Companion robot Moflin learns to comfort via local model and JEPA world model
Stefania_druga · x · 2026-10-27
A social robot demo using Casio's Moflin companion robot explores whether a robot can learn what comforts someone living alone: a local model classifies touch from camera motion and appearance, while a JEPA adapter on frozen DINO features predicts likely next interactions to deliver personalized comfort.
The author also describes the MorphoBot project, which co-evolves robot body, controllers and world models around a task, using simulation to explore designs and real-world feedback to refine them.
More from Embodied
- Noetix Robotics, backed by CATL, reportedly files for Hong Kong IPO — pstAsiatech · 2026-10-27
- Ex-Microsoft exec Mikhail Parakhin slams Tesla FSD for repeating the same mistakes — MParakhin · 2026-10-27
- Meta's InteractiveWorld Benchmark Shows MLLMs Still Far from Reliable Physical Assistants — meta · 2026-10-27
- 8.3M words transcribed across nearly 5,000 conversations on MIRA smart glasses — AnhPhuNguyen1 · 2026-10-27
- Surface Laptop Ultra review: impressive local AI but bandwidth limited — draginol · 2026-10-27
- Feather Robotics sells a $29,990 humanoid platform, betting on anti-overengineering — darian314 · 2026-10-27