My lab will be heading over to #RSS2025 ! If you are interested in contact-aware information theory for robotics, reach out to @Hrishikesh913 . @haoxiang_you Yilang Liu, and Christian Hughes will be around to talk about their work on efficient robot learning and control!.

Check out paper in the repost for more info and results!!!.

Think of the contact aware fisher information as a sensitivity measure that we can directly optimize wrt control-contact decisions to help robots learn about their environment more effectively!.

Taking a Taylor expansion over parameters yields the contact aware Fisher information matrix that quantifies how useful contact mechanics are to understanding physical constants!!.

We posed a contact aware max likelihood problem where the goal was to correlate robot control, sensing to physical (contact) constraints.

Robots 🤖 make and break contact all the time. So what quantifies usefulness of contacts for a robot’s understanding of its environment? Check out our latest #RSS2025 paper on contact aware fisher information maximization!! 🧵below—-.

RT @TCOptRob: [Announcement] All of our seminar series videos are now available on YouTube. Happy watching!.

*clever -- fun typo 🔪.

Doing some analysis, we find observation-only gradient information actually made policy updates more challenging. Removing this term led to interesting connections with student-teacher policy distillation and huge computational gains! check out @haoxiang_you 's post for more info.

We took a good hard look at the analytical policy gradient going from vision to state to dynamics to policy and realize it is separable!! -- one part only has state/dynamics info the remaining is observation-only.

The idea was quite simple, but cleaver --- we are very good/fast at trajectory opt with diff sims, why can't the same be true for visual policy learning?.

🚀🚀🚀 Check out this work out of my lab on accelerating visual-policy learning by exploiting computational structures in diff sims!! 🧵 below on why its exciting!!.

Check out the latest work by my students @haoxiang_you and Yilang Liu! ~~~Thread coming soon~~~.

RT @haoxiang_you: 🚀 Excited to introduce — a computationally efficient approach for learning visual policies!.⚡ Tra….

Elena Wittemyer will present Multi-Agent Ergodic Exploration under Smoke-Based, Time-Varying Sensor Visibility Constraints, WeAT10.TLDR; Ergodic search with a smoke-based fluid solver to inform search of visibility constraints ( search in forest fires).

Christian Hughes will present Ergodic Trajectory Optimization on Generalized Domains Using Maximum Mean Discrepancy, ThBT19 .TLDR; A novel metric for ergodic trajectory optimization that only requires domain samples useful for coverage guarantees for SLAM.

Dayi Dong will present Ergodic Exploration over Meshable Surfaces, ThBT19 TLDR; Demonstrates ergodic trajectory optimization over mesh domains via the Laplace-Beltrami operator.

My lab and I will be @ICRA in Atlanta showcasing three papers on ergodic search! .more details below in comments!

RT @h_ravichandar: 📢ICRA workshop on structured robot learning with awesome speakers and an exciting program! . We will discuss current sol….

@h_ravichandar.