Learning to Predict and to Act - Exploring Structure in World Models and Latent Spaces

Add to your list(s) Download to your calendar using vCal

• Ingmar Posner, Oxford University
• Thursday 07 March 2024, 14:00-15:00
• JDB Seminar Room, Department of Engineering and online (Zoom).

If you have a question about this talk, please contact Fulvio Forni.

In robotics, the ability to learn predictive models of systems and environments in an unsupervised, data-driven way has emerged as a promising research direction. World models in particular harbour the potential to serve as an interactive experience store for autonomous agents, enabling direct trajectory optimisation as well as model-based learning in imagination. In this talk I will describe our recent work in creating robust and versatile world models. In particular, I will demonstrate that causally inspired inductive biases provide sufficient structure to achieve efficient adaptation to intervened environments. I will then demonstrate that the structure encoded in a learnt latent space already provides a powerful and intuitive way to disentangle and manipulate task-relevant factors of variation. I will describe how this structure can be exploited to capture a purely data-driven model of complex robot platforms and demonstrate that this not only casts a novel light on affordance learning, but also reveals a framework capable of learning a versatile unified representation for quadruped locomotion deployable in the real-world.

The seminar will be held in the JDB Seminar Room, Department of Engineering, and online (zoom): https://newnham.zoom.us/j/92544958528?pwd=YS9PcGRnbXBOcStBdStNb3E0SHN1UT09

This talk is part of the CUED Control Group Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• CUED Control Group Seminars
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge University Engineering Department Talks
• Cambridge talks
• Centre for Smart Infrastructure & Construction
• Chris Davis' list
• Computational Continuum Mechanics Group Seminars
• Featured lists
• Information Engineering Division seminar list
• Interested Talks
• JDB Seminar Room, Department of Engineering and online (Zoom)
• School of Technology
• Signal Processing and Communications Lab Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.