相关论文: PoCo: Policy Composition from and for Heterogeneou…

A goal of artificial intelligence is to construct an agent that can solve a wide variety of tasks. Recent progress in text-guided image synthesis has yielded models with an impressive ability to generate complex novel images, exhibiting…

Reinforcement learning has been applied to a wide variety of robotics problems, but most of such applications involve collecting data from scratch for each new task. Since the amount of robot data we can collect for any single task is…

Combined visual and force feedback play an essential role in contact-rich robotic manipulation tasks. Current methods focus on developing the feedback control around a single modality while underrating the synergy of the sensors. Fusing…

Reinforcement learning (RL) and trajectory optimization (TO) present strong complementary advantages. On one hand, RL approaches are able to learn global control policies directly from data, but generally require large sample sizes to…

Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for…

Co-training, which combines limited in-domain real-world data with abundant surrogate data such as simulation or cross-embodiment robot data, is widely used for training generative robot policies. Despite its empirical success, the…

We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of…

Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies…

We develop a hybrid control approach for robot learning based on combining learned predictive models with experience-based state-action policy mappings to improve the learning capabilities of robotic systems. Predictive models provide an…

The control of a robot for manipulation tasks generally relies on object detection and pose estimation. An attractive alternative is to learn control policies directly from raw input data. However, this approach is time-consuming and…

In this paper, we propose the use of generative artificial intelligence (AI) to improve zero-shot performance of a pre-trained policy by altering observations during inference. Modern robotic systems, powered by advanced neural networks,…

The physical design of a robot and the policy that controls its motion are inherently coupled, and should be determined according to the task and environment. In an increasing number of applications, data-driven and learning-based…

Robots and other intelligent systems navigating in complex dynamic environments should predict future actions and intentions of surrounding agents to reach their goals efficiently and avoid collisions. The dynamics of those agents strongly…

The hype about sensorimotor learning is currently reaching high fever, thanks to the latest advancement in deep learning. In this paper, we present an open-source framework for collecting large-scale, time-synchronised synthetic data from…

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,…

To improve generalization and resilience in human-robot collaboration (HRC), robots must handle the combinatorial diversity of human behaviors and contexts, motivating multi-agent reinforcement learning (MARL). However, inherent…

Imitation learning from human motion capture (MoCap) data provides a promising way to train humanoid robots. However, due to differences in morphology, such as varying degrees of joint freedom and force limits, exact replication of human…

In this work, we present an approach to construct a video-based robot policy capable of reliably executing diverse tasks across different robots and environments from few video demonstrations without using any action annotations. Our method…

Humanoid robots, capable of assuming human roles in various workplaces, have become essential to embodied intelligence. However, as robots with complex physical structures, learning a control model that can operate robustly across diverse…

Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. However, existing methods typically treat it as a discrete filter or post-hoc regulator rather…