cs.RO（2026-06-01）

📊 共 8 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects	提出基于高斯溅射的多刚体对象世界模型，用于学习动作条件下的对象动力学	manipulation world model world models
2	AFUN: Towards an Affordance Foundation Model for Functionality Understanding	提出AFUN，用于功能理解的具身智能基础模型，实现开放世界机器人操作	manipulation affordance foundation model
3	RoboDream: Compositional World Models for Scalable Robot Data Synthesis	RoboDream：通过组合世界模型实现可扩展的机器人数据合成	manipulation teleoperation world model
4	The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space	提出Lie Diffuser Actor以解决视觉语言动作策略中的欧几里得谬误问题	manipulation vision-language-action

#	题目	一句话要点	标签
5	WALL-WM: Carving World Action Modeling at the Event Joints	WALL-WM：通过事件联合雕琢世界行为建模，实现更精细的视频-行为学习。	world action model world action models vision-language-action
6	Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation	提出HSAN框架，通过分层语义增强导航解决连续环境下的视觉-语言导航问题	reinforcement learning scene understanding VLN
7	Network Distributed Multi-Agent Reinforcement Learning for Consensus Control of Quadcopters	提出网络分布式多智能体强化学习框架以解决四旋翼共识控制问题	reinforcement learning
8	World-Task Factorization for Robot Learning	提出世界-任务分解框架，提升机器人学习在复杂环境下的泛化能力。	world model world models