Related papers: Diffusion Trajectory-guided Policy for Long-horizo…
Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vision-Language Models (DVLMs) are particularly attractive…
Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…
Recent advances in diffusion models have opened new avenues for research into embodied AI agents and robotics. Despite significant achievements in complex robotic locomotion and skills, mobile manipulation-a capability that requires the…
While imitation learning provides a simple and effective framework for policy learning, acquiring consistent actions during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action…
Planning with pretrained diffusion models has emerged as a promising approach for solving test-time guided control problems. Standard gradient guidance typically performs optimally under convex, differentiable reward landscapes. However, it…
Robots must adapt to diverse human instructions and operate safely in unstructured, open-world environments. Recent Vision-Language models (VLMs) offer strong priors for grounding language and perception, but remain difficult to steer for…
Diffusion policies (DPs) achieve state-of-the-art performance on complex manipulation tasks by learning from large-scale demonstration datasets, often spanning multiple embodiments and environments. However, they cannot guarantee safe…
Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing motor skills; instead, they expose a…
Offline reinforcement learning (RL) leverages pre-collected datasets to train optimal policies. Diffusion Q-Learning (DQL), introducing diffusion models as a powerful and expressive policy class, significantly boosts the performance of…
Most existing vision-language-action (VLA) models for robotic manipulation lack progress awareness, typically relying on hand-crafted heuristics for task termination. This limitation is particularly severe in long-horizon tasks involving…
This paper introduces Consistency Trajectory Planning (CTP), a novel offline model-based reinforcement learning method that leverages the recently proposed Consistency Trajectory Model (CTM) for efficient trajectory optimization. While…
Although multi-step generative policies achieve strong performance in robotic manipulation by modeling multimodal action distributions, they require multi-step iterative denoising at inference time. Each action therefore needs tens to…
Learning from observation (LfO) aims to imitate experts by learning from state-only demonstrations without requiring action labels. Existing adversarial imitation learning approaches learn a generator agent policy to produce state…
Long-horizon planning is crucial in complex environments, but diffusion-based planners like Diffuser are limited by the trajectory lengths observed during training. This creates a dilemma: long trajectories are needed for effective…
While generalist robot policies hold significant promise for learning diverse manipulation skills through imitation, their performance is often hindered by the long-tail distribution of training demonstrations. Policies learned on such…
We hypothesize that a key bottleneck in generalizable robot manipulation is not solely data scale or policy capacity, but a structural mismatch between current visual backbones and the physical requirements of closed-loop control. While…
Machine learning has demonstrated remarkable promise for solving the trajectory generation problem and in paving the way for online use of trajectory optimization for resource-constrained spacecraft. However, a key shortcoming in current…
Current robotic pick-and-place policies typically require consistent gripper configurations across training and inference. This constraint imposes high retraining or fine-tuning costs, especially for imitation learning-based approaches,…
Given a dataset of expert trajectories, standard imitation learning approaches typically learn a direct mapping from observations (e.g., RGB images) to actions. However, such methods often overlook the rich interplay between different…
Robotic manipulation policies are commonly initialized through imitation learning, but their performance is limited by the scarcity and narrow coverage of expert data. Reinforcement learning can refine polices to alleviate this limitation,…