相关论文: ModSkill: Physical Character Skill Modularization

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

Learning a general motion tracking policy from human motions shows great potential for versatile humanoid whole-body control. Conventional approaches are not only inefficient in data utilization and training processes but also exhibit…

Humans and animals developed a sophisticated motor control apparatus and there is much evidence that it has a modular structure. The modularity offers a range of benefits, e.g. ability to learn dissociable motion styles without interference…

Generalizing across robot embodiments and tasks is crucial for adaptive robotic systems. Modular policy learning approaches adapt to new embodiments but are limited to specific tasks, while few-shot imitation learning (IL) approaches often…

In real-world scenarios, achieving domain generalization (DG) presents significant challenges as models are required to generalize to unknown target distributions. Generalizing to unseen multi-modal distributions poses even greater…

Humanoid robots hold significant potential in accomplishing daily tasks across diverse environments thanks to their flexibility and human-like morphology. Recent works have made significant progress in humanoid whole-body control and…

Animals (especially humans) have an amazing ability to learn new tasks quickly, and switch between them flexibly. How brains support this ability is largely unknown, both neuroscientifically and algorithmically. One reasonable supposition…

Recent years have witnessed many successful trials in the robot learning field. For contact-rich robotic tasks, it is challenging to learn coordinated motor skills by reinforcement learning. Imitation learning solves this problem by using a…

Embodied agents can benefit from skills that guide object search, action execution, and state changes across diverse environments. Since embodied environments vary across layouts, object states, and other execution factors, these skills…

The domain of robotics is challenging to apply deep reinforcement learning due to the need for large amounts of data and for ensuring safety during learning. Curriculum learning has shown good performance in terms of sample- efficient deep…

A core aspect of human intelligence is the ability to learn new tasks quickly and switch between them flexibly. Here, we describe a modular continual reinforcement learning paradigm inspired by these abilities. We first introduce a visual…

We present Skill Transformer, an approach for solving long-horizon robotic tasks by combining conditional sequence modeling and skill modularity. Conditioned on egocentric and proprioceptive observations of a robot, Skill Transformer is…

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…

In recent years, a myriad of advanced results have been reported in the community of imitation learning, ranging from parametric to non-parametric, probabilistic to non-probabilistic and Bayesian to frequentist approaches. Meanwhile, ample…

Modeling and control of the human musculoskeletal system is important for understanding human motor functions, developing embodied intelligence, and optimizing human-robot interaction systems. However, current human musculoskeletal models…

Multimodal learning seeks to combine data from multiple input sources to enhance the performance of different downstream tasks. In real-world scenarios, performance can degrade substantially if some input modalities are missing. Existing…

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…

Assembling a slave object into a fixture-free master object represents a critical challenge in flexible manufacturing. Existing deep reinforcement learning-based methods, while benefiting from visual or operational priors, often struggle…

Large language models (LLMs) are moving beyond static uses and are now powering agents that learn continually during their interaction with external environments. For example, agents can learn reusable skills while navigating web pages or…

Traditional language-conditioned manipulation agent sequential adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practical deployment. In this paper, we propose SkillsCrafter, a…