Humanoid manipulation is improving, but the task set is still tiny
chris_j_paxton · x · 2026-07-20
A note on humanoid manipulation progress: Xiaomi reported that one older task, loading self-tapping nuts, improved from 90.2% to 98% success after four months.
The broader takeaway is that there are still very few manipulation tasks being explored at scale. Each task requires a huge amount of engineering and data collection effort, which helps explain why the set of deployed humanoid tasks remains small.
The quoted thread also lists common humanoid tasks seen across different robots, such as:
- passage reorientation
- box packing
- clothes folding
- engine covers
- rigid pick-and-place
More from Embodied
- Musk: Cybercab certified at 165 Wh/mi, the most efficient production EV ever — elonmusk · 2026-09-11
- MKBHD goes hands-on with the first folding iPhone; $2,000 48MP selfie cam mocked — alexmacgregor__ · 2026-09-11
- NTU spin-off Ropedia launches HOMIE Gen 2 wearable system to train robots from human experience — liuziwei7 · 2026-09-11
- M.2-Oculink eGPU Link Silently Downgrades to PCIe Gen1 — Here's How to Check — El_90 · 2026-09-11
- Replit Agent in a robot builds and publishes websites autonomously via MCP — amasad · 2026-09-11
- TARS Robotics unveils embodied foundation model AWE: 15+ tasks, one model, zero retraining — heyshrutimishra · 2026-09-11