相关论文: Learning High-Frequency Continuous Action Chunks i…

Sequential decision-making in high-dimensional continuous action spaces, particularly in stochastic environments, faces significant computational challenges. We explore this challenge in the traditional offline RL setting, where an agent…

Modern paradigms for robot imitation train expressive policy architectures on large amounts of human demonstration data. Yet performance on contact-rich, deformable-object, and long-horizon tasks plateau far below perfect execution, even…

In this paper, we describe a simple strategy for mitigating variability in temporal data series by shifting focus onto long-term, frequency domain features that are less susceptible to variability. We apply this method to the human action…

The increasing demand for accelerated scientific discovery, driven by global challenges, highlights the need for advanced AI-driven robotics. Deploying robotic chemists in human-centric labs is key for the next horizon of autonomous…

Temporal abstraction and efficient planning pose significant challenges in offline reinforcement learning, mainly when dealing with domains that involve temporally extended tasks and delayed sparse rewards. Existing methods typically plan…

Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…

Robotic grasping under uncertainty remains a fundamental challenge due to its uncertain and contact-rich nature. Traditional rigid robotic hands, with limited degrees of freedom and compliance, rely on complex model-based and heavy feedback…

Recent advances in learning reusable motion priors have demonstrated their effectiveness in generating naturalistic behaviors. In this paper, we propose a new learning framework in this paradigm for controlling physics-based characters with…

In intelligent manufacturing, robots are asked to dynamically adapt their behaviours without reducing productivity. Human teaching, where an operator physically interacts with the robot to demonstrate a new task, is a promising strategy to…

In order to solve complex, long-horizon tasks, intelligent robots need to carry out high-level, abstract planning and reasoning in conjunction with motion planning. However, abstract models are typically lossy and plans or policies computed…

For decades, people have been seeking for fishlike flapping motions that can realize underwater propulsion with low energy cost. Complexity of the nonstationary flow field around the flapping body makes this problem very difficult. In…

Learning long-horizon robotic manipulation requires jointly achieving expressive behavior modeling, real-time inference, and stable execution, which remains challenging for existing generative policies. Diffusion-based approaches offer…

This paper presents an approach to externally influencing a team of robots by means of time-varying density functions. These density functions represent rough references for where the robots should be located. To this end, a continuous-time…

Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process…

A fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips. We learn data-driven generative models of human movement using autoregressive…

Contact-rich manipulation requires not only vision-dominant task semantics but also closed-loop reactions to force/torque (F/T) transients. Yet, generative visuomotor policies are typically constrained to low-frequency updates due to…

The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution. While goal conditioning of policies has been studied in the RL literature,…

The goal of offline reinforcement learning is to learn a policy from a fixed dataset, without further interactions with the environment. This setting will be an increasingly more important paradigm for real-world applications of…

Reinforcement Learning algorithms can learn complex behavioral patterns for sequential decision making tasks wherein an agent interacts with an environment and acquires feedback in the form of rewards sampled from it. Traditionally, such…

Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and…