cs.RO（2026-09-17）

📊 共 89 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (66 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (11) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱三：空间感知与语义 (Perception & Semantics) (4) 支柱八：物理动画 (Physics-based Animation) (2) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (66 篇)

#题目一句话要点标签🔗⭐
1 Learning Slope-Adaptive Whole-Body Locomotion for Humanoid Robots in Roofing Construction 提出基于场景的全身运动学习框架以解决人形机器人屋顶施工问题 humanoid humanoid robot motion tracking
2 MoWAM: Explicit Future Motion Prediction for Efficient World Action Models 提出MoWAM以解决未来动态预测的计算效率问题 manipulation policy learning world action model
3 Towards High-DoF Dexterous Manipulation through VLA Post-Training 提出统一的后训练管道以解决高自由度灵巧操控问题 manipulation dexterous hand dexterous manipulation
4 DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation 提出DexTouch-WM以解决机器人触觉模型学习问题 manipulation dexterous manipulation policy learning
5 DR-MPC: Fast and Feasible Dynamics-Relaxed Model-Predictive Control for Legged Locomotion 提出DR-MPC以解决腿部运动控制中的动态约束问题 quadruped legged locomotion locomotion
6 Imagine-TAMP: Imagination-Guided Task and Motion Planning in Partial Observability 提出Imagine-TAMP以解决部分可观测环境中的任务与运动规划问题 manipulation motion planning task and motion planning
7 LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction 提出LYRIC以解决语言驱动的物理基础角色控制问题 humanoid behavior cloning flow matching ✅
8 CoRef-GS: Cooperative Referring Gaussian Splatting for Multi-Agent Scene Understanding 提出CoRef-GS框架以解决多智能体场景理解中的语言查询问题 quadruped gaussian splatting splatting ✅
9 Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control 提出SGPS以解决视觉策略学习中的计算成本问题 locomotion manipulation bi-manual
10 Affective Shared Autonomy: Temporal Affect Dynamics and Subjective Evaluation in Bimanual Teleoperation Tasks 提出情感共享自主框架以解决双手遥操作中的认知负担问题 motion tracking manipulation bi-manual
11 Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision 通过动作相似性监督提升潜在动作模型的跨体转移能力 bi-manual cross-embodiment embodiment transfer
12 HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface 提出HIL-UMI框架以解决机器人操作中的数据适应性问题 manipulation vision-language-action VLA
13 SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulation 提出SkipVLA以解决机器人操作中的效率问题 manipulation vision-language-action VLA
14 WorldContact: A Contact-Centric World Model for Scalable Robot Learning 提出WorldContact以解决机器人适应新任务的数据生成问题 manipulation world model world models
15 GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies 提出GeoAAC以解决固定动作时间窗适应性不足的问题 manipulation flow matching vision-language-action
16 Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control 提出Agile-WAM以解决接触丰富机器人控制中的效率问题 manipulation flow matching world action model ✅
17 AnyViewDex: View-Invariant Dexterous Manipulation from RGB Observations 提出AnyViewDex以解决多指灵巧操作中的视角敏感问题 manipulation dexterous manipulation reinforcement learning
18 OmniCalib: Target-Free, Task-Structured Self-Calibration for Humanoid Robots 提出OmniCalib以解决人形机器人自校准问题 humanoid humanoid robot visual odometry
19 Walking on the Slope: Stable Bipedal Gaits with Genetic-Algorithm-Optimized Trajectories 提出基于遗传算法优化的双足机器人稳定行走方案 bipedal biped
20 OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotion 提出OmniMimic以解决四足机器人运动风格多样性问题 quadruped locomotion
21 Compliance for Free: Learning Identifiable Impedance via Bilateral Teleoperation 提出四通道双向遥操作以解决机器人合规性识别问题 teleoperation vision-language-action VLA
22 Visual Sim-to-Real Learning for Robotic Insertion under Geometric Variations: Application to Rebar Installation 提出RebarSim以解决建筑工地钢筋插入问题 sim-to-real domain randomization reinforcement learning
23 MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving 提出MILER以解决无结构环境下的仿真到现实转移问题 sim-to-real reinforcement learning
24 LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation 提出LIFD框架以解决机器人操作中的3D场景记忆问题 manipulation representation learning OpenVLA
25 ReShoot: Generative Visual Domain Randomization of Recorded Robot Demonstrations for Visuomotor Policy Learning 提出ReShoot框架以解决机器人示范中的视觉过拟合问题 domain randomization policy learning
26 SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs 提出SmellDiffusion以解决气体泄漏导航问题 quadruped open-vocabulary open vocabulary
27 Quantifying Mechanical Intelligence in Legged Robots with Information Theory 提出信息论度量以量化腿部机器人机械智能 quadruped legged robot locomotion
28 Underwater Visual Target Tracking with Target-Specific Depth Estimation and Adaptive Model-Fusion Predictive Control 提出基于目标特定深度估计的水下视觉目标跟踪方法 MPC depth estimation
29 FlipToSee: A Probabilistic Stable Placement Prior for Active Visual Exploration via Regrasping 提出FlipToSee以解决主动视觉探索中的稳定放置问题 motion planning multimodal zero-shot transfer
30 Tele-Traversability: Rethinking Traversability for Teleoperated Ground Robots in Terrain Navigation 提出人本可操作性以解决遥控地面机器人导航问题 teleoperation traversability
31 UniExo: Unified Multi-Skill Policies for Musculoskeletal Locomotion and Co-Adaptive Exoskeleton Control 提出UniExo框架以解决多技能步态与外骨骼控制的统一问题 locomotion reinforcement learning
32 Learning Foresight without Explicit Trajectories for 3D Diffusion Policies 提出运动趋势引导以解决3D扩散策略的前瞻性问题 manipulation diffusion policy
33 TADreamer: Zero-Shot Language-Guided 3D Navigation for Terrestrial-Aerial Bimodal Robots via Video Imagination 提出TADreamer以解决双模机器人零-shot语言引导导航问题 locomotion dreamer
34 Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation 提出SafeHarness以解决机器人操作中的安全问题 manipulation
35 V2-STRep: VLM-Grounded Structured Task Representations for Reusable Robot Skills Acquired from Generated Videos 提出V2-STRep以解决机器人技能重用问题 manipulation trajectory optimization motion planning
36 Resilient Motion Planning for Free-Flying Space Robots under Actuator Failures 提出一种鲁棒运动规划框架以应对自由飞行空间机器人中的驱动器故障 motion planning
37 Mechanical Precision Weeding with a Quadruped Robot 提出基于四足机器人机械除草的新方法以解决化学除草问题 quadruped
38 MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation 提出MaskHarness-WAM以解决长时间机器人操作中的目标跟踪问题 manipulation
39 Distributed Model Predictive Control with Connectivity-based Contracts 提出基于连通性合同的分布式模型预测控制以解决机器人协调问题 model predictive control
40 TacSushi: Tactile-Grounded World-Action Modeling for Dexterous Sushi Manipulation 提出TacSushi以解决精细寿司操控中的不确定性问题 manipulation
41 SLAMSqueezeBench: Comparing SLAM Systems under Resource Constraints 提出SLAMSqueezeBench以解决SLAM系统在资源约束下的比较问题 manipulation gaussian splatting splatting
42 RotateIt! Fast and Reliable Single-Arm Garment Unfolding via Online-Adaptive Dynamic Rotation 提出RotateIt!以解决单臂机器人服装展开问题 manipulation bi-manual
43 Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision 提出轻量级工作空间模型以解决机器人记忆问题 manipulation
44 RoboFind: Multi-Agent Personalized Object Search for People Who Are Blind or Have Low Vision 提出RoboFind以解决盲人及低视力者的个性化物体搜索问题 quadruped
45 Universal Navigation Interface: Robot-Free Data for Wheeled Robot Navigation 提出通用导航接口以解决机器人导航数据收集难题 teleoperation
46 Graph-Based Design of Soft Grippers with Multi-Objective Quality-Diversity Optimisation 提出基于图的设计方法以优化软抓手的多目标质量多样性 manipulation
47 VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control 提出VA-Bench以评估具身空间智能的观察-推理-行动循环 dual-arm
48 Learning Scene-Aware Humanoid Locomotion through 3D Clutter from Immersive Human Demonstrations 提出MTC框架以解决复杂环境中的人形机器人运动问题 humanoid humanoid locomotion locomotion
49 DEXTERA: From a Single Image to Deployable Dexterous Manipulation via Real-to-Sim-to-Real 提出DEXTERA以解决机器人灵巧操作的数据收集问题 manipulation dexterous manipulation sim-to-real
50 DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation 提出DexTouch-WM以解决机器人操控中的触觉数据稀缺问题 manipulation dexterous manipulation policy learning
51 ForeTac-VLA: A Forecasting-Based Tactile-Vision-Language-Action Model for Contact-Rich Robotic Manipulation 提出ForeTac-VLA以解决接触丰富环境下的机器人操控问题 manipulation vision-language-action VLA
52 SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulation 提出SkipVLA以解决机器人操作中的延迟问题 manipulation vision-language-action VLA
53 Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs 提出VLA-Feedback以解决动态场景下的实时反馈去噪问题 manipulation vision-language-action VLA
54 OmniCalib: Target-Free, Task-Structured Self-Calibration for Humanoid Robots 提出OmniCalib以解决人形机器人自校准问题 humanoid humanoid robot visual odometry
55 Same World, Different Knowledge: When Isolated Audits Misjudge World-Model Repairs 提出信息接口审计以解决世界模型修复中的误判问题 model predictive control world model world models
56 WM-VS: Progress-Aligned World Models for Closed-Loop Visual Servoing 提出WM-VS框架以解决闭环视觉伺服中的预测控制不匹配问题 trajectory optimization world model world models
57 LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation 提出LIFD框架以解决机器人操作中的3D场景记忆问题 manipulation representation learning OpenVLA
58 SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs 提出SmellDiffusion以解决四足机器人气体泄漏导航问题 quadruped open-vocabulary open vocabulary
59 MetaPusher: Meta Learning and Planning for Nonprehensile Manipulation of Unseen Objects with Rapid Online Adaption 提出MetaPusher以解决未见物体的非抓取操控问题 manipulation sim-to-real reinforcement learning
60 Dynamics-Induced Commitment in Learning-Based Robotic Penalty Kicks 提出动态诱导承诺映射以优化机器人罚球策略 quadruped humanoid whole-body control ✅
61 Constraint-Unified MPC for Over-Actuated Surface Vehicles with Post-Detection Fault Reconfiguration 提出统一约束MPC以解决过驱动水面车辆故障重配置问题 MPC
62 Shake to Learn: Dynamic Interrogation of Hidden Object Physics for Robotic Manipulation with Physical Reservoir Computing 提出动态干预方法以解决机器人操控中的隐藏物理属性问题 manipulation
63 SAGE: Safety-Aligned Gradient Enforcement for Human--Robot Collaboration 提出SAGE以解决人机协作中的安全性与可解释性问题 humanoid humanoid robot reinforcement learning
64 Diverse and Adaptable Arm Coordination for Octopus-Crawling via Diffusion-Based Uncertainty-Aware Optimization 提出基于扩散的不确定性优化算法以解决章鱼爬行控制问题 locomotion shared control
65 Square Root Gauss-Newton iLQR 提出平方根Gauss-Newton iLQR以优化非线性轨迹问题 trajectory optimization
66 RoboFind: Multi-Agent Personalized Object Search for People Who Are Blind or Have Low Vision 提出RoboFind以解决盲人和低视力用户的个性化物体搜索问题 quadruped

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
67 Recovering Aggressively Pruned Vision-Language-Action Models with Offline Hidden-State Distillation 提出离线隐状态蒸馏以恢复大幅剪枝的视觉-语言-动作模型 reinforcement learning distillation vision-language-action
68 TraceFlow: Guiding Frozen Flow-Matching Robot Policies with Success and Failure Traces 提出TraceFlow以优化机器人策略的成功与失败轨迹 flow matching vision-language-action VLA
69 Learning Reliable Parking Policies via Offline Reinforcement Learning with Quantized Action Representations 提