While solving complex manipulation tasks, manipulation policies often need to learn a set of diverse skills to accomplish these tasks. The set of skills is often quite multimodal - each one may have a quite distinct distribution of actions and states. Standard deep policy-learning algorithms often model policies as deep neural networks with a single output head (deterministic or stochastic). This structure requires the network to learn to switch between modes internally, which can lead to lower sample efficiency and poor performance. In this paper we explore a simple structure which is conducive to skill learning required for so many of the manipulation tasks. Specifically, we propose a policy architecture that sequentially executes different action heads for fixed durations, enabling the learning of primitive skills such as reaching and grasping. Our empirical evaluation on the Metaworld tasks reveals that this simple structure outperforms standard policy learning methods, highlighting its potential for improved skill acquisition.
MetaWorld-X: Hierarchical World Modeling via VLM-Orchestrated Experts for Humanoid Loco-Manipulation
University of Hamburg（汉堡大学）；School of Information Science and Technology, Beijing University of Technology（信息科学与技术学院，北京理工大学）；School of Information Science and Engineering, Fudan University（信息科学与工程学院，复旦大学）；University of Alberta（阿尔伯塔大学）
Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation
Technical University of Darmstadt（达姆施塔特工业大学）；University of Washington（华盛顿大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Cornell University（康奈尔大学）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation
TAMS (Technical Aspects of Multimodal Systems), Department of Informatics, University of Hamburg（汉堡大学信息学院TAMS（多模态系统技术））；Technical University of Munich（慕尼黑技术大学）；Agile Robots SE（敏捷机器人有限公司）
G$^3$VLA: Geometric Inductive Bias for Vision-Language-Action Models
New York University Shanghai（上海纽约大学）；Technical University of Denmark（丹麦技术大学）；MBZUAI - Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；New York University Abu Dhabi（纽约大学阿布扎比分校）
From a Single Demonstration to a General Policy for Contact-Rich Manipulation
Robotics and Biology Laboratory, Technische Universität Berlin（技术大学柏林机器人与生物学实验室）；Science of Intelligence, Research Cluster of Excellence, Berlin（智能科学，卓越研究集群，柏林）；Robotics Institute Germany（德国机器人研究所）
Towards Safe Robot Foundation Models Using Inductive Biases
Technical University of Darmstadt（德累斯顿技术大学）；German Research Center for AI ( dfki )（人工智能研究中心）；University of Oxford（牛津大学）；Robotics Institute Germany ( rig )（德国机器人研究所）；Centre for Cognitive Science（认知科学中心）
Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learning
Department of Computer Science, Yale University（计算机科学系，耶鲁大学）；Department of Computer and Information Science, University of Pennsylvania（计算机与信息科学系，宾夕法尼亚大学）；Department of Electrical and Systems Engineering, University of Pennsylvania（电气与系统工程系，宾夕法尼亚大学）
