Drift Lipschitz budget K yields 1/K value approximation for diffusion policies, with matching lower bound, and finite-sample rates Õ(n^{-2/(m+6)}) (generic) or Õ(n^{-2/(m+4)}) (dissipative).
https://github
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
This work introduces DiffuseLoco, a framework for training multi-skill diffusion-based policies for dynamic legged locomotion from offline datasets, enabling real-time control of diverse skills on robots in the real world. Offline learning at scale has led to breakthroughs in computer vision, natural language processing, and robotic manipulation domains. However, scaling up learning for legged robot locomotion, especially with multiple skills in a single policy, presents significant challenges for prior online reinforcement learning methods. To address this challenge, we propose a novel, scalable framework that leverages diffusion models to directly learn from offline multimodal datasets with a diverse set of locomotion skills. With design choices tailored for real-time control in dynamical systems, including receding horizon control and delayed inputs, DiffuseLoco is capable of reproducing multimodality in performing various locomotion skills, zero-shot transfer to real quadrupedal robots, and it can be deployed on edge computing devices. Furthermore, DiffuseLoco demonstrates free transitions between skills and robustness against environmental variations. Through extensive benchmarking in real-world experiments, DiffuseLoco exhibits better stability and velocity tracking performance compared to prior reinforcement learning and non-diffusion-based behavior cloning baselines. The design choices are validated via comprehensive ablation studies. This work opens new possibilities for scaling up learning-based legged locomotion controllers through the scaling of large, expressive models and diverse offline datasets.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
SMP turns pre-trained motion diffusion models into task-agnostic, reusable reward functions via score distillation sampling, enabling style-specific and composable motion priors for humanoid control without retraining per task.
AID trains diffusion policies via behavior cloning on existing MAIPP planners followed by RL fine-tuning to achieve faster execution and higher information gain in multi-agent coordination.
NavOL collects expert trajectory labels online from a global planner during policy rollouts in simulation to train a diffusion navigation policy, mitigating distribution shift and improving performance on visual navigation tasks.
Diff-CAST replaces GAN discriminators with diffusion-based priors and adds symmetric command conditioning plus constrained RL to enable versatile, drift-free, and hardware-safe quadruped locomotion.
PODPO is a likelihood-free generative policy optimization method for online RL that steers actions to high-return regions using only positive-advantage samples and local contrastive drifting.
DynaMOMA uses an anchor-based diffusion predictor for temporally consistent grasp trajectories and feeds encoded features to an anticipation-guided whole-body RL policy, reporting strong simulation performance and real-world generalizability for dynamic mobile grasping.
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.
citing papers explorer
-
Expressivity and Statistical Trade-offs in Diffusion Policy Learning
Drift Lipschitz budget K yields 1/K value approximation for diffusion policies, with matching lower bound, and finite-sample rates Õ(n^{-2/(m+6)}) (generic) or Õ(n^{-2/(m+4)}) (dissipative).
-
Unleashing Infinite Motion: Scaling Expressive Quadrupedal Motion via Generative Video Priors
Uni-Mo generates 7,488 language-annotated quadruped motions via LLM prompts and video diffusion, lifts them to 3D trajectories, and trains policies achieving 96.7% real-robot success on 392 sampled motions.
-
SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control
SMP turns pre-trained motion diffusion models into task-agnostic, reusable reward functions via score distillation sampling, enabling style-specific and composable motion priors for humanoid control without retraining per task.
-
AID: Agent Intent from Diffusion for Multi-Agent Informative Path Planning
AID trains diffusion policies via behavior cloning on existing MAIPP planners followed by RL fine-tuning to achieve faster execution and higher information gain in multi-agent coordination.
-
NavOL: Navigation Policy with Online Imitation Learning
NavOL collects expert trajectory labels online from a global planner during policy rollouts in simulation to train a diffusion navigation policy, mitigating distribution shift and improving performance on visual navigation tasks.
-
Constraint-Aware Diffusion Priors for High-Fidelity and Versatile Quadruped Locomotion
Diff-CAST replaces GAN discriminators with diffusion-based priors and adds symmetric command conditioning plus constrained RL to enable versatile, drift-free, and hardware-safe quadruped locomotion.
-
Positive-Only Drifting Policy Optimization
PODPO is a likelihood-free generative policy optimization method for online RL that steers actions to high-return regions using only positive-advantage samples and local contrastive drifting.
-
DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects
DynaMOMA uses an anchor-based diffusion predictor for temporally consistent grasp trajectories and feeds encoded features to an anticipation-guided whole-body RL policy, reporting strong simulation performance and real-world generalizability for dynamic mobile grasping.
-
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.