cs.RO（2026-02-09）

📊 共 29 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (21 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (21 篇)

#题目一句话要点标签🔗⭐
1 Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning 提出R&B-EnCoRe，通过自监督方式引导具身推理，提升VLA模型性能。 quadruped bipedal biped
2 BiManiBench: A Hierarchical Benchmark for Evaluating Bimanual Coordination of Multimodal Large Language Models BiManiBench：多模态大语言模型双臂协调能力的层级评估基准 manipulation bi-manual dual-arm
3 TwinRL-VLA: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation TwinRL-VLA：基于数字孪生的强化学习，用于真实世界机器人操作 manipulation sim-to-real reinforcement learning
4 MOSAIC: Bridging the Sim-to-Real Gap in Generalist Humanoid Motion Tracking and Teleoperation with Rapid Residual Adaptation MOSAIC：通过快速残差自适应弥合通用人形机器人运动跟踪和遥操作的Sim-to-Real差距 humanoid sim-to-real teleoperation
5 Informative Object-centric Next Best View for Object-aware 3D Gaussian Splatting in Cluttered Scenes 提出一种信息驱动的、面向对象的NBV策略，用于在复杂场景中实现对象感知的3D高斯溅射。 manipulation 3D gaussian splatting 3DGS
6 Dexterous Manipulation Policies from RGB Human Videos via 4D Hand-Object Trajectory Reconstruction VIDEOMANIP：通过RGB视频进行4D手-物轨迹重建，学习灵巧操作策略 manipulation dexterous manipulation teleoperation
7 DexFormer: Cross-Embodied Dexterous Manipulation via History-Conditioned Transformer DexFormer：基于历史条件Transformer的跨具身灵巧操作 manipulation dexterous hand dexterous manipulation ✅
8 Learning Human-Like Badminton Skills for Humanoid Robots 提出Imitation-to-Interaction框架，使人形机器人掌握类人羽毛球技能 humanoid humanoid robot locomotion
9 Aerial Manipulation with Contact-Aware Onboard Perception and Hybrid Control 提出一种基于板载感知和混合控制的空中操作方法，用于接触式任务。 manipulation VIO contact-aware
10 Bi-Adapt: Few-shot Bimanual Adaptation for Novel Categories of 3D Objects via Semantic Correspondence Bi-Adapt：基于语义对应，实现3D物体新类别下的少样本双臂操作自适应 manipulation bi-manual bimanual manipulation
11 UniPlan: Vision-Language Task Planning for Mobile Manipulation with Unified PDDL Formulation 提出UniPlan以解决大规模室内环境中的移动操控任务规划问题 manipulation mobile manipulation bi-manual
12 STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction STEP：基于时空一致性预测的扩散模型视觉运动策略加速方法 manipulation diffusion policy spatiotemporal
13 Mimic Intent, Not Just Trajectories MINT：通过解耦意图与执行细节，提升模仿学习的泛化性和迁移能力 manipulation dexterous manipulation imitation learning
14 Constrained Sampling to Guide Universal Manipulation RL 提出Sample-Guided RL，引导通用操作强化学习探索复杂操作策略 manipulation reinforcement learning behavior cloning
15 $χ_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies 提出$χ_{0}$框架，通过驯服分布不一致性实现资源高效的鲁棒操作 manipulation dual-arm
16 Mind the Gap: Learning Implicit Impedance in Visuomotor Policies via Intent-Execution Mismatch 提出基于意图-执行不匹配学习的隐式阻抗控制方法，用于提升遥操作机器人性能。 manipulation bi-manual teleoperation ✅
17 Finite-Time Teleoperation of Euler-Lagrange Systems via Energy-Shaping 提出基于能量塑形的有限时间遥操作控制器，用于欧拉-拉格朗日系统 teleoperation
18 A Precise Real-Time Force-Aware Grasping System for Robust Aerial Manipulation 提出一种精确的实时力感知抓取系统，用于鲁棒的无人机操作 manipulation
19 Characteristics, Management, and Utilization of Muscles in Musculoskeletal Humanoids: Empirical Study on Kengoro and Musashi 针对肌骨人形机器人，系统性分析肌肉特性、管理与利用方法 humanoid
20 Contact-Anchored Policies: Contact Conditioning Creates Strong Robot Utility Models 提出Contact-Anchored Policies，通过接触点条件反射提升机器人操作能力 manipulation VLA
21 Post-Collision Trajectory Restoration for a Single-track Ackermann Vehicle using Heuristic Steering and Tractive Force Functions 提出启发式控制法以恢复单轨Ackermann车辆的碰撞后轨迹 recovery control

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

#题目一句话要点标签🔗⭐
22 SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios SteerVLA：利用视觉-语言模型在长尾驾驶场景中实现可控的自动驾驶 vision-language-action VLA ✅
23 Decentralized Intent-Based Multi-Robot Task Planner with LLM Oracles on Hyperledger Fabric 提出基于LLM Oracle和Hyperledger Fabric的去中心化多机器人任务规划器 embodied AI large language model
24 From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selection 提出基于VLM的路径选择方法，用于机器人社交导航，提升人机交互体验 foundation model

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

#题目一句话要点标签🔗⭐
25 GaussianCaR: Gaussian Splatting for Efficient Camera-Radar Fusion GaussianCaR：利用高斯溅射实现高效相机-雷达融合的BEV分割 gaussian splatting splatting

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
26 Benchmarking Autonomous Vehicles: A Driver Foundation Model Framework 提出驾驶员基础模型框架，用于全面评估自动驾驶车辆性能 penetration foundation model

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

#题目一句话要点标签🔗⭐
27 Reduced-order Control and Geometric Structure of Learned Lagrangian Latent Dynamics 提出基于学习的拉格朗日隐空间动力学降阶控制框架，用于高维机械系统控制。 latent dynamics

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
28 Reliability-aware Execution Gating for Near-field and Off-axis Vision-guided Robotic Alignment 提出可靠性感知执行门控，解决近场和离轴视觉引导机器人对准中的误差放大问题 geometric consistency

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
29 Chamelion: Reliable Change Detection for Long-Term LiDAR Mapping in Transient Environments Chamelion：面向动态环境的长期LiDAR建图可靠变化检测 spatiotemporal ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页