cs.RO（2026-02-28）

📊 共 28 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (21) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (21 篇)

#题目一句话要点标签🔗⭐
1 DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation DySL-VLA：基于动态-静态层跳跃的机器人操作高效视觉-语言-动作模型推理 manipulation distillation vision-language-action
2 A Pragmatic VLA Foundation Model LingBot-VLA：基于2万小时真实机器人数据的实用视觉-语言-动作基础模型 manipulation dual-arm vision-language-action
3 SignBot: Learning Human-to-Humanoid Sign Language Interaction 提出SignBot框架，实现人与人形机器人之间自然的手语交互 humanoid humanoid robot humanoid control
4 SignVLA: A Gloss-Free Vision-Language-Action Framework for Real-Time Sign Language-Guided Robotic Manipulation 提出SignVLA框架，实现基于手语的实时机器人操作控制 manipulation vision-language-action VLA
5 Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline 提出CEBench基准和LLaVA-VLA模型，提升VLA模型在机器人领域的实用性。 manipulation mobile manipulation domain randomization
6 InCoM: Intent-Driven Perception and Structured Coordination for Whole-Body Mobile Manipulation 提出InCoM框架以解决全身移动操控中的感知与协调问题 whole-body control manipulation mobile manipulation
7 DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning DreamWaQ++：基于多模态强化学习的四足机器人障碍感知稳健运动控制 quadruped locomotion reinforcement learning
8 Spatially anchored Tactile Awareness for Robust Dexterous Manipulation 提出SaTA框架，通过空间锚定的触觉感知实现鲁棒的灵巧操作 manipulation dexterous manipulation bi-manual
9 Pixel2Catch: Multi-Agent Sim-to-Real Transfer for Agile Manipulation with a Single RGB Camera Pixel2Catch：基于单RGB相机和多智能体强化学习的敏捷操作Sim-to-Real迁移 manipulation sim-to-real reinforcement learning
10 EgoAVFlow: Robot Policy Learning with Active Vision from Human Egocentric Videos via 3D Flow EgoAVFlow：利用3D光流，从人类第一视角视频中学习机器人主动视觉策略 manipulation policy learning egocentric
11 A Perspective on Open Challenges in Deformable Object Manipulation 综述：针对柔性物体操作中的开放性挑战与未来方向 manipulation reinforcement learning differentiable simulation
12 Sparse Imagination for Efficient Visual World Model Planning 提出稀疏想象方法，加速视觉世界模型规划，提升机器人决策效率 trajectory optimization world model VLA
13 NMPCM: Nonlinear Model Predictive Control on Resource-Constrained Microcontrollers 提出NMPCM方法，在资源受限的微控制器上实现四旋翼无人机的非线性模型预测控制 MPC model predictive control
14 GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion GraspLDP：通过潜在扩散模型提升抓取策略的泛化性和精确性 manipulation policy learning imitation learning
15 Robust Helicopter Ship Deck Landing With Guaranteed Timing Using Shrinking-Horizon Model Predictive Control 提出基于收缩时域模型预测控制的鲁棒直升机舰船甲板着陆方法 model predictive control
16 Considering Perspectives for Automated Driving Ethics: Collective Risk in Vehicular Motion Planning 提出考虑多方风险的自动驾驶运动规划，提升交通整体安全性与效率 motion planning
17 STL-Based Motion Planning and Uncertainty-Aware Risk Analysis for Human-Robot Collaboration with a Multi-Rotor Aerial Vehicle 提出基于STL的多旋翼人机协作运动规划与不确定性风险分析方法 motion planning
18 SPARR: Simulation-based Policies with Asymmetric Real-world Residuals for Assembly SPARR：结合模拟策略与真实残差策略，提升机器人装配精度与效率 manipulation sim-to-real reinforcement learning
19 DigiArm: An Anthropomorphic 3D-Printed Prosthetic Hand with Enhanced Dexterity for Typing Tasks DigiArm：一种用于打字任务的具有增强灵巧性的人形3D打印假肢手 manipulation dexterous manipulation
20 LeRobot: An Open-Source Library for End-to-End Robot Learning LeRobot：一个用于端到端机器人学习的开源库 teleoperation
21 Grasp, Slide, Roll: Comparative Analysis of Contact Modes for Tactile-Based Shape Reconstruction 研究触觉抓取、滑动、滚动三种模式，加速物体形状重建 dexterous hand

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
22 Sapling-NeRF: Geo-Localised Sapling Reconstruction in Forests for Ecological Monitoring 提出Sapling-NeRF，用于森林中幼树的地理定位重建，以进行生态监测。 3D gaussian splatting 3DGS gaussian splatting
23 Relational Appliances: A Robot in the Refrigerator for Home-Based Health Promotion 提出关系型家电概念，冰箱内置机器人用于家庭健康促进 affordance

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

#题目一句话要点标签🔗⭐
24 Metamorphic Testing of Vision-Language Action-Enabled Robots 提出基于变质测试的VLA机器人测试方法，解决测试预言机问题。 vision-language-action VLA multimodal
25 Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning 提出基于层级LLM的多智能体框架，通过提示优化解决多机器人任务规划问题 large language model

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

#题目一句话要点标签🔗⭐
26 From Prompts to Printable Models: Support-Effective 3D Generation via Offset Direct Preference Optimization 提出SEG框架，通过Offset DPO优化3D模型，减少打印支撑结构。 DPO direct preference optimization

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
27 An Empirical Analysis of Cooperative Perception for Occlusion Risk Mitigation 提出基于跟踪丢失风险的合作感知评估指标，优化V2X部署策略 penetration

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
28 SCREP: Scene Coordinate Regression and Evidential Learning-based Perception-Aware Trajectory Generation 提出基于场景坐标回归和证据学习的感知自主轨迹生成方法，解决GPS拒止环境下的定位问题。 feature matching

⬅️ 返回 cs.RO 首页 · 🏠 返回主页