ContactBench 1.0: A Benchmark for Contact-Rich Robot Manipulation With Printable Assets
leto__jean · x · 2026-11-12
A new benchmark, ContactBench 1.0, targets contact-rich manipulation tasks like cable plugging, door unlocking, and part snapping — skills that are hard to benchmark due to diverse setups and poor reproducibility across labs.
It ships with printable physical assets, demos, and simulation. Notably, it includes objects that look identical but feel different, posing a challenge for vision-only policies and probing the need for tactile sensing.
More from Embodied
- LeRobot explains why scaling in the wild matters for physical AI — micoolcho · 2026-11-12
- RoboCap-10k: 10,000 hours of open egocentric robot data across 21 industries released — micoolcho · 2026-11-12
- Embodied First Exam: 1,156 tasks on 47 robots test coding agents, best agent solves only 34% in standard setting — burny_tech · 2026-11-12
- Apple affirms Vision Pro commitment; glasses rumored to be in secret development — Scobleizer · 2026-11-12
- AMD runs MolmoAct2 robot policy locally on a Ryzen AI Max+ 395 mini PC — DJiafei · 2026-11-12
- Open-Source CoRL Paper Browser: 2,100+ Robot Learning Papers, a Decade of Searchable Research — promptdom · 2026-11-12