiving
No talk
   
12/02/2016
CSE 305
Shai Revzen
University of Michigan
Seeking simple models for multilegged locomotion: hybrid oscillators, rapid manufacturing, and slippage abstract
12/09/2016
CSE 305
Ashis Banerjee
University of Washington
Toward Real-Time Motion Planning and Control of Optically Actuated Micro-Robots abstract
 
Spring 2016 Organizers: Justin Huang, Leah Perlmutter, Dieter Fox, and Maya Cakmak
4/1/16
CSE 305
Tomás Lozano-Pérez
MIT
Integrated task and motion planning in belief space abstract
4/8/16
CSE 305
Henny Admoni
CMU / Yale
Recognizing Human Intent for Assistive Robotics abstract
4/11/16
CSE 305
Wolfram Burgard
University of Frieburg
Deep Learning for Robot Navigation and Perception abstract
4/22/16
CSE 305
Travis Deyle
Cobalt Robotics
RFID-Enhanced Robots Enable New Applications in Healthcare, Asset Tracking, and Remote Sensing abstract
5/6/16
CSE 305
Brian Scassellati
Yale
Robots That Teach abstract
5/13/16
CSE 305
Sarah Elliott, Mohammad Haghighipanah, Vikash Kumar, Yangming Li, Muneaki Miyasaka, Leah Perlmutter, Luis Puig, and Yuyin Sun
University of Washington
ICRA 2016 Practice Talks abstract
6/3/16
CSE 305
Sidd Srinivasa
CMU
Physics-based Manipulation abstract
*6/10/16
CSE 403
3:30 pm
Ashish Kapoor
Microsoft Research
Planetary Scale Swarm Sensing, Planning and Control for Weather Prediction abstract
 
Winter 2016 Organizers: Kendall Lowrey, Patrick Lancaster, and Dieter Fox
3/11/16
CSE 305
Daniel Butler
UW CSE
Model-based Reinforcement Learning with Parametrized Physical Models and Optimism-Driven Exploration abstract
3/04/16
CSE 305
James Youngquist
UW CSE
DeepMPC: Learning Deep Latent Features for Model Predictive Control abstract
2/26/16
CSE 305
Justin Huang
UW CSE
Place Recognition with ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free abstract
2/19/16
EEB 303
Daniel Gordon
UW CSE
Deep Neural Decision Forests abstract
2/12/16
CSE 305
Harley Montgomery
UW CSE
End-to-End Training of Deep Visuomotor Policies abstract
2/5/16
CSE 305
Aaron Walsman
UW CSE
Mastering the game of Go with deep neural networks and tree search abstract
1/29/16
CSE 305
Zachary Nehrenberg
UW CSE
Real-Time Trajectory Generation for Quadrocopters abstract
1/29/16
CSE 305
Patrick Lancaster
UW CSE
Towards Learning Hierarchical Skills for Multi-Phase Manipulation Tasks abstract
1/22/16
CSE 305
Tanner Schmidt
UW CSE
Pose Estimation of Kinematic Chain Instances via Object Coordinate Regression abstract
1/15/16
CSE 305
Kendall Lowrey
UW CSE
Combining the benefits of function approximation and trajectory optimization abstract
1/15/16
CSE 305
Vladimir Korukov
UW CSE
Information-Theoretic Planning with Trajectory Optimization for Dense 3D Mapping abstract
 
Fall 2015 Organizers: Tanner Schmidt and Dieter Fox
10/9/15
CSE 305
Dan Bohus
Microsoft Research
Physically Situated Dialog: Opportunities and Challenges abstract
10/16/15
CSE 305
Sawyer Fuller
UW
Aerial autonomy at insect scale: What flying insects can tell us about robotics and vice versa abstract
10/23/15
Kane Hall 110
Russ Tedrake
MIT
From Polynomials to Humanoid Robots
Part of the MathAcrossCampus Colloquium Series
abstract
10/30/15
CSE 305
Frank Dellaert
Skydio
Factor Graphs for Flexible Inference in Robotics and Vision abstract
11/6/15
CSE 305
Student Research Lightning Talks    
11/13/15
CSE 305
Louis-Philippe Morency
CMU
Modeling Human Communication Dynamics abstract
11/20/15
CSE 305
Tom Whelan
Oculus Research
Real-time dense methods for 3D perception abstract
11/27/15
CSE 305
Thanksgiving
No talk
   
