News & EventsDepartment Events
Events
-
Feb3
EVENT DETAILS
less
Join the Center for Robotics and Biosystems (CRB) for the February Speaker Series
Speaker: Bradly Stadie, Assistant Professor of Statistics, Northwestern University
Date and Time: Friday, February 3 at 12:00 p.m. CT
Location: Tech B211 and Zoom
Zoom Link: https://tinyurl.com/CRBSeminar
• NU-authenticated attendees will be automatically admitted. Others, please email amy.nedoss@northwestern.edu to be admitted from the waiting room.Abstract:
How should we train reinforcement learning agents that are capable of abstract planning? One recent technique that has shown much promise is Search on the Replay Buffer. In this technique, agents treat a buffer of past experience as nodes on a graph and execute a graph search algorithm. The result of this search is a sequence of known good states that an agent can use to navigate its environment. There are two obvious shortcomings with this approach. 1) If we assume we can transition between every pair of states, then the complexity of the path planning problem is exponential in the size of the buffer. 2) Exploration over different possible paths remains a challenge, even if we prune the number of nodes.Towards overcoming these shortcomings, we introduce L3P, an algorithm for learning latent landmarks for planning. This algorithm learns landmarks in a latent space, where the distance between graph nodes is optimized to equal the number of steps it takes to transition between environmental states. We introduce a novel clustering algorithm that forces states that are close in this metric to cluster together, reducing our buffer to a few representative latent landmarks. Finally, we wrap up by considering cold diffusion approaches to solving this path planning problem. We show that sequence planning over a buffer can be recast as a diffusion model, and introduce the notion of Maximum Entropy Subgoal Skipping (MESS) to help with exploration.
Bio:
Bradly Stadie's research explores techniques for developing general machine intelligence. Recently, foundational models such as GPT-3 have provided a promising avenue towards training intelligent machines. In particular, these foundational models show that we can leverage large quantities of unsupervised data to learn a latent underlying structure of a data space. In this latent space, planning and abstract reasoning become much more tractable.
In spite of its promise, there does not currently exist a GPT-3 equivalent in Reinforcement Learning. The current leading method, learning a dynamics model to predict the agent's next state, and then using this model to bootstrap a planning or curiosity module, has proven ineffective. Dr. Stadie’s current research proposes an enticing alternative: that goal-reaching should be used as the foundational model for reinforcement learning. The idea is as follows: they want agents to learn in an unsupervised fashion how to generate and reach various goal states in their environments. They can then bootstrap from this goal-reaching ability, breaking complex goals into a series of simpler tasks. This will endow agents with the ability to plan and reason over long time horizons, an essential capacity for the emergence of general intelligence. There exists a deep relationship between unsupervised goal-reaching and imitation learning, which frequently comes up in his research. From time to time, he also uses various tools from graph search, causal inference, and generative networks.TIME Friday, February 3, 2023 at 12:00 PM - 1:00 PM
LOCATION Mechanical Engineering, B211, Technological Institute map it
CONTACT Amy Nedoss amy.nedoss@northwestern.edu EMAIL
CALENDAR Center for Robotics and Biosystems (CRB)
-
Mar27
EVENT DETAILS
lessSpring Break Ends
TIME Monday, March 27, 2023
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Mar28
EVENT DETAILS
lessSpring Classes begin 8 a.m. (Northwestern Monday: Classes scheduled to meet on Mondays meet on this day)
TIME Tuesday, March 28, 2023
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Apr5
EVENT DETAILSmore info
less
Join us on April 5 for the Grand Challenges in Robotics: Dexterity an interactive webinar discussing the state of the art and open problems for new research in robot dexterity.
Grand Challenges in Robotics: Dexterity
Conversation 4 on Robot Dexterity: Industrial Dexterity: Rate, Range, and Reliability
Wednesday, April 5, 12-1 PM CT
Moderator: Ken Goldberg, University of California, Berkeley and Ambi RoboticsPanelists: Jeff Mahler, Ambi Robotics; Matt Mason, Berkshire Grey and Carnegie Mellon University; Lauren Miller, Boston Dynamics
E-Commerce has increased dramatically due to the pandemic, putting tremendous pressure on warehouses to meet the demand. As each order and package varies, robots must dynamically and reliably plan grasps and motions at a high rate of speed for a broad range of packages. Warehouse applications are a “sweet spot” for emerging advanced in robot sensing, planning, and control; a number of companies are using “Industrial Dexterity” to handle millions of packages per day. This panel will consider the state of the art and open problems for the new research.
Register: https://northwestern.zoom.us/webinar/register/WN_J8TqZqo8SQKMQDxhpzdvJw
For more information on Grand Challenges in Robotics webinars: https://robotics.northwestern.edu/grand-challenges/
TIME Wednesday, April 5, 2023 at 12:00 PM - 1:00 PM
CONTACT Amy Nedoss amy.nedoss@northwestern.edu EMAIL
CALENDAR Center for Robotics and Biosystems (CRB)
-
Apr7
EVENT DETAILSmore info
less
Join the Center for Robotics and Biosystems (CRB) for the April Speaker Series
Speaker: Carmel Majidi, Clarence H. Adamson Professor of Mechanical Engineering, Carnegie Mellon University
Date and Time: Friday, April 7 at 12:00 p.m. CT
Location: Tech B211 and Zoom
Zoom Link: https://tinyurl.com/CRBSeminar
• NU-authenticated attendees will be automatically admitted. Others, please email amy.nedoss@northwestern.edu to be admitted from the waiting room.Abstract: Progress in soft lithography and soft materials integration have led to extraordinary new classes of soft-matter sensors, circuits, and transducers. These material technologies are composed almost entirely out of soft matter – elastomers, gels, and conductive fluids like liquid metal – and represent the building blocks for machines and electronics that are soft, flexible, and stretchable. Because of their intrinsic compliance and elasticity, such devices can be incorporated into soft, biologically-inspired robots or be worn on the body and operate continuously without impairing natural body motion. In this talk, Prof. Majidi will review recent contributions from his research group in creating soft multifunctional materials for wearable electronics and soft robotics using these emerging practices in “soft-matter engineering.” In particular, he will focus on soft robots powered using shape memory materials and soft material architectures for highly stretchable digital electronics, wearable energy harvesting, and electrically-responsive actuation. When possible, he will show how the design and operation of these soft-matter technologies can be guided by theoretical modeling methods based on principles of mechanics and discrete differential geometry. In addition to presenting his own research in the field, Prof. Majidi will also briefly review broader efforts and emerging challenges in utilizing soft multifunctional materials for applications in wearable electronics, bioelectronic interfaces, and soft robotics.
Bio: Carmel Majidi is the Clarence H. Adamson Professor of Mechanical Engineering at Carnegie Mellon University, where he leads the Soft Machines Lab. His lab is dedicated to the discovery of novel material architectures that allow machines and electronics to be soft, elastically deformable, and biomechanically compatible. Currently, Prof. Majidi's research is focused on modeling, design, and control of soft robotic systems as well as the development of multifunctional materials that exhibit unique combinations of mechanical, electrical, and thermal properties and can function as “artificial” skin, nervous tissue, and muscle. Prof. Majidi has received grants from industry and federal agencies along with early career awards from DARPA, ONR, AFOSR, and NASA to explore challenges in soft-matter engineering and robotics. Prior to arriving at CMU, he had postdoctoral appointments at Harvard and Princeton Universities and received his PhD in Electrical Engineering at UC Berkeley.
TIME Friday, April 7, 2023 at 12:00 PM - 1:00 PM
LOCATION ME B211, Technological Institute map it
CONTACT Amy Nedoss amy.nedoss@northwestern.edu EMAIL
CALENDAR Center for Robotics and Biosystems (CRB)
-
Apr21
EVENT DETAILSmore info
less
Introducing a new joint Executive Education series created by Northwestern Pritzker School of Law and McCormick School of Engineering designed to help law firm leaders, lawyers, and other legal professionals understand and make the most of the computational technologies that are transforming the delivery of legal services.
TIME Friday, April 21, 2023 at 9:00 AM - 5:30 PM
LOCATION Levy Mayer Hall map it
CONTACT Daniel W. Linna Jr. daniel.linna@law.northwestern.edu EMAIL
CALENDAR McCormick School of Engineering and Applied Science
-
May29
EVENT DETAILS
lessNo classes - Memorial Day
TIME Monday, May 29, 2023
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar
-
Jun3
EVENT DETAILS
lessSpring classes end
TIME Saturday, June 3, 2023
CONTACT Office of the Registrar nu-registrar@northwestern.edu EMAIL
CALENDAR University Academic Calendar