Related papers: Masked Generative Policy for Robotic Control

A central task in control theory, artificial intelligence, and formal methods is to synthesize reward-maximizing strategies for agents that operate in partially unknown environments. In environments modeled by gray-box Markov decision…

Autonomous learning of object manipulation skills can enable robots to acquire rich behavioral repertoires that scale to the variety of objects found in the real world. However, current motion skill learning methods typically restrict the…

Automated Machine Learning encompasses a set of meta-algorithms intended to design and apply machine learning techniques (e.g., model selection, hyperparameter tuning, model assessment, etc.). TPOT, a software for optimizing machine…

Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In…

Manipulation policies deployed in uncontrolled real-world scenarios are faced with great in-category geometric diversity of everyday objects. In order to function robustly under such variations, policies need to work in a category-level…

Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of…

In learning from demonstrations, it is often desirable to adapt the behavior of the robot as a function of the variability retrieved from human demonstrations and the (un)certainty encoded in different parts of the task. In this paper, we…

Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-GoalNet, a framework that generates task-specific policy…

Effective contact-rich manipulation requires robots to synergistically leverage vision, force, and proprioception. However, Reinforcement Learning agents struggle to learn in such multisensory settings, especially amidst sensory noise and…

Generative recommendation (GR) typically first quantizes continuous item embeddings into multi-level semantic IDs (SIDs), and then generates the next item via autoregressive decoding. Although existing methods are already competitive in…

Scooping items with tools such as spoons and ladles is common in daily life, ranging from assistive feeding to retrieving items from environmental disaster sites. However, developing a general and autonomous robotic scooping policy is…

Learning control policies for multi-robot systems (MRS) remains a major challenge due to long-term coordination and the difficulty of obtaining realistic training data. In this work, we address both limitations within an imitation learning…

Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy…

We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate…

Model predictive control (MPC) is an effective method for controlling robotic systems, particularly autonomous aerial vehicles such as quadcopters. However, application of MPC can be computationally demanding, and typically requires…

With the increasing presence of autonomous vehicles (AVs) on public roads, developing robust control strategies to navigate the uncertainty of human-driven vehicles (HVs) is crucial. This paper introduces an advanced method for modeling HV…

We introduce MoMask, a novel masked modeling framework for text-driven 3D human motion generation. In MoMask, a hierarchical quantization scheme is employed to represent human motion as multi-layer discrete motion tokens with high-fidelity…

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models, enabling parallel token generation while achieving competitive performance. Despite these advantages, MDMs face a fundamental limitation: once…

In industry, the reliability of rotating machinery is critical for production efficiency and safety. Current methods of Prognostics and Health Management (PHM) often rely on task-specific models, which face significant challenges in…

Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant…