cs.RO（2026-10-19）

📊 共 47 篇论文 | 🔗 13 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (37 🔗11) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (37 篇)

#题目一句话要点标签🔗⭐
1 HAF-VLA: Hierarchical Action Flow Framework for Humanoid Vision-Language-Action Control 提出HAF-VLA框架以解决人形机器人视觉-语言-动作控制问题 humanoid humanoid robot locomotion
2 Vector-Quantized World Model: Latent Feedback Motion Planning for Robot Manipulation 提出向量量化世界模型以解决机器人长时间操控问题 locomotion manipulation motion planning
3 Humanoid SRL: Augmenting Humanoids with Supernumerary Limbs for Coordinated Loco-Manipulation 提出超numerary肢体以增强类人机器人协调运动能力 humanoid humanoid robot manipulation
4 Robot Learning with Vision-Language-Action Models for Agricultural Manipulation 提出视觉-语言-动作模型以解决农业操作中的机器人学习问题 manipulation teleoperation vision-language-action
5 RoboMMT: Learning Stable Tracking of Modulated Expressive and Interactive Robot Motion 提出RoboMMT以解决动态不稳定平台上机器人运动稳定性问题 quadruped humanoid humanoid robot
6 Compositional Humanoid Manipulation through Isomorphic Teleoperation and Independent Skill Routing 提出HS-MoDP以解决人形机器人技能组合问题 humanoid locomotion manipulation
7 ReDOA: Real-World Distillation via Observation Alignment for Image-Based Manipulation Policy Learning 提出ReDOA框架以解决机器人操控中的数据收集与适应性问题 manipulation bi-manual bimanual manipulation ✅
8 HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation 提出HandsOn平台以解决通用灵巧操作的基准测试问题 manipulation dexterous hand dexterous manipulation
9 DexOAK: Object-Aware Kinematic Retargeting 提出DexOAK以解决机器人手部运动重定向问题 bi-manual penetration kinematic retargeting ✅
10 Data-Efficient Learning from Demonstration for Humanoid Robots via Feature-Level Perception and Prompt-Based Object Detection 提出一种数据高效的学习框架以解决人形机器人技能学习问题 humanoid humanoid robot manipulation
11 SPAR: Structural Pruning and Action Recovery for Vision-Language-Action Models 提出SPAR以解决机器人视觉语言动作模型的计算资源瓶颈问题 manipulation reinforcement learning vision-language-action
12 FR-VLA: Implicit Force Reasoning VLA for Contact-Rich Manipulation 提出FR-VLA以解决机器人操作中的力感知问题 manipulation vision-language-action VLA
13 OmniInteract: Towards Unified Whole-Body Interaction Control for Dual Humanoids 提出OmniInteract以解决双人类机器人交互控制问题 humanoid humanoid control policy learning
14 TrajWAM: An Efficient Trajectory-Guided World Action Model for Dynamic Robotic Manipulation 提出TrajWAM以解决动态物体操控中的预测与执行延迟问题 manipulation world action model world action models ✅
15 Physical Words: A Vocabulary for Structuring Latent Reasoning in Robot Manipulation 提出PhysWord以解决机器人操作中的多模态推理问题 manipulation dexterous hand bi-manual
16 PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models 提出PaceVLA以解决视觉-语言-动作模型的执行效率问题 manipulation dexterous manipulation vision-language-action
17 Learning Wheel Motion Uncertainty for Degeneracy-Aware LiDAR-Inertial Odometry on Quadrupedal Wheel-Legged Robots 提出基于学习轮运动不确定性的LiDAR-惯性里程计以解决四足轮腿机器人定位问题 quadruped legged robot multimodal ✅
18 ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation 提出ScaleNav以解决语言条件下的本地导航问题 quadruped sim-to-real egocentric ✅
19 SWAP: Test-Time Steerable Humanoid Whole-Body Collision Avoidance 提出SWAP以解决人形机器人全身碰撞避免问题 humanoid humanoid robot Unitree ✅
20 Bio-inspired Thrust-Assisted Trotting on a legged-Aerial Robot via Real-Time QP-MPC 提出基于QP-MPC的控制器以实现腿部飞行机器人助推跑步 bipedal biped locomotion
21 Validation of Human Motor Development Scales with Humanoid Robots 利用人形机器人验证人类运动发展尺度的有效性 humanoid humanoid robot reinforcement learning
22 SkateNav: Learning Energy-Efficient Navigation through Adaptive Skating on Passive-Wheel Quadrupedal Robots 提出SkateNav以解决被动轮四足机器人能效导航问题 quadruped locomotion reinforcement learning ✅
23 GPT-6 Astra Is a Native Visuo-Tactile Policy for Contact-Rich Manipulation 提出GPT-6 Astra以解决接触丰富操控中的触觉感知问题 manipulation foundation model multimodal
24 Learn the Task, Not the Schedule: Reducing Spurious Cross-Arm Coupling in Bimanual Imitation Learning 提出约束保持时间重组方法以解决双手模仿学习中的虚假交叉臂耦合问题 bi-manual imitation learning diffusion policy ✅
25 Vision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic Manipulation 提出Vision-Language-Delta-Action以解决机器人操控中的状态变化建模问题 manipulation vision-language-action VLA
26 OV-PEAR: Observation-Verified Pose-Scale Estimation and Reconstruction for Unknown Industrial Manipulation Objects 提出OV-PEAR框架以解决未知工业物体的姿态和尺度估计问题 manipulation 3D reconstruction geometric consistency
27 ReInsVLN: Revisiting Historical Evidence for Training-Free Vision-and-Language Navigation 提出ReInsVLN以解决视觉语言导航中的历史信息冗余问题 quadruped humanoid VLN
28 ALIGN: Aligning Condition Estimation and Expression in Advantage-Conditioned Behavior Cloning 提出ALIGN框架以解决混合质量数据下的机器人行为克隆问题 manipulation behavior cloning vision-language-action
29 Long-Horizon Multi-Object Rearrangement via Distilled Tree Search over Continuous Actions 提出DISCO以解决长时间多物体重排问题 manipulation reinforcement learning policy learning
30 K-AoI: A Spatio-Temporal Synchronization Metric for Digital Twin-based Teleoperation in Dynamic Network Environments 提出K-AoI以解决数字双胞胎远程操作中的同步问题 teleoperation ✅
31 PhantomTac: Hijacking Robotic Tactile Systems with Deploy-and-forget Tags 提出PhantomTac以解决机器人触觉系统安全问题 manipulation multimodal
32 Tactile In-Hand Object Rotation: A Comparative Study of Hand Morphology in Simulation and Hardware 通过手部形态比较研究实现触觉驱动的物体旋转 manipulation reinforcement learning
33 RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models 提出RoboValue基准以统一评估机器人价值模型 manipulation policy learning ✅
34 Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy 提出PhysRSI-eval以量化物理递归自我改进能力 manipulation
35 CAOS-SLAM: Class-Agnostic Object-Aware Real-Time vSLAM for Dynamic Environments 提出CAOS-SLAM以解决动态环境下vSLAM的鲁棒性问题 motion planning
36 Learning from Fleet Experience: A Collective Learning Paradigm for Robots 提出集体经验学习以提升机器人政策可靠性 manipulation
37 SteerAct: Unlocking Action Models through Few-Shot Temporal Steering 提出SteerAct以解决机器人动作模型在少量样本下的优化问题 manipulation ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
38 Robotic Photography System based on Vision-Language-Action Model 提出RoboPhoto-VLA以解决机器人摄影中的美学与控制问题 direct preference optimization vision-language-action VLA
39 Learning Geometry-Aware Planning Representations for Monocular Flight with Cross-Modal Supervision 提出几何感知单目飞行规划框架以解决高速度导航问题 distillation 3D gaussian splatting 3DGS
40 CoopUQ: Robust Multi-Robot Social Navigation via Uncertainty-Aware Cooperative Forecasting 提出CoopUQ以解决多机器人社交导航中的不确定性问题 reinforcement learning occupancy grid spatiotemporal ✅
41 ForagerSim: Evaluating Embodied Map-Based Reasoning in Large-Scale Dynamic Worlds 提出ForagerSim以解决动态环境中地图推理问题 reinforcement learning embodied AI

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

#题目一句话要点标签🔗⭐
42 InteractAgent: Agentic Human Motion Interaction with Memory-Augmented Reflection 提出InteractAgent以解决长时间人机交互中的空间推理问题 open-vocabulary open vocabulary text-driven motion ✅
43 AnchorFlow-VIO: Fixed-Template Monocular Visual-Inertial Odometry on LaMAria 提出AnchorFlow-VIO以解决单目视觉惯性测程的局限性 VIO TAMP
44 Revealing and Bridging the Physical Executability Gap in Vision-Language Navigation 提出VeSTA框架以解决视觉语言导航中的物理可执行性差距问题 traversability VLN multimodal

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

#题目一句话要点标签🔗⭐
45 Cartender: Verifiable Language-Conditioned Driving by Learning the Drives Not Taken 提出Cartender以解决语言条件驾驶中的场景约束问题 instruction following language conditioned
46 AeroIntent: A Synchronized Multimodal Benchmark for UAV Mission Intent Recognition 提出AeroIntent基准以解决无人机任务意图识别问题 multimodal

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

#题目一句话要点标签🔗⭐
47 EgoRayFormer: Ray-Space Stereo Refinement for Egocentric 3D Human Pose Estimation 提出EgoRayFormer以解决头戴立体鱼眼相机的3D姿态估计问题 egocentric

⬅️ 返回 cs.RO 首页 · 🏠 返回主页