cs.RO（2026-02-11）

📊 共 20 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#	题目	一句话要点	标签	🔗	⭐
1	LocoVLM: Grounding Vision and Language for Adapting Versatile Legged Locomotion Policies	LocoVLM：通过视觉语言 grounding 实现通用足式机器人运动策略自适应	legged robot legged locomotion locomotion
2	LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer	LAP：语言-动作预训练实现零样本跨具身迁移	manipulation cross-embodiment embodiment transfer
3	APEX: Learning Adaptive High-Platform Traversal for Humanoid Robots	APEX：学习人型机器人自适应高平台攀爬策略	humanoid humanoid robot humanoid locomotion
4	Scaling World Model for Hierarchical Manipulation Policies	提出VISTA-WM框架，利用世界模型提升机器人操作策略的泛化性	manipulation world model vision-language-action
5	Co-jump: Cooperative Jumping with Quadrupedal Robots via Multi-Agent Reinforcement Learning	提出Co-jump框架，通过多智能体强化学习实现四足机器人协同跳跃	quadruped legged locomotion locomotion
6	RISE: Self-Improving Robot Policy with Compositional World Model	RISE：基于可组合世界模型的自提升机器人策略，解决复杂操作任务中的鲁棒性问题	manipulation reinforcement learning world model
7	RADAR: Benchmarking Vision-Language-Action Generalization via Real-World Dynamics, Spatial-Physical Intelligence, and Autonomous Evaluation	RADAR：通过真实世界动力学、空间物理智能和自主评估，对视觉-语言-动作泛化能力进行基准测试。	manipulation vision-language-action VLA
8	Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation	提出基于视频世界模型的指令驱动机器人操作框架，提升预测精度和操作性能。	manipulation world model distillation
9	Pitch Angle Control of a Magnetically Actuated Capsule Robot with Nonlinear FEA-based MPC and EKF Multisensory Fusion	提出基于非线性有限元MPC和EKF多传感器融合的磁驱动胶囊机器人俯仰角控制方法	locomotion actuator dynamics MPC
10	Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows	提出NF-HIQL，通过Normalizing Flow提升分层强化学习的数据效率和策略表达能力	locomotion manipulation reinforcement learning
11	YOR: Your Own Mobile Manipulator for Generalizable Robotics	YOR：一款低成本、开源的通用移动操作机器人平台	whole-body control manipulation mobile manipulation
12	Morphogenetic Assembly and Adaptive Control for Heterogeneous Modular Robots	针对异构模块化机器人，提出形态构建与自适应控制的闭环自动化框架	locomotion motion generation
13	ContactGaussian-WM: Learning Physics-Grounded World Model from Videos	提出ContactGaussian-WM，从视频中学习物理规律，解决稀疏数据和复杂接触下的世界建模难题。	MPC world model
14	A receding-horizon multi-contact motion planner for legged robots in challenging environments	提出一种基于后退水平面的多接触运动规划器，用于腿式机器人在复杂环境中导航。	legged robot
15	Omnidirectional Dual-Arm Aerial Manipulator with Proprioceptive Contact Localization for Landing on Slanted Roofs	提出基于力矩观测器的双臂无人机，用于在倾斜屋顶上自主着陆	dual-arm
16	SQ-CBF: Signed Distance Functions for Numerically Stable Superquadric-Based Safety Filtering	提出基于有符号距离函数的超二次曲面安全滤波SQ-CBF，提升机器人安全性和任务效率。	manipulation teleoperation
17	RadarEye: Robust Liquid Level Tracking Using mmWave Radar in Robotic Pouring	RadarEye：利用毫米波雷达实现机器人倾倒中鲁棒的液位跟踪	manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning	提出LifeLong-RFT，通过强化微调VLA模型实现机器人终身学习。	reinforcement learning VLA
19	Flow-Enabled Generalization to Human Demonstrations in Few-Shot Imitation Learning	提出SFCrP，利用场景光流预测和裁剪点云，提升少样本模仿学习中跨具身泛化能力	imitation learning scene flow cross-embodiment

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
20	From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving	HybridDriveVLA：融合VLM与纯视觉骨干网络，提升端到端驾驶性能	vision-language-action VLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页