RoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids

• URL: http://arxiv.org/abs/2603.17927v2
• Date: Thu, 19 Mar 2026 08:42:09 GMT
• Title: RoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids
• Abstract summary: 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.
• Score: 20.796118584632904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While generative models have become effective at producing human-like motions from text, transferring these motions to humanoid robots for physical execution remains challenging. Existing pipelines are often limited by retargeting, where kinematic quality is undermined by physical infeasibility, contact-transition errors, and the high cost of real-world dynamical data. We present a unified latent-driven framework that bridges natural language and whole-body humanoid locomotion through a retarget-free, physics-optimized pipeline. Rather than treating generation and control as separate stages, our key insight is to couple them bidirectionally under physical constraints.We introduce a Physical Plausibility Optimization (PP-Opt) module as the coupling interface. In the forward direction, PP-Opt refines a teacher-student distillation policy with a plausibility-centric reward to suppress artifacts such as floating, skating, and penetration. In the backward direction, it converts reward-optimized simulation rollouts into high-quality explicit motion data, which is used to fine-tune the motion generator toward a more physically plausible latent distribution. This bidirectional design forms a self-improving cycle: the generator learns a physically grounded latent space, while the controller learns to execute latent-conditioned behaviors with dynamical integrity.Extensive experiments on the Unitree G1 humanoid show that our bidirectional optimization improves tracking accuracy and success rates. Across IsaacLab and MuJoCo, the implicit latent-driven pipeline consistently outperforms conventional explicit retargeting baselines in both precision and stability. By coupling diffusion-based motion generation with physical plausibility optimization, our framework provides a practical path toward deployable text-guided humanoid intelligence.

Related papers

• Synthetic-to-Real Translation for Class-Agnostic Motion Prediction [64.55842058684583]
  We explore the potential of synthetic-to-real translation for motion prediction (SRMP)<n>We propose a novel approach integrating a motion knowledge translation framework with two key components.<n>We present a physically-based pipeline for generating Motion4D, the first synthetic 4D LiDAR dataset tailored for SRMP research.
  arXiv  Detail & Related papers  (2026-07-07T14:19:22Z)
• TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation [48.72797830886802]
  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.
  arXiv  Detail & Related papers  (2026-06-22T08:14:35Z)
• PhysDrift: Bridging the Embodiment Gap in Humanoid Co-Speech Motion Generation [31.168201029670865]
  We introduce PhysDrift, an embodiment-aware co-speech motion framework that predicts humanoid joint trajectories from speech without relying on human-body representations.<n>Experiments and real-world humanoid deployment demonstrate that embodiment-aware robot-native generation substantially improves speech-motion alignment, physical plausibility, motion smoothness, inference efficiency, and real-time interaction capability.
  arXiv  Detail & Related papers  (2026-06-18T08:31:58Z)
• Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation [16.622175523077917]
  Co-manipulation requires multiple humans to synchronize their motions with a shared object.<n>Most existing motion generation approaches fail to account for payload-induced dynamics.<n>We propose a flow-matching framework that ensures the generated co-manipulation motions align with the intended goals.
  arXiv  Detail & Related papers  (2026-04-22T08:31:40Z)
• PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization [55.25800735159481]
  Whole-Body Controller (WBC) converts diffusion-generated motions into executable trajectories.<n>WBC trajectories become compliant with physics, but they may expose substantial deviations from original motion.<n>We propose PhysMoDPO, a Direct Preference Optimization framework.<n> PhysMoDPO results in significant improvements when applied to zero-shot motion transfer in simulation and for real-world deployment on a G1 humanoid robot.
  arXiv  Detail & Related papers  (2026-03-13T17:59:59Z)
• SPARK: Skeleton-Parameter Aligned Retargeting on Humanoid Robots with Kinodynamic Trajectory Optimization [9.553570391005257]
  Human motion provides rich priors for training general-purpose humanoid control policies, but raw demonstrations are often incompatible with a robot's kinematics and dynamics.<n>We present a two-stage pipeline for generating natural and dynamically feasible motion references from task-space human data.
  arXiv  Detail & Related papers  (2026-03-12T03:03:14Z)
• AdaMorph: Unified Motion Retargeting via Embodiment-Aware Adaptive Transformers [49.796014934503184]
  We present a unified neural framework that enables a single model to adapt human motion to diverse robot morphologies.<n> Experimental results on 12 distinct humanoid robots demonstrate that AdaMorph effectively control across heterogeneous topologies.
  arXiv  Detail & Related papers  (2026-01-12T07:39:38Z)
• 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)
• PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation [35.563978243352764]
  We introduce physical mapping, integrated throughout the human interaction generation pipeline.<n>Specifically, motion imitation within a physics-based simulation environment is used to project target motions into a physically valid space.<n>Experiments show our method achieves impressive results in generated human motion quality, with a 3%-89% improvement in physical fidelity.
  arXiv  Detail & Related papers  (2025-06-09T06:04:49Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)

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.