12/4/15
CSE 305
Seth Hutchinson
UIUC
Robust Distributed Control Policies for Multi-Robot Systems abstract
12/11/15
CSE 305
Dmitry Berenson
WPI
Toward General-Purpose Manipulation of Deformable Objects abstract
 
Spring 2015 Organizers: Connor Schenck, Maya Cakmak, Dieter Fox
04/17/15
CSE 303
Neil Lebeck and Natalie Brace
UW CSE
Multirotor Aerial Vehicles: Modeling, Estimation, and Control of Quadrotor abstract
04/24/15
CSE 303
Peter Henry
UW CSE
LSD-SLAM: Large-Scale Direct Monocular SLAM abstract
05/01/15
CSE 303
Dan Butler
UW CSE
Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments abstract
05/07/15
CSE 303
Marc Deisenroth
Imperial College, London
Statistical Machine Learning for Autonomous Systems and Robots abstract
05/15/15
CSE 303
Arunkumar Byravan and Kendall Lowrey
UW CSE
Reinforcement Learning in Robotics: A Survey abstract
05/22/15   ICRA practice talks. abstracts
05/29/15 No Colloquium Colloquium cancelled for ICRA 2015.  
06/05/15
CSE 303
Jim Youngquist
UW CSE
A Strictly Convex Hull for Computing Proximity Distances With Continuous Gradients abstract
 
Winter 2015 Organizers: Connor Schenck, Maya Cakmak, Dieter Fox
01/14/15
CSE 305
Mike Chung
UW CSE
Accelerating Imitation Learning through Crowdsourcing abstract
  Tanner Schmidt
UW CSE
Dense Articulated Real-Time Tracking abstract
01/23/15
CSE 305
Discussion Amazon Picking Challenge <
01/30/15 No colloquium    
02/06/15
CSE 305
Joseph Xu
UW CSE
Design and Control of an Anthropomorphic Robotic Hand: Learning Advantages From the Human Body & Brain abstract
  Vikash Kumar
UW CSE
Dimensionality Augmentation: A tool towards synthesizing complex and expressive behaviors abstract
02/13/15
CSE 305
Sofia Alexandrova
UW CSE
RoboFlow: A Flow-based Visual Programming Language for Mobile Manipulation Tasks abstract
02/20/15
CSE 305
Igor Mordatch
UW CSE
Synthesis of Interactive Control for Diverse Complex Characters with Neural Networks abstract
02/27/15
CSE 305
Richard Newcombe
UW CSE
DynamicFusion: Reconstruction and Tracking of Non-Rigid Scenes in Real-Time abstract
03/06/15
CSE 691
Aaron Steinfeld
Carnegie Mellon University
Understanding and Creating Appropriate Robot Behavior abstract
03/13/15
CSE 305
Luis Puig
UW CSE
Overview of Omnidirectional Vision abstract
 
