cs.RO（2026-04-20）

📊 共 17 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#	题目	一句话要点	标签	🔗	⭐
1	ST-$π$: Structured SpatioTemporal VLA for Robotic Manipulation	提出ST-$π$，通过结构化时空VLA模型提升机器人操作中细粒度时空推理能力。	manipulation spatiotemporal vision-language-action	✅
2	DART: Learning-Enhanced Model Predictive Control for Dual-Arm Non-Prehensile Manipulation	DART：用于双臂非抓取操作的学习增强型模型预测控制	manipulation dual-arm MPC	✅
3	AnchorRefine: Synergy-Manipulation Based on Trajectory Anchor and Residual Refinement for Vision-Language-Action Models	AnchorRefine：基于轨迹锚点和残差精化的视觉-语言-动作模型	manipulation vision-language-action VLA
4	ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning	ReFineVLA：通过教师引导微调实现多模态推理的通用机器人策略	manipulation vision-language-action VLA
5	OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation	提出OFlow，通过注入对象感知时序流匹配增强机器人操作的鲁棒性	manipulation flow matching VLA
6	SYMBOLIZER: Symbolic Model-free Task Planning with VLMs	SYMBOLIZER：利用视觉语言模型进行无模型符号化任务规划	motion planning task and motion planning TAMP
7	COFFAIL: A Dataset of Successful and Anomalous Robot Skill Executions in the Context of Coffee Preparation	COFFAIL：咖啡准备场景下机器人技能成功与异常执行数据集	manipulation bi-manual bimanual manipulation
8	Locomotion of an Elastic Snake Robot via Natural Dynamics	利用自然动力学提升弹性蛇形机器人运动效率	locomotion
9	SpaceDex: Generalizable Dexterous Grasping in Tiered Workspaces	SpaceDex：针对分层工作空间的可泛化灵巧抓取框架	manipulation dexterous hand dexterous manipulation
10	DAG-STL: A Hierarchical Framework for Zero-Shot Trajectory Planning under Signal Temporal Logic Specifications	提出DAG-STL框架，解决未知动力学下基于STL的零样本轨迹规划问题	manipulation
11	Will People Enjoy a Robot Trainer? A Case Study with Snoopie the Pacerbot	提出SNOOPIE四足机器人教练，提升跑步训练依从性和用户体验	quadruped
12	Chatting about Conditional Trajectory Prediction	提出CiT模型，通过跨时域意图交互进行条件轨迹预测，提升人机交互安全性。	motion planning
13	Periodic Steady-State Control of a Handkerchief-Spinning Task Using a Parallel Anti-Parallelogram Tendon-driven Wrist	针对手帕舞的周期稳态控制，提出一种并联反平行四边形腱驱动灵巧手腕。	manipulation	✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
14	Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models	提出BeTTER基准，揭示VLA模型在具身推理中存在的幻觉问题	vision-language-action VLA
15	StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement	StableIDM：通过时空优化稳定逆动力学模型，提升机械臂截断下的控制性能	embodied AI VLA

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
16	OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL	OmniVLA-RL：结合空间理解与在线强化学习的视觉-语言-动作模型	reinforcement learning flow matching embodied AI

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation	提出基于深度先验的玻璃表面重建方法，提升机器人导航在复杂环境下的鲁棒性	Depth Anything foundation model	✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页