cs.RO（2026-07-13）

📊 共 34 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (25 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (25 篇)

#题目一句话要点标签🔗⭐
1 PAKE: Learning Whole-Body Loco-Manipulation with Partial Kinematic Embeddings 提出PAKE框架以解决高维全身运动控制问题 quadruped whole-body control motion tracking
2 A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation 提出REGRIND以解决灵巧操作中的运动重定向问题 humanoid whole-body control manipulation
3 Robust bipedal locomotion on flowable slopes via foot-driven terrain manipulation 通过足部驱动的地形操控提高流动坡面上的双足行走稳定性 bipedal biped locomotion
4 SKooP: Symmetric Koopman Predictions for Faster and More Generalizable Legged Robot Locomotion with Reinforcement Learning 提出SKooP以解决机器人强化学习样本效率低的问题 quadruped legged robot bipedal ✅
5 Mixture of Frames Policy: Multi-Frame Action Denoising for Bimanual Mobile Manipulation 提出混合帧策略以解决双手移动操控中的动作去噪问题 manipulation mobile manipulation bi-manual
6 Affordance-Based Manipulation Planning with Text Goals and Sim-to-Real Generalisation via Real-to-Sim Image Conversion 提出基于可供性识别的操控规划系统以解决文本目标问题 manipulation sim-to-real affordance
7 Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model 提出Xiaomi-Robotics-U0以解决机器人多视图一致性问题 manipulation world model world models
8 Towards Predictive, Aligned, and Scalable Robot Learning 提出Lumo-2以解决机器人学习中的预测与对齐问题 manipulation dexterous manipulation world model
9 CR-Solver: GPU-Accelerated Kinematics Solver for Tendon-driven Continuum Robots 提出CR-Solver以解决连续机器人运动生成问题 manipulation motion planning motion generation
10 NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception 提出NeuralActuator以解决机器人动力学和外力感知问题 sim-to-real actuator dynamics teleoperation
11 DA-Nav: Direction-Aware City-Scale Vision-Language Navigation 提出DA-Nav以解决城市规模视觉语言导航问题 quadruped humanoid humanoid robot
12 VIA: Visual Interface Agent for Robot Control 提出VIA框架以实现机器人控制的视觉接口代理 manipulation vision-language-action VLA
13 WarpMPC: Large-Batch MPC on GPU via ADMM with Unrolled $LDL^\top$ Factorization 提出WarpMPC以提升GPU上大批量MPC求解效率 humanoid humanoid robot MPC
14 Towards Human-level Dexterous Teleoperation 提出TeleDexter以解决机器人灵巧遥操作的精确控制问题 dexterous hand domain randomization teleoperation
15 Stop to Decide: Latency-Aware Proprioceptive Navigation Primitives for Mapping-Free Quadruped Inspection 提出延迟感知的自我感知导航原语以解决四足机器人无地图检查问题 quadruped Unitree
16 Wearing A Coat: Dual-Arm Robot-Assisted Dressing with Differentiable Clothing Simulation 提出实时可微服装仿真以解决双臂机器人辅助穿衣问题 dual-arm differentiable simulation
17 Real-Time Rulebook-Aware Nonlinear MPC for Autonomous Driving with Priority-Biased Tiered Slacks 提出基于优先级偏置的非线性MPC以解决自动驾驶中的实时决策问题 MPC model predictive control
18 EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation 提出EDAR以解决机器人操作中的环境依赖动作表示问题 manipulation policy learning
19 Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentation 提出Pix2Act以解决图像空间操作策略的精度与可解释性问题 manipulation imitation learning
20 SegDiff: Segmented Trajectory Diffusion for Consistent and Adaptive Robot Manipulation 提出SegDiff以解决机器人操控中的短期预测问题 manipulation imitation learning
21 A Compact Top-Loading Robot for Endovascular Interventions: Design, Control and Evaluation 提出一种紧凑型顶装机器人以解决血管内手术中的仪器交换问题 motion tracking manipulation
22 AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations 提出AutoPath以解决动态环境中的安全导航问题 quadruped multimodal
23 WALA Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos 提出WALA框架以从无标签视频中学习可执行潜在动作 manipulation world model world models
24 Requirement-Driven Design of Whole-Body Social Tactile Sensing via Virtual Human-Robot Interaction 提出需求驱动的全身社交触觉感知设计以解决现有方法局限 humanoid humanoid robot
25 Breaking the 15% Barrier: A Real-World Data-Driven System for Proactive Social Robot Triggered by User Nonverbal Cues 提出基于非语言行为的社交机器人主动响应系统以提升用户互动体验 humanoid humanoid robot

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
26 GeoGS-SLAM: Online Monocular Reconstruction Using Gaussian Splatting with Geometric Priors 提出GeoGS-SLAM以解决单目重建中几何信息不足的问题 3D gaussian splatting 3DGS gaussian splatting ✅
27 Self-Healing Visual Recovery for Autonomous Ground Vehicles Using Camera-Only Visual Odometry 提出自愈视觉恢复方法以解决无人地面车辆的视觉里程计问题 visual odometry
28 Desc++: Efficient Descriptor Enhancement for Data Association in Existing Visual SLAM Systems 提出Desc++以解决视觉SLAM中数据关联的效率与准确性问题 visual SLAM
29 A Glimpse into Long-term Physical Coexistence with Intelligent Robots 提出PHILIA以解决智能机器人长期共存问题 scene understanding

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

#题目一句话要点标签🔗⭐
30 From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence 提出共生智能路线图以解决开放世界物理智能问题 world model world models world action model
31 Whole-Body Semantic-to-Actuation Grounding of Elephant-Inspired Soft-Trunk Motion via Lightweight Flow Matching 提出全身语义到驱动的基础框架以解决人机交互中的运动表达问题 flow matching open-vocabulary open vocabulary

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

#题目一句话要点标签🔗⭐
32 See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models 提出机器人中心点图以解决视觉-语言-动作模型的帧不匹配问题 vision-language-action VLA
33 ERR@HRI 3.0 Challenge: Multimodal Detection of Errors and Anticipation in Human-Robot Interactions 提出ERR@HRI 3.0挑战以解决人机交互中的错误检测问题 multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
34 Automated Synthesis of Facial Mechanisms for Conversational Animatronic Robots 提出自动化面部机制合成方法以解决社交机器人个性化问题 motion synthesis

⬅️ 返回 cs.RO 首页 · 🏠 返回主页