Autumn 2014 Organizers: Vikash Kumar, Maya Cakmak, Dieter Fox
10/03/14
CSE 305
Danny Kaufman
Adobe Creative Technologies Lab, Seattle
Geometric Algorithms for Computing Frictionally Contacting Systems abstract
10/10/14
EE 037
Dubi Katz & Michael Abrash
Oculus VR
VR, the future, and you abstract
10/17/14
CSE 503
3:30pm
Kira Mourao
PostDoc, Institute for Language, Cognition and Computation, University of Edinburgh
What happens if I push this button? Learning planning operators from experience abstract
10/24/14
CSE 305
Sam Burden
PostDoc, University of California, Berkeley
Hybrid Models for Dynamic and Dexterous Robots abstract
*10/29/14 (Wed)
HUB 250
12:30pm
Bilge Mutlu
University of Wisconsin, Madison
Human-Centered Principles and Methods for Designing Robotic Technologies
(Joint with DUB seminar, lunch will be served at 12:00)
abstract
10/31/14
CSE 305
Sergey Levine
PostDoc, University of California, Berkeley
Learning to Move: Machine Learning for Robotics and Animation abstract
11/07/14 No talk    
11/14/14 Sachin Patil
PostDoc, University of California, Berkeley
Coping with Uncertainty in Robotic Navigation and Manipulation abstract
11/21/14
Gates Commons
3:00pm
HRI Mini Symposium
HRI 2015 Program committee members
   
11/28/14 No talk, Thanksgiving Break    
12/05/14
CSE 305
Marianna Madry
Royal Institute of Technology (KTH), Sweden
Representing Objects in Robotics from Visual, Depth and Tactile Sensing abstract
*12/18/14 (Thu)
CSE 305
11:00am
Scott Niekum
Carnegie Mellon University
Structure Discovery in Robotics with Demonstrations and Active Learning abstract
Winter 2014, Organizer: Maya Cakmak
01/17/14
CSE 403
Byron Boots
UW CSE
Learning Better Models of Dynamical Systems abstract
01/24/14
CSE 403
Julie Shah
MIT
Integrating Robots into Team-Oriented Environments abstract
01/31/14
CSE 403
Ryan Calo
UW Law
Robotics & The New Cyberlaw abstract
02/07/14
CSE 403
James McLurkin
Rice University
Distributed Algorithms for Robot Recovery, Multi-Robot Triangulation, and Advanced Low-Cost Robots abstract
02/14/14   Cancelled  
02/21/14
CSE 403
Mihai Jalobeanu
Microsoft Research
Towards ubiquitous robots abstract
02/28/14
CSE 403
Cynthia Matuszek
UW CSE
Talking to Robots: Learning to Ground Human Language in Perception and Execution abstract
03/07/14   Cancelled  
03/14/14
CSE 403
Peter H. Kahn, Jr.
UW Psychology
Social and Moral Relationships with Robots abstract
03/21/14
Gates Commons
Gur Kimchi
Amazon
Amazon Prime Air abstract
Autumn 2013, Organizer: Maya Cakmak
10/11/13
MGH 241
Ashutosh Saxena
Cornell University
How should a robot perceive the world?
(Joint with Machine Learning)
abstract
10/18/13   UW/MSR Machine Learning day  
10/25/13
CSE 403
Kat Steele
University of Washington, Mechanical Engineering
Strategies for understanding and improving movement disorders abstract
11/01/13
CSE 403
Maya Cakmak
University of Washington, CSE
Towards seamless human-robot hand-overs abstract
*11/07/13 (Thu)
CSE 403
2:30-3:20pm
Ross A. Knepper
MIT
