Humanoid Locomotion as Next Token Prediction
Reviewed by Pithpith:OKA42BU4open to challenge →
read the original abstract
We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language. Our model is a causal transformer trained via autoregressive prediction of sensorimotor trajectories. To account for the multi-modal nature of the data, we perform prediction in a modality-aligned way, and for each input token predict the next token from the same modality. This general formulation enables us to leverage data with missing modalities, like video trajectories without actions. We train our model on a collection of simulated trajectories coming from prior neural network policies, model-based controllers, motion capture data, and YouTube videos of humans. We show that our model enables a full-sized humanoid to walk in San Francisco zero-shot. Our model can transfer to the real world even when trained on only 27 hours of walking data, and can generalize to commands not seen during training like walking backward. These findings suggest a promising path toward learning challenging real-world control tasks by generative modeling of sensorimotor trajectories.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
Deep Multimodal Learning with Missing Modality: A Survey
This survey provides the first comprehensive overview of deep multimodal learning methods designed to remain robust when some input modalities are absent.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
-
HoloMotion-1 Technical Report
HoloMotion-1 trains a large Mixture-of-Experts Transformer policy on a hybrid corpus of video-reconstructed and MoCap motions to achieve robust zero-shot whole-body tracking that transfers directly to real humanoid robots.
-
HoloMotion-1 Technical Report
HoloMotion-1 trains a MoE Transformer policy on hybrid video and MoCap motion data to achieve robust zero-shot tracking that transfers directly to real humanoid robots.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.