Select a calendar:
Filter December Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for December
-
Is Data All You Need?: Large Robot Action Models and Good Old Fashioned Engineering
Thu, Dec 05, 2024 @ 03:00 PM - 05:15 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ken Goldberg, Ph.D., William S. Floyd Distinguished Chair of Engineering - UC Berkeley
Talk Title: Is Data All You Need?: Large Robot Action Models and Good Old Fashioned Engineering
Abstract: Enthusiasm has been skyrocketing for humanoids based on recent advances in "end-to-end" large robot action models. Initial results are promising, and several collaborative efforts are underway to collect the needed demonstration data. But is data really all you need?
Although end-to-end Large Vision, Language, Action (VLA) Models have potential to generalize and reliably solve all problems in robotics, initial results have been mixed[1]. It seems likely that the size of the VLA state space and dearth of available demonstration data, combined with challenges in getting models to generalize beyond the training distribution and the inherent challenges in interpreting and debugging large models, will make it difficult for pure end-to-end systems to provide the kind of robot performance that investors expect in the near future.
In this presentation, I share my concerns about current trends in robotics, including task definition, data collection, and experimental evaluation. I propose that to reach expected performance levels, we will need "Good Old Fashioned Engineering (GOFE)" – modularity, algorithms, and metrics. I'll present MANIP[2], a modular systems architecture that can integrate learning with well-established procedural algorithmic primitives such as Inverse Kinematics, Kalman Filters, RANSAC outlier rejection, PID modules, etc. I’ll show how we are using MANIP to improve performance on robot manipulation tasks such as grasping, cable untangling, surgical suturing, motion planning, and bagging, and propose open directions for research.
Presented at:
>Stanford Robotics Seminar, 19 April, 2024 4-min video clip
>Berkeley AI Research (BAIR) Seminar, 24 April, 2024
>IEEE ICRA Workshop, Yokohama Japan, 16 May 2024
>Berkeley Sky Lab Retreat Keynote, Santa Cruz, 29 May 2024
>Amazon Lab 126, Sunnyvale, CA, 18 June 2024
>Apple Park, Cupertino, CA, 24 July 2024
>Toyota Research Lab, San Jose, CA, 31 July 2024
>ICRA@40 Keynote, Rotterdam, 23 Sept 2024
>WAFR Keynote, Chicago, 7 Oct 2024
>Univ of Southern California (USC) Computer Science Distinguished Lecture Seminar, 5 Dec 2024
[1] Nishanth J. Kumar. Will Scaling Solve Robotics? The idea of solving the biggest robotics challenges by training large models is sparking debate. IEEE Spectrum. 28 May 2024.
[2] MANIP: A Modular Architecture for iNtegrating Iteractive Perception into Long-Horizon Robot Manipulation Systems. Justin Yu*, Tara Sadjadpour*, Abby O’Neill, Mehdi Khfifi, Lawrence Yunliang Chen, Richard Cheng, Ashwin Balakrishna, Thomas Kollar, Ken Goldberg. IEEE/RSJ International Conference on Robots and Systems (IROS), Abhu Dhabi, UAE. Oct 2024. Paper
**LOCATION CHANGE**
GINSBURG COMPUTATION HALL (GCS)
AUDITORIUM
This lecture satisfies requirements for CSCI 591: Research Colloquium.
This lecture will be presented as a HYBRID presentation, but will not be recorded.
Zoom details below: https://usc.zoom.us/j/94205149719?pwd=LjETcnHLvCzyDbB6LjjxfknZaab3Dm.1
Meeting ID: 942 0514 9719 | Passcode: 400232
Biography: Ken Goldberg is William S. Floyd Distinguished Chair of Engineering at UC Berkeley and Chief Scientist of Ambi Robotics and Jacobi Robotics. Ken leads research in robotics and automation: grasping, manipulation, and learning for applications in warehouses, industry, homes, agriculture, and robot-assisted surgery. He is Professor of IEOR with appointments in EECS and Art Practice. Ken is Chair of the Berkeley AI Research (BAIR) Steering Committee (60 faculty) and is co-founder and Editor-in-Chief emeritus of the IEEE Transactions on Automation Science and Engineering (T-ASE). He has published ten US patents, over 400 refereed papers, and presented over 600 invited lectures to academic and corporate audiences.
http://goldberg.berkeley.edu
Host: USC Thomas Lord Department of Computer Science
More Info: https://forms.gle/w1r6Yo3se3WU8Bou7
Webcast: https://usc.zoom.us/j/94205149719?pwd=LjETcnHLvCzyDbB6LjjxfknZaab3Dm.1Location: Ginsburg Hall (GCS) - Auditorium
WebCast Link: https://usc.zoom.us/j/94205149719?pwd=LjETcnHLvCzyDbB6LjjxfknZaab3Dm.1
Audiences: Everyone Is Invited
Contact: USC Thomas Lord Department of Computer Science
Event Link: https://forms.gle/w1r6Yo3se3WU8Bou7
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
-
World models beyond autoregressive next state prediction
Mon, Dec 09, 2024 @ 03:00 PM - 04:00 PM
Ming Hsieh Department of Electrical and Computer Engineering, Thomas Lord Department of Computer Science, USC School of Advanced Computing
Conferences, Lectures, & Seminars
Speaker: Abhishek Gupta, Ph.D., Assistant Professor of Computer Science and Engineering, Paul G. Allen School at the University of Washington
Talk Title: World models beyond autoregressive next state prediction
Series: CSC@USC/CommNetS-MHI Seminar Series
Abstract: Learned models of system dynamics provide an appealing way of predicting the future outcomes in a system, enabling downstream usage for planning or off-policy evaluation in applications such as robotics. However, the prevalent paradigm of autoregressive, next-state prediction in learning dynamics models is challenging to scale to environments with high dimensional observations and long horizons. In this talk, I will present alternative techniques for model learning that go beyond directly predicting next states. Firstly, we will discuss a reconstruction-free class of models that go beyond next-observation prediction by learning the evolution of task-directed latent representations for high dimensional observation spaces. We will then show how this can be generalized to learning a new class of models that avoid autoregressive prediction altogether by directly modeling long-term cumulative outcomes, while remaining task agnostic. In doing so, this talk will propose alternative ways of thinking about model learning that retain the benefits of transferability and efficiency from model-based RL, while going beyond next-state prediction.
Biography: Abhishek Gupta is an assistant professor of computer science and engineering at the Paul G. Allen School at the University of Washington. Prior to joining University of Washington, he was a post-doctoral scholar at MIT, collaborating with Russ Tedrake and Pulkit Agarwal. He completed his Ph.D. at UC Berkeley working with Pieter Abbeel and Sergey Levine, building systems that can leverage reinforcement learning algorithms to solve robotics problems. He is interested in research directions that enable directly performing reinforcement learning directly in the real world — reward supervision in reinforcement learning, large scale real world data collection, learning from demonstrations, and multi-task reinforcement learning. He has also spent time at Google Brain. He is a recipient of the NDSEG and NSF graduate research fellowships, and several of his works have been presented as spotlight presentations at top-tier machine learning and robotics conferences.
Host: Erdem Biyik
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Erdem Biyik
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