Autonomous Assembly In a Human World abstract
*11/08/13
CSE 403
12-1pm
Brian Ziebart
University of Illinois, Chicago
Beyond Conditionals: Structured Prediction for Interacting Processes
(Lunch will be served)
abstract
11/08/13
Gates Commons
Jenay Beer
University of South Carolina
Considerations for Designing Assistive Robotics to Promote Aging-in-Place abstract
11/15/13
CSE 403
Dinei Florencio
Microsoft Research
Navigation for telepresence robots and some thoughts on robot learning abstract
11/22/13
CSE 403
Andrzej Pronobis
University of Washington, CSE
Semantic Knowledge in Mobile Robotics: Perception, Reasoning, Communication and Actions abstract
12/06/13
Gates Commons
Steve Cousins
Savioke, Inc. & Willow Garage, Inc.
It's Time for Service Robots
(Joint with CSNE)
abstract
Spring 2013, Organizers: Cynthia Matuszek, Dieter Fox
04/5/13 Dieter Fox
Cynthia Matuszek
PechaKucha 20x20 for Robotics abstract
04/12/13 No talk    
04/19/13 Robotics Students & Staff PechaKucha-style Robotics Research Overviews abstract
04/26/13 Pete Wurman
Special Wednesday Colloquium, CSE 203
Coordinating Hundreds of Autonomous Vehicles in Warehouses
abstract
04/26/13 Matt Mason Learning to Use Simple Hands abstract
05/03/13 Nadia Shouraboura Canceled  
05/10/13 No talk (ICRA)
05/17/13 Tom Daniel Control and Dynamics of Animal Flight: Reverse Engineering Nature's Robots abstract
05/24/13 Katherine Kuchenbecker The Value of Tactile Sensations in Haptics and Robotics abstract
05/31/13 Pieter Abbeel Machine Learning and Optimization for Robotics abstract
06/07/13 Nick Roy Canceled  
Winter 2013, Organizer: Dieter Fox
01/18/13 Robotics and State
Estimation Lab
Overview of RSE Lab Research
01/25/13 Joshua Smith Robotics Research in the Sensor Systems Group abstract
02/01/13 no talk    
02/08/13 Gaurav Sukhatme Persistent Autonomy at Sea abstract
02/15/13 Jiri Najemnik Sequence Optimization in Engineering, Artificial Intelligence and Biology abstract
02/22/13 no talk    
03/01/13 Richard Newcombe Beyond Point Clouds: Adventures in Real-time Dense SLAM abstract
03/08/13 Tom Erez Model-Based Optimization for Intelligent Robot Control abstract
03/15/13 Byron Boots Spectral Approaches to Learning Dynamical Systems abstract
Spring 2012, Organizer: Dieter Fox
3/30/12 Andrea Thomaz Designing Learning Interactions for Robots abstract
4/6/12 Javier Movellan Towards a New Science of Learning abstract
4/13/12 Emanuel Todorov Automatic Synthesis of Complex Behaviors with Optimal Control abstract
4/20/12 Andrew Barto Autonomous Robot Acquisition of Transferable Skills abstract
4/27/12 Dieter Fox Grounding Natural Language in Robot Control Systems abstract
5/4/12 Allison Okamura Robot-Assisted Needle Steering abstract
5/11/12 Blake Hannaford Click the Scalpel -- Better Patient Outcomes by Advancing Robotics in Surgery abstract
5/18/12 no talk  
5/25/12 Malcolm MacIver Robotic Electrolocation abstract
6/1/12 Drew Bagnell Imitation Learning, Inverse Optimal Control and Purposeful Prediction abstract
 
DETAILED SCHEDULE FOR WINTER 2018
01/18/2018 Allison Okamura
Stanford University
Let’s be Flexible: Soft Haptics and Soft Robotics
Abstract: While traditional robotic manipulators are constructed from rigid links and localized joints, a new generation of robotic devices are soft, using flexible, deformable materials. In this talk, I will describe several new systems that leverage softness to achieve novel shape control, provide a compliant interface to the human body, and access hard-to- reach locations. First, soft haptic devices change their shape and mechanical properties to allow medical simulation and new paradigms for human-computer interface. They can be made wearable by people or by objects in the environment, as needed to assist human users. Second, superelastic materials and 3D-printed soft plastics enable surgical robots that can steer within the human body in order to reach targets inaccessible via the straight-line paths of traditional instruments. These surgical robots are designed on a patient- and procedure-specific basis, to minimize invasiveness and facilitate low-cost interventions in special patient populations. Third, everting pneumatic tubes are used to create robots that can grow hundreds of times in length, steer around obstacles, and squeeze through tight spaces. These plant-inspired growing robots can achieve simple remote manipulation tasks, deliver payloads such as water or sensors in search and rescue scenarios, and shape themselves into useful structures.

Speaker’s Bio: Allison M. Okamura received the BS degree from the University of California at Berkeley in 1994, and the MS and PhD degrees from Stanford University in 1996 and 2000, respectively, all in mechanical engineering. She is currently Professor in the mechanical engineering department at Stanford University, with a courtesy appointment in computer science. She was previously Professor and Vice Chair of mechanical engineering at Johns Hopkins University. She has been an associate editor of the IEEE Transactions on Haptics, editor-in- chief of the IEEE International Conference on Robotics and Automation Conference Editorial Board, an editor of the International Journal of Robotics Research, and co-chair of the IEEE Haptics Symposium. Her awards include the 2016 Duca Family University Fellow in Undergraduate Education, 2009 IEEE Technical Committee on Haptics Early Career Award, 2005 IEEE Robotics and Automation Society Early Academic Career Award, and 2004 NSF CAREER Award. She is an IEEE Fellow. Her academic interests include haptics, teleoperation, virtual environments and simulators, medical robotics, neuromechanics and rehabilitation, prosthetics, and engineering education. Outside academia, she enjoys spending time with her husband and two children, running, and playing ice hockey. For more information about her research, please see the Collaborative Haptics and Robotics in Medicine (CHARM) Laboratory website: http://charm.stanford.edu.
01/19/2018 David Reinkensmeyer
UC Irvine
Robotic-assisted movement training after stroke: Why does it work and how can it be made to work better?
Abstract: Robotic therapy refers now to a diverse set of technologies and algorithms that can match or improve the clinical benefits achievable with conventional rehabilitation therapies after stroke and other neurologic injuries. However, the principles by which robotic therapy devices can be optimized are still not well understood. Here, I will first briefly overview the evolution of the technology and science of robot-assisted rehabilitation. Then, I will describe recent experimental evidence that implicates three key neuro-computational mechanisms that determine the effectiveness of robotic therapy: human slacking, Hebbian learning via proprioceptive stimulation, and mechanical modulation of psychological outcomes that influence motor retention. I will conclude by describing recent attempts to enhance the effectiveness of robotic therapy by combining it with neuro-regeneration, and by making it more accessible via “consumer stroke tech”.

Speaker’s Bio: David Reinkensmeyer is Professor in the Departments of Mechanical and Aerospace Engineering, Anatomy and Neurobiology, Biomedical Engineering, and Physical Medicine and Rehabilitation at the University of California at Irvine. He is co-director of the NIDILRR MARS3 Robotic Rehabilitation Engineering Center, co-director of the NIH K12 Engineering Career Development Center in Movement and Rehabilitation Sciences, and Editor-in- Chief of the Journal of Neuroengineering and Rehabilitation. He recently received the Innovator of the Year Award from the Henry Samueli School of Engineering and the Distinguished Midcareer Faculty Research Award from UC Irvine.
01/26/2018 Stefanos Nikolaidis
CMU/University of Washington
Mathematical Models of Adaptation in Human-Robot Collaboration
Abstract: The goal of my research is to improve human-robot collaboration by integrating mathematical models of human behavior into robot decision making. I develop game-theoretic algorithms and probabilistic planning techniques that reason over the uncertainty in the human internal state and its dynamics, enabling autonomous systems to act optimally in a variety of real-world collaborative settings. While much work in human-robot interaction has focused on leader-assistant teamwork models, the recent advancement of robotic systems that have access to vast amounts of information suggests the need for robots that take into account the quality of the human decision making and actively guide people towards better ways of doing their task. In this talk, I propose an equal partners model, where human and robot engage in a dance of inference and action, and I focus on one particular instance of this dance: the robot adapts its own actions via estimating the probability of the human adapting to the robot. I start with a bounded memory model of human adaptation parameterized by the human adaptability - the probability of the human switching towards a strategy newly demonstrated by the robot. I then propose data-driven models that capture subtler forms of adaptation, where the human teammate updates their expectations of the robot’s capabilities through interaction. Integrating these models into robot decision making allows for human-robot mutual adaptation, where coordination strategies, informative actions and trustworthy behavior are not explicitly modeled, but naturally emerge out of optimization processes. Human subjects experiments in a variety of collaboration and shared autonomy settings show that mutual adaptation significantly improves human-robot team performance, compared to one-way robot adaptation to the human.

Speaker’s Bio: Stefanos Nikolaidis completed his PhD at Carnegie Mellon's Robotics Institute in December 2017 and he is currently a research associate at the University of Washington, Computer Science & Engineering. His research lies at the intersection of human-robot interaction, algorithmic game-theory and planning under uncertainty. Stefanos develops decision making algorithms that leverage mathematical models of human behavior to support deployed robotic systems in real-world collaborative settings. He has a MS from MIT, a MEng from the University of Tokyo and a BS from the National Technical University of Athens. He has additionally worked as a research specialist at MIT and as a researcher at Square Enix in Tokyo. He has received a Best Enabling Technologies Paper Award from the IEEE/ACM International Conference on Human-Robot Interaction and was a Best Paper Award Finalist in the International Symposium on Robotics.
02/07/2018 Peter Trautman
Lockheed Martin
1-Dimensional Joint Probability Distributions: the Duality of Shared Control and Crowd Navigation Solutions
Abstract: In human-robot interaction (HRI), failing to model human-robot interdependence leads to severe performance decrements. In crowd navigation, modeling the crowd and robot independently leads to the "freezing robot problem"; in shared control, modeling the operator and robot independently leads to "unnecessary and unresolvable disagreement." These results suggest that joint modeling is a fundamental component of robust HRI. This is a non-trivial assertion because conventional joint approaches are intractable. My recent work focuses on low (one) dimensional “arbitration spaces” that enable real-time joint computation while retaining important optimality properties. This construction also provides mathematical guidance for applying machine learning—such as multi-view, transfer, and deep learning—to HRI. Finally, arbitration space methods show promise for human robot collaboration, assistive technologies, human-machine team design, hierarchical planning stacks, and distributed control.

Speaker’s Bio: Pete Trautman received his B.S. in Physics and Applied Mathematics from Baylor University in 2000. He then entered the United States Air Force, serving first as an analyst at the National Air and Space Intelligence Center, and then as a program manager at the Sensors Directorate. In 2005, he returned to graduate school at Caltech, completing his Ph.D. in Control and Dynamical Systems in 2012. His thesis research focused on robot navigation in dense human crowds, the result of which was a probabilistic model of human robot cooperation and a 6 month case study in Caltech’s student cafeteria. Pete has since worked on fully autonomous and shared control factory robots at Boeing, and on the “human machine teaming” problem for defense applications (e.g., assistive analytics and UAV navigation in congested airspaces). He was a best paper finalist at ICRA 2013 for his work on autonomous crowd navigation.
02/09/2018 Amir Rubin
Paracosm
SLAM and 3D-reconstruction for Real World Use Cases
Abstract: Occipital is a computer vision company developing SLAM and 3D-mapping solutions for both consumer and professional users. This talk gives insight into the tech stack used by a leading computer vision company, our approach to developing high-performance CV algorithms that must satisfy customer needs while running on low-power hardware, and how our CV engineers collaborate across multiple time zones to build solutions for customer problems. We'll review examples of real-world customer use cases that revolve around SLAM and 3D-reconstruction.

Speaker’s Bio: Amir Rubin co-founded his first company, Prioria Robotics, after graduated from University of Florida with a BS in computer engineering in 2003. While at Prioria he developed embedded vision-based control+navigation systems for small UAVs. In 2011 he joined Shadow Health, a UF spin-out that develops education training+3D simulation software, as employee #1. During his time leading engineering and product development at Shadow, the company grew to 40 employees (and is currently 80 people). In 2013, Amir co-founded Paracosm, a 3D-mapping company based in Gainesville that was acquired in 2017 by Occipital. Paracosm currently operates as a division of Occipital developing 3D LiDAR mapping solutions for heavy industry.
02/16/2018 Emel Demircan
California State University
Human Movement Understanding
Abstract: Human motor performance is a key area of investigation in biomechanics, robotics, and machine learning. Understanding human neuromuscular control is important to synthesize prosthetic motions and ensure safe human-robot interaction. Building controllable biomechanical models through modeling and algorithmic tools from both robotics and biomechanics increases our scientific understanding of musculoskeletal mechanics and control. The resulting models can consequently help quantifying the characteristics of a subject’s motion and in designing effective treatments, like predictive simulations and motion training. My objective is to explore how neural control dictates motor performance in humans by developing a computational framework that enables robotics-based control and simulation of the human musculoskeletal system. In this talk, I will present the modeling, control, and simulation components of this new framework with examples of applications in rehabilitation, robotics, and athletics. The presented framework has promise to advance the field of rehabilitation robotics by deepening our scientific understanding of human motor performance dictated by musculoskeletal physics and neural control. Automated and real-time motion improvement and retraining, facilitated with such frameworks, promise to transform the neuromuscular health, longevity, and independence of millions of people, utilizing a cost effective approach.

Speaker’s Bio: Dr. Emel Demircan is an Assistant Professor at the Departments of Mechanical and Aerospace Engineering and Biomedical Engineering at California State University, Long Beach. Dr. Demircan obtained her Ph.D in Mechanical Engineering from Stanford University in 2012. She was a postdoctoral scholar at Stanford from 2012 to 2014 and a visiting assistant professor at University of Tokyo from 2014 to 2015. She was also a part-time scientist at Lucile Salter Packard Children's Hospital Gait Analysis Lab at Stanford University. Dr. Demircan's research focuses on the application of dynamics and control theory for the simulation and analysis of biomechanical and robotic systems. Her research interests include cyber-physical systems, rehabilitation robotics, sports biomechanics, natural motion generation in humanoid robotics, and human motion synthesis. Dr. Demircan is an OpenSim Fellow; and the founder & co-chair of the IEEE RAS Technical Committee on "Human Movement Understanding." She is actively collaborating with clinical, athletic, and industrial partners; and she is involved in professional and educational activities within the IEEE Robotics Society.
02/23/2018 Kris Hauser
Duke University
The Space of Spaces: Understanding the Structure Between Motion Planning Problems
Abstract: Motion planning is the problem of generating continuous motions to achieve certain goals while respecting certain constraints, and is a key component in intelligent robots. The vast majority of motion planning work focuses on algorithms for solving individual problem instances. For several years my research has been raising the question, “What is the structure between motion planning problem instances?” (and of course, “how can it be exploited?”) By embedding a deeper understanding of this structure, we can design planners that reason about changes to constraints, plan for several related problems simultaneously, or use experience to adapt solutions between problems. These approaches lead to faster and higher quality plans, which are in some cases fast enough to be suitable for inner loops of feedback controllers. Moreover, we are able to design machine learning models that embed structural knowledge to learn optimal controllers with substantially higher accuracy than black box approaches (e.g., deep neural networks).

Speaker’s Bio: Kris Hauser is an Associate Professor at the Pratt School of Engineering at Duke University with a joint appointment in the Electrical and Computer Engineering Department and the Mechanical Engineering and Materials Science Department. He received his PhD in Computer Science from Stanford University in 2008, bachelor's degrees in Computer Science and Mathematics from UC Berkeley in 2003, and worked as a postdoctoral fellow at UC Berkeley. He then joined the faculty at Indiana University from 2009-2014, where he started the Intelligent Motion Lab, and began his current position at Duke in 2014. He is a recipient of a Stanford Graduate Fellowship, Siebel Scholar Fellowship, Best Paper Award at IEEE Humanoids 2015, and an NSF CAREER award. His research interests include robot motion planning and control, semiautonomous robots, and integrating perception and planning, as well as applications to intelligent vehicles, robotic manipulation, robot-assisted medicine, and legged locomotion.
03/02/2018 Marco Pavone
Stanford University
Planning and Decision Making for Autonomous Spacecraft and Space Robots
Abstract: In this talk I will present planning and decision-making techniques for safely and efficiently maneuvering autonomous aerospace vehicles during proximity operations, manipulation tasks, and surface locomotion. I will first address the "spacecraft motion planning problem," by discussing its unique aspects and presenting recent results on planning under uncertainty via Monte Carlo sampling. I will then turn the discussion to higher-level decision making; in particular, I will discuss an axiomatic theory of risk and how one can leverage such a theory for a principled and tractable inclusion of risk-awareness in robotic decision making, in the context of Markov decision processes and reinforcement learning. Throughout the talk, I will highlight a variety of space-robotic applications my research group is contributing to (including the Mars 2020 and Hedgehog rovers, and the Astrobee free-flying robot), as well as applications to the automotive and UAV domains. This work is in collaboration with NASA JPL, NASA Ames, NASA Goddard, and MIT.

Speaker’s Bio: Dr. Marco Pavone is an Assistant Professor of Aeronautics and Astronautics at Stanford University, where he is the Director of the Autonomous Systems Laboratory and Co-Director of the Center for Automotive Research at Stanford. Before joining Stanford, he was a Research Technologist within the Robotics Section at the NASA Jet Propulsion Laboratory. He received a Ph.D. degree in Aeronautics and Astronautics from the Massachusetts Institute of Technology in 2010. His main research interests are in the development of methodologies for the analysis, design, and control of autonomous systems, with an emphasis on autonomous aerospace vehicles and large-scale robotic networks. He is a recipient of a Presidential Early Career Award for Scientists and Engineers, an ONR YIP Award, an NSF CAREER Award, a NASA Early Career Faculty Award, a Hellman Faculty Scholar Award, and was named NASA NIAC Fellow in 2011. His work has been recognized with best paper nominations or awards at the Field and Service Robotics Conference, at the Robotics: Science and Systems Conference, and at NASA symposia.
03/09/2018 Yu Xiang
UW/NVidia
Perceiving the 3D World from Images and Videos
Abstract: With recent advances in artificial intelligence, we have witnessed the deployment of AI systems that are capable of improving our daily lives such as the Amazon checkout-free shop and self-driving cars. However, deploying a personal robot that is able to assist people in accomplishing real world tasks is still very challenging. The difficulty lies in the complexity of the 3D world we live in, where a robot may encounter thousands of objects, different scenes and human activities. For a robot to safely operate in such an environment, it needs to effectively extract, represent and interpret information about the 3D environment from different sensory data. In this talk, I will present my efforts towards designing intelligent visual models that perceive the 3D world from images and videos. I will start by describing a novel 3D scene understanding framework that jointly reconstructs the geometry of a scene and recognizes objects in the scene. Then, I will elaborate on the design of a new convolutional neural network for recognizing the 3D location and 3D pose of objects in cluttered scenes. The network is very robust to occlusions between objects and handles symmetric objects elegantly. I will conclude this talk by demonstrating that our methods for 3D object recognition and scene understanding provide useful information for intelligent systems to conduct tasks in the real world such as in autonomous driving and robot manipulation.

Speaker’s Bio: Yu Xiang is a Robotics Research Scientist at Nvidia. He received his Ph.D. in electrical engineering from the University of Michigan at Ann Arbor in 2016 advised by Prof. Silvio Savarese. He was a postdoctoral researcher with Prof. Dieter Fox in Computer Science & Engineering at the University of Washington from 2016 to 2017 and was a visiting student researcher in the artificial intelligence lab at Stanford University from 2013 to 2016. He received M.S. degree and B.S. degree both in computer science from Fudan University in 2010 and 2007, respectively. His research interests primarily focus on computer vision and perception for robotics, with emphasize on studying how can an intelligent system or a robot understand its 3D environment from sensing.

Details of previous Robotics Colloquia can be found here.