Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Omnigrasp: Grasping Diverse Objects with Simulated Humanoids
Authors: Zhengyi Luo, Jinkun Cao, Sammy Christen, Alexander Winkler, Kris Kitani, Weipeng Xu
NeurIPS 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present a method for controlling a simulated humanoid to grasp an object and move it to follow an object s trajectory. To demonstrate the capabilities of our method, we show state-of-the-art success rates in following object trajectories and generalizing to unseen objects. Table 1: Quantitative results on object grasp and trajectory following on the GRAB dataset. |
| Researcher Affiliation | Collaboration | Zhengyi Luo1,2 Jinkun Cao1 Sammy Christen2,3 Alexander Winkler2 Kris Kitani1,2 Weipeng Xu2 1Carnegie Mellon University; 2Reality Labs Research, Meta; 3ETH Zurich |
| Pseudocode | Yes | Algo 1: Learn Omnigrasp |
| Open Source Code | No | Code and models will be released. |
| Open Datasets | Yes | We use the GRAB [71], Oak Ink [86], and OMOMO [34] to study grasping small and large objects. |
| Dataset Splits | Yes | We split them into 1330 objects for training, 185 for validation, and 185 for testing. |
| Hardware Specification | Yes | We train Omnigrasp for three days collecting around 10^9 samples on a Nvidia A100 GPU. |
| Software Dependencies | No | Simulation is conducted in Isaac Gym [46], where the policy is run at 30 Hz and the simulation at 60 Hz. |
| Experiment Setup | Yes | Simulation is conducted in Isaac Gym [46], where the policy is run at 30 Hz and the simulation at 60 Hz. For PULSE-X and PHC-X, each policy is a 6-layer MLP. For the grasping task, we employ a GRU [14] based recurrent policy and use a GRU with a latent dimension of 512, followed by a 3-layer MLP. Object density is 1000 kg/m3. The static and dynamic friction coefficients of the object and humanoid fingers are set to 1. For reference object trajectory, we use ϕ = 20 future frames sampled at 15Hz. For more details, please refer to Appendix C. Table 7: Hyperparameters for Omnigrasp, PHC-X, and PULSE-X. |