cs.RO（2026-05-21）

📊 共 18 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 Learning to Evolve: Multi-modal Interactive Fields for Robust Humanoid Navigation in Dynamic Environments 提出多模态交互场MIF，用于动态环境中人形机器人稳健导航。 humanoid humanoid robot locomotion ✅
2 Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action SOMA：为视觉-语言-动作模型构建空间记忆，实现视野外操作 manipulation dual-arm vision-language-action
3 GesVLA: Gesture-Aware Vision-Language-Action Model Embedded Representations 提出GesVLA模型，通过融合手势信息增强VLA模型在复杂机器人操作场景中的目标定位和交互效率。 manipulation sim-to-real vision-language-action ✅
4 Branch-Stochastic Model Predictive Control for Motion Planning under Multi-Modal Uncertainty with Scenario Clustering 提出基于分支随机模型预测控制的运动规划方法，解决自动驾驶中多模态不确定性问题。 model predictive control motion planning
5 Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors Imagine2Real：通过视频生成先验实现零样本人机交互 humanoid HOI foundation model
6 Action with Visual Primitives AVP：利用视觉原语提升机器人操作的泛化性和数据效率 manipulation flow matching scene understanding
7 Terminal Constraint Model Predictive Control for Image-Based Visual Servoing of UAVs with Kalman Filter-Based Moment Loss Compensation 提出基于终端约束MPC的IBVS方法，解决无人机视觉伺服中的约束和特征丢失问题 MPC model predictive control
8 Industrial Dual-Arm Box Handling via Online Inertial Estimation and Convex Wrench Optimization 提出基于在线惯性估计和凸wrench优化的工业双臂箱体搬运方法 dual-arm
9 TacO: Benchmarking Tactile Sensors for Object Manipulation TacO：针对物体操作任务，系统性评测多种触觉传感器的性能 manipulation
10 OCELOT: Odometry and Contact Estimation for Legged Robots OCELOT：一种用于腿式机器人的里程计和接触估计方法，可应对滑移环境。 legged robot
11 Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations 提出基于少量演示学习不变奖励的框架，提升机器人泛化能力。 manipulation reinforcement learning policy learning
12 Symmetries Here and There, Combined Everywhere: Cross-space Symmetry Compositions in Robotics 提出跨空间对称组合框架，提升机器人策略在多对称性场景下的泛化能力 dual-arm
13 CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation 提出CoRMA，用于解决力主导装配任务中的接触丰富元适应问题 real2sim

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
14 EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control EvoScene-VLA：在动作解码器内演化场景信念，实现分块机器人控制 vision-language-action VLA
15 How can reasoning capability empower the AI copilot robot in endoscopic surgery 探索推理能力在内窥镜手术AI辅助机器人中的应用潜力 vision-language-action VLA multimodal
16 AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation 提出AwareVLN，通过自感知推理增强视觉语言导航能力 VLN ✅

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

#题目一句话要点标签🔗⭐
17 Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning 提出基于多智能体强化学习的四旋翼无人机竞速方法，实现超人级别的安全性和敏捷性。 reinforcement learning
18 Steins;Gate Drive: Semantic Safety Arbitration over Structured Futures for Latency-Decoupled LLM Planning SteinsGateDrive：面向延迟解耦LLM规划的结构化未来语义安全仲裁 world model world models

⬅️ 返回 cs.RO 首页 · 🏠 返回主页