TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

robotics

The Manipulation Skill Declared Its Geometry First

Without new demonstrations, geometric contracts reached 88.24% pick-and-place and 75.00% average functional-task success.

Published Updated Story ID: mp-2026-09-16-014
Read the complete editionStory JSON

Summary

Without new demonstrations, geometric contracts reached 88.24% pick-and-place and 75.00% average functional-task success.

ManiSkillFormer replaces an end-to-end visuomotor policy with task-conditioned geometric contracts. Each skill declares the object keypoints, surface normals and other primitives perception must find; language-model agents generate contracts and motion templates inside human-defined skill structures. On a dual-arm robot, the authors report 88.24% zero-shot pick-and-place across eight object categories and 30 instances, 75.00% average success on unscrewing, pouring, pressing and folding, and 50% to 80% completion on three long-horizon tasks. The results are confined to the reported platform and skill library.

Why it matters

Without new demonstrations, geometric contracts reached 88.24% pick-and-place and 75.00% average functional-task success.

Limits and context

No additional limitation was separately recorded.

Key claims

  1. Without new demonstrations, geometric contracts reached 88.24% pick-and-place and 75.00% average functional-task success.

    Evidence: source-2026-09-16-014

Sources

  1. arXiv preprint 2609.16331arXiv · primary research

Corrections

No corrections have been recorded for this story.