HumanoidToolBench organizes 18 tasks across three scenarios and three execution levels, covering tool selection, stationary use and mobile execution.
Benchmark exposes gap between choosing tools and using them
HumanoidToolBench tests whether robots can select, grasp and deploy tools while stationary or moving, in simulation and on a real humanoid.
Big Tech
Kyochul Jang · Seohyeon Park · Ohchul Kwon · Sangjun Park · Junhyeok Choi · Seungyeop Yi · +6 more
Seoul National University · University of Massachusetts Amherst · Google Research
Research Digest··2 min read
The authors introduce an 18-task benchmark that evaluates humanoid tool use as an end-to-end process, rather than treating recognition, manipulation and locomotion separately.
Why this paper
From Google Research and 2 others
In one line
HumanoidToolBench reveals gaps between tool selection and task execution in humanoid policies.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§