cs.RO（2026-09-16）

📊 共 56 篇论文 | 🔗 11 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (46 🔗9) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (3)

🔬 支柱一：机器人控制 (Robot Control) (46 篇)

#题目一句话要点标签🔗⭐
1 Learning Holistic Whole-Body Loco-Manipulation with a Bipedal Mobile Manipulator 提出统一的全身控制器以实现双足移动操控 bipedal biped whole-body control
2 KINO: A Keyframe Interface for VLM Planning and Whole-Body Control in Humanoid Loco-Manipulation 提出KINO框架以解决类人机器人运动控制与任务执行问题 humanoid whole-body control manipulation
3 WholeBodyWAM: Learning Whole-Body World Action Models with Scalable Motion Priors 提出WholeBodyWAM以解决人形机器人全身动态建模问题 humanoid manipulation whole-body manipulation
4 Gated Residual Body-Hand Coordination for Whole-Body Humanoid Teleoperation 提出门控残差协调框架以解决全身人形机器人遥操作中的手体协调问题 humanoid motion tracking dexterous hand
5 M$^3$P-R1: Reinforcement Learning for Large Language Model Guided Multi-Modal Motion Planning via MIP Code Generation 提出M$^3$P-R1以解决多模态运动规划问题 bipedal biped motion planning
6 ForceDelta-VLA: Distilling Force-Conditioned ActionCorrections for Contact-Rich Manipulation 提出ForceDelta-VLA以解决接触丰富操作中的动作校正问题 manipulation bi-manual distillation
7 OpenDexGrasp: Open-vocabulary Task-Oriented Dexterous Grasping 提出OpenDexGrasp以解决开放词汇任务导向的灵巧抓取问题 manipulation teleoperation open-vocabulary ✅
8 Asymptotically Optimal Multi-Robot Task and Motion Planning 提出渐近最优的多机器人任务与运动规划方法 manipulation motion planning task and motion planning
9 PASSAGE: Scaling Scene-Aligned Motion Learning for Perceptive Humanoid Traversal in Cluttered Environments 提出PASSAGE以解决人形机器人在复杂环境中的运动学习问题 humanoid humanoid robot reinforcement learning
10 Reinforcement Learning for Real-Time Vision-Language-Action Policies 提出实时强化学习框架以解决视觉-语言-动作模型延迟问题 manipulation reinforcement learning imitation learning ✅
11 DistAL: Distance-based Advantage Learning for VLA Fine-Tuning 提出DistAL以解决VLA微调中的奖励信息不足问题 manipulation bi-manual flow matching
12 rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference 提出rMuscle以提升视觉-语言-动作模型推理效率 manipulation embodied AI vision-language-action
13 WAVE-Go: World-Model Navigation with Adaptive Execution for Wheel-Legged Robots 提出WAVE-Go以解决动态障碍下的导航执行问题 legged robot locomotion world model ✅
14 Function-Preserving Data Generation for Zero-Shot Real-to-Sim-to-Real Manipulation 提出函数保持的数据生成方法以解决零-shot机器人操作问题 manipulation sim-to-real domain randomization
15 ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware 提出ActiveScale以解决机器人主动感知的挑战 manipulation mobile manipulation teleoperation
16 Feedback-Modulated Harmonic Policies for Quadruped Locomotion 提出反馈调制谐波策略以优化四足动物运动控制 quadruped locomotion locomotion policy
17 Acting in Meters: Learning Metric Interactions for Precise Robotic Manipulation 提出度量交互框架以解决精确机器人操控问题 manipulation vision-language-action VLA
18 A Comprehensive Review of Generative Physical Artificial Intelligence 提出生成物理人工智能以提升机器人自主能力 humanoid sim-to-real diffusion policy
19 UMI-Bridge: Action-Anchored Latent Alignment across Human and Robot Manipulation Data 提出UMI-Bridge以解决人机操作数据对齐问题 manipulation egocentric vision-language-action
20 TAO-Force: Unifying Force-Aware Perception and Fast-Slow Control for Contact-Rich Manipulation 提出TAO-Force以解决接触丰富操作中的感知与控制问题 manipulation policy learning vision-language-action
21 Energy-Regularized Imitation Learning for Force- and Work-Aware Robotic Manipulation 提出能量正则化模仿学习以解决机器人操控中的能量效率问题 manipulation imitation learning
22 AdaGeoVLN: Selective Geometry Across Representation Depth and Navigation Time for Vision-Language Navigation 提出AdaGeoVLN以解决视觉语言导航中的几何特征利用问题 humanoid VGGT VLN ✅
23 GroundingVLN: Reasoning and Acting with Grounding for Vision-Language Navigation 提出GroundingVLN以解决视觉语言导航中的推理与执行问题 locomotion reinforcement learning VLN
24 ForwardDLO: Model-Based Bimanual Shape Matching of Unconstrained Deformable Linear Objects 提出ForwardDLO以解决无约束可变形线性物体的双手形状匹配问题 manipulation bi-manual latent dynamics
25 WeaveRL: Weaving Reconstruction into Scene-Aware Fabrics for Perceptive Reinforcement Learning 提出WeaveRL以解决复杂场景下的强化学习问题 manipulation sim-to-real reinforcement learning
26 CaSCo: Cascade-Aware Soft-Collision Motion Planning 提出CaSCo框架以解决机器人运动规划中的软碰撞问题 manipulation motion planning
27 Body-Motion Control of a Simulated Aerial Swarm from a First-Person View 提出上半身运动控制接口以提升无人机群体第一人称视角导航效率 teleoperation first-person view
28 Decoupling Vision, Language, and Action for Efficient Multi-Task Robot Policies 提出解耦视觉、语言与动作的模型以提高多任务机器人策略的效率 manipulation vision-language-action VLA
29 UAVs Meet Embodied Intelligence: Bridging Human Intents and Flying Dynamics Via Harnessing Physical-Digital AI Agents 提出UAV EI框架以提升无人机的自主智能与人类意图理解 manipulation world model world models
30 Characterizing Replay Retention Under Dynamics Shift in Model-Based Reinforcement Learning 提出动态变化下的重放保留策略以提升模型驱动强化学习适应性 locomotion reinforcement learning model-based RL
31 InterMASH: A Unified Geometric Representation for Grasp Synthesis 提出InterMASH以解决人机抓取合成统一表示问题 manipulation physically plausible cross-embodiment ✅
32 TacBPM: A Tactile-conditioned Behavior Prior Model for Dexterous Reorientation 提出TacBPM以解决灵巧重定向中的行为优先问题 manipulation in-hand manipulation sim-to-real
33 Fetch My Beer: Synthetic-to-real Hierarchical Policy for Smooth Pick-and-place 提出合成到真实的层次化策略以解决液体容器的平稳搬运问题 manipulation teleoperation reinforcement learning
34 Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation 提出音频与视频生成结合的方法以解决机器人操作中的力感知问题 manipulation
35 From Gameplay to Policy: Towards Scalable Robot Data Collection via Gamified Robot-Free Interaction 提出Project Kitchen与Game2Policy以解决机器人数据收集的可扩展性问题 manipulation affordance egocentric
36 DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation 提出DeformSmith以解决机器人操作中可变形资产生成问题 manipulation ✅
37 GraphPoint: Semantic Entity Graphs and Point Trajectories for Compositional Robot Manipulation 提出GraphPoint以解决机器人操作中的指令依赖泛化问题 manipulation
38 RAFAIL: Relationship-Aware Failure Detection for Robotic Manipulation 提出RAFAIL框架以解决机器人操作中的故障检测问题 manipulation
39 CANTABILE: Learning Expressive Dynamics for Robotic Piano Performance 提出CANTABILE框架以提升机器人钢琴演奏的表现力 manipulation bi-manual bimanual manipulation
40 DynoFluxBench: Benchmarking Kinodynamic Space-Time Planners in Dynamic Environments 提出DynoFluxBench以解决动态环境中的运动规划问题 trajectory optimization ✅
41 DetAug: Obstacle-Blind Trajectory Augmentation for Zero-shot Obstacle Avoidance 提出DetAug以解决机器人避障中的数据集不足问题 manipulation
42 RecMorph: Topology-Guided Spatial Recurrence for Generalized Morphology Control 提出RecMorph以解决通用形态控制中的信息传递问题 quadruped ✅
43 A3P5 NEMESIS Integrated Rover Design for Environmental Reconnaissance and Robotic Sampling with Reproducible Mobility Analysis and an External Data Machine Learning Calibration Benchmark 提出A3P5 NEMESIS探测车以解决环境勘探与机器人采样问题 manipulation
44 Approximating High Dimensional Self-Motion Manifolds via Deep Generative Models 提出基于深度生成模型的高维自运动流形近似方法 motion planning ✅
45 Prior Evolution and Task Alignment for Aerial Grasping 提出基于学习的轨迹优化方法以解决空中抓取问题 trajectory optimization
46 Causal-History Test-Time Scaling for Failure Recovery in Autoregressive World-Action Models 提出无训练框架以解决自回归世界-动作模型的失败恢复问题 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
47 Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models 提出一种新方法以优化视觉-语言-动作模型的适应性调整 vision-language-action VLA Octo
48 ${M}^2$Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models 提出M²Tok以解决离散动作标记中的重构损失问题 vision-language-action VLA multimodal ✅
49 Online Multimodal Workload Assessment in Contact-Rich Physical Human-Robot Interaction 提出在线多模态工作负载评估框架以解决人机交互中的动态需求问题 multimodal
50 Technical Report: One-Step Drifting Action Heads for GR00T N1.7 提出一阶漂移动作头以降低视觉-语言-动作策略的推理成本 vision-language-action VLA

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
51 ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models 提出ActionPiece以解决动作标记化的准确性问题 policy learning representation learning vision-language-action
52 VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge 提出VLA-ULAP以解决远程推理延迟问题 JEPA VLA
53 FIERCE: From Generalist Robot Policies to Fast Specialists via Progress-Failure Feedback 提出FIERCE框架以提升机器人策略的学习效率 reinforcement learning policy learning ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
54 QMSR: Query-Conditioned Mask-wise Expert Routing for Robust Open-Vocabulary Underwater Object Retrieval 提出QMSR框架以解决复杂水下环境中的开放词汇物体检索问题 open-vocabulary open vocabulary
55 Active perception for robotic harvesting: 3D reconstruction and localisation of tomatoes hidden within clusters in a Mediterranean greenhouse 提出一种3D重建与定位方法以解决温室内番茄采摘问题 3D reconstruction
56 Benchmarking Visual-Inertial Odometry in Subterranean Environments Under Sensor Degradation, Miscalibration, and Dynamic Occlusion 提出针对地下环境的视觉惯性里程计失效评估基准 VIO

⬅️ 返回 cs.RO 首页 · 🏠 返回主页