Matheus Paiva Angarola

CS Researcher Fellow @ ICMC-USP | Research Intern @ UIUC

[Robotics Papers @OWW]

CATNAV: Cached Vision-Language Traversability for Efficient Zero-Shot Robot Navigation

Aditya Potnis, Francisco Affonso, Shreya Gummadi, Naveen Kumar Uppalapati, Girish Chowdhary
https://t.co/vplnQSBwpf [𝚌𝚜.𝚁𝙾]

[Francisco Affonso @faffonso2]

How do you get perceptive locomotion over rough terrain without brittle terrain classifiers?

Excited to share CTS-MoE, a framework for implicit terrain adaptation via Mixture-of-Experts for perceptive locomotion. No selectors or per-task policies; the policy adapts end-to-end straight from vision.

TL;DR:
→ Perception-driven routing handles diverse, discontinuous terrain implicitly; no high-level task selector or per-task policy distillation.
→ Big gains on hard tasks (climbing, gaps) under MTRL, with smooth transitions on both seen and unseen terrain.

🧵Thread: