cs.RO（2026-06-29）

📊 共 32 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (23 🔗4) 支柱三：空间感知与语义 (Perception & Semantics) (6 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (23 篇)

#题目一句话要点标签🔗⭐
1 X-Morph: Human Motion Priors for Scalable Robot Learning Across Morphologies 提出X-Morph以解决非人形机器人运动数据稀缺问题 quadruped legged robot humanoid ✅
2 Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision 提出ZR-0模型以解决跨平台视觉-语言-动作转移问题 humanoid manipulation bi-manual ✅
3 VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes 提出VLK以解决人形机器人感知与运动控制问题 humanoid manipulation loco-manipulation
4 KYON: Semi-Modular Wheel-Legged Quadruped With Agile Bimanual Capability 提出KYON机器人以解决复杂环境中的运动与操作问题 quadruped legged locomotion whole-body control
5 ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control 提出ReactiveBFM以解决人形机器人反应性运动规划问题 humanoid whole-body control motion planning
6 SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance 提出SA-VLA以解决机器人动作离散化中的状态感知问题 manipulation sim-to-real vision-language-action
7 Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform 提出VLA模型在真实机器人平台上的应用框架以解决控制问题 manipulation vision-language-action VLA
8 Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation 提出Chronos框架以解决非马尔可夫长时间操控问题 manipulation dual-arm state space model
9 OpenSPM: An Environment-Transferable Robotic Key Spatial Pose Memory and Closed-Loop High-Frequency Flow-Matching Action Generation Model 提出OpenSPM以解决开放环境下机器人操作的空间记忆与动作生成问题 manipulation flow matching vision-language-action
10 Sequential Planning via Anchored Robotic Keypoints 提出SPARK以解决机器人操作中的感知与规划问题 manipulation bi-manual teleoperation ✅
11 ConCent: Contact-Centric Real-to-Sim-to-Real Learning from One Demonstration 提出接触中心的真实到仿真再到真实学习框架以解决接触动态转移问题 manipulation sim-to-real reward design
12 Analytic Concept-Centric Memory for Agentic Embodied Manipulation 提出分析概念中心记忆框架以解决长时间体态操控问题 manipulation affordance
13 Grasp-Oriented Non-Prehensile Manipulation via Learning a Graspability Field 通过学习抓取场域提出非抓取操作以优化物体重构 manipulation reinforcement learning
14 Automating the Design of Embodied AgentArchitectures 提出AgentCanvas和KDLoop以自动化设计具身智能体架构 manipulation distillation language conditioned
15 Behavior Prompting Policy: Demonstrations as Prompts for Manipulation 提出行为提示策略以解决机器人任务学习问题 manipulation
16 WARP: Whole-Body Retargeting for Learning from Offline Human Demonstrations 提出WARP以解决人类示范到机器人动作的转移问题 manipulation mobile manipulation teleoperation
17 Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies 提出CI-MSE以解决机器人策略离线验证不可靠问题 manipulation
18 FalconTrack: Photorealistic Auto-Labeled Perception and Physics-Aware Vision-Based Aerial Tracking 提出FalconTrack以解决GPS缺失环境中的视觉跟踪问题 sim-to-real gaussian splatting splatting
19 Trajectory Optimization for Collision-Aware Redundant Robotic Multi-Axis Additive Manufacturing by Constrained Gradient Projection 提出基于约束梯度投影的轨迹优化方法以解决多轴增材制造中的碰撞问题 trajectory optimization
20 Heterogeneous Tactile Transformer 提出异构触觉变换器以解决传感器间知识迁移问题 manipulation ✅
21 Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation 提出动态运动关联的多模态融合策略以解决触觉状态识别问题 manipulation
22 Legible Shared Autonomy: Implicit Communication of Robot Belief through Motion 提出可读性共享自主控制以解决用户目标理解问题 manipulation
23 Data-Driven Modeling and Control for Tethered Space Systems with Koopman-Informed Graphs 提出KGD框架以解决系留空间系统建模与控制问题 model predictive control

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#题目一句话要点标签🔗⭐
24 MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM 提出MyGO-Splat以解决RGB-only SLAM中的几何自校正问题 3D gaussian splatting 3DGS gaussian splatting
25 Sphere-VIO: Fast and Robust Visual-Inertial Odometry via Unified Spherical Representation for Heterogeneous Multi-Camera Systems 提出Sphere-VIO以解决异构多摄像头系统的视觉惯性测程问题 VIO depth estimation
26 GROW$^2$: Grounding Which and Where for Robot Tool Use 提出GROW²以解决机器人工具使用中的开放世界赋能问题 affordance foundation model
27 CSAR: Containerized System Architecture for Robotics 提出CSAR以解决机器人系统复杂性问题 semantic mapping semantic map ✅
28 TACO: A Test and Check Framework for Robust Pose Graph Optimization 提出TACO框架以增强姿态图优化的鲁棒性 visual SLAM
29 Cross-Spectral Stereo Inertial Odometry 提出跨光谱立体惯性测距以解决光谱冗余问题 VIO ✅

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

#题目一句话要点标签🔗⭐
30 Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models 提出T^2VLA框架以解决VLA模型缺乏外部反馈的问题 reinforcement learning imitation learning vision-language-action
31 Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation 提出SWAM以解决视觉导航中的轨迹生成问题 world model world models world action model

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

#题目一句话要点标签🔗⭐
32 FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation 提出FutureNav以解决视觉语言导航中的世界状态建模问题 egocentric VLN foundation model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页