TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation
- URL: http://arxiv.org/abs/2606.22998v2
- Date: Tue, 23 Jun 2026 07:19:46 GMT
- Title: TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation
- Abstract summary: We introduce TEXEDO, a test-time scaling framework for humanoid motion generation.<n>It improves motion quality without requiring a stronger underlying generator.<n>We show it consistently improves both tracking fidelity and text alignment.
- Score: 48.72797830886802
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Text-conditioned motion generation is a promising interface for programming humanoid robots, yet current generators are often trained on human motion datasets retargeted to robot morphologies. Although such data provides rich semantic and kinematic priors, it fails to capture the nuances of whole-body tracking controllers, including balance, contact dynamics, actuation limits, and controller-specific failure modes. As a result, generated motions can be semantically plausible but difficult or impossible for the robot to execute. We introduce TEXEDO, a test-time scaling framework for humanoid motion generation that improves motion quality without requiring a stronger underlying generator. Given a text prompt, TEXEDO samples multiple candidate motions from a pretrained text-conditioned generator and selects the best motion that is both executable and task-aligned. The reward model combines a dynamic feasibility verifier, distilled from whole-body tracking rollouts to predict physical executability, with a semantic alignment verifier that measures text-motion alignment in a learned co-embedding space. Our pipeline treats dynamic feasibility as a hard constraint and semantic alignment as the selection objective within the feasible set. Through large-scale simulation studies and real-world deployment on a Unitree G1 humanoid robot, we show that TEXEDO consistently improves both tracking fidelity and text alignment. These results demonstrate that grounded verification is an effective path toward deployable language-guided humanoid motion generation. Project website: https://jianuocao.github.io/TEXEDO/
Related papers
- CLAW: Composable Language-Annotated Whole-body Motion Generation [55.99805728566105]
We present CLAW, a pipeline for scalable generation of language-annotated whole-body motion data.<n>CLAW composes motion primitives from a kinematic planner, parameterized by movement, heading, speed, pelvis height, and duration.<n>A low-level controller tracks these references in MuJoCo simulation, yielding physically grounded trajectories.
arXiv Detail & Related papers (2026-04-13T10:02:04Z) - RoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids [20.796118584632904]
We present a unified latent-driven framework that bridges natural language and whole-body locomotion.<n>Our framework provides a practical path toward deployable text-guided humanoid intelligence.
arXiv Detail & Related papers (2026-03-18T17:02:56Z) - PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking [23.96905373874686]
We present PhyGile, a unified framework that closes the loop between robot-native motion generation and inference.<n>We train the GMT controller with a curriculum-based mixture-of-experts scheme, followed by post-training on unlabeled motion data to improve robustness over large-scale robot motions.<n>PhyGile expands the frontier of text-driven humanoid control, enabling stable tracking of agile, highly difficult whole-body motions.
arXiv Detail & Related papers (2026-03-13T06:43:44Z) - TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control [62.93681680333618]
TextOp is a real-time text-driven humanoid motion generation and control framework.<n>It supports streaming language commands and on-the-fly instruction modification during execution.<n>By bridging interactive motion generation with robust whole-body control, TextOp unlocks free-form intent expression.
arXiv Detail & Related papers (2026-02-07T08:42:11Z) - From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance [55.31807046722006]
Existing language-guided humanoid pipelines are cumbersome and untrustworthy.<n>We present RoboGhost, a language-free framework that conditions humanoid policies on language-grounded motion latents.<n>We show that RoboGhost substantially reduces deployment latency, improves success rates and tracking precision, and produces smooth, semantically aligned humanoids.
arXiv Detail & Related papers (2025-10-16T17:57:47Z) - KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills [58.73043119128804]
This paper presents a physics-based humanoid control framework, aiming to master highly-dynamic human behaviors such as Kungfu and dancing.<n>For motion processing, we design a pipeline to extract, filter out, correct, and retarget motions, while ensuring compliance with physical constraints.<n>For motion imitation, we formulate a bi-level optimization problem to dynamically adjust the tracking accuracy tolerance.<n>In experiments, we train whole-body control policies to imitate a set of highly-dynamic motions.
arXiv Detail & Related papers (2025-06-15T13:58:53Z) - RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control [32.37239524019001]
This paper focuses on translating text-driven human motions into executable actions for humanoid robots.<n>Existing text-to-motion generation methods produce kinematically or physically infeasible motions unsuitable for real-world deployment.<n>We propose Reinforcement Learning from Physical Feedback, a novel framework that integrates physics-aware motion evaluation with text-conditioned motion generation.
arXiv Detail & Related papers (2025-06-15T08:39:49Z) - TLControl: Trajectory and Language Control for Human Motion Synthesis [68.09806223962323]
We present TLControl, a novel method for realistic human motion synthesis.
It incorporates both low-level Trajectory and high-level Language semantics controls.
It is practical for interactive and high-quality animation generation.
arXiv Detail & Related papers (2023-11-28T18:54:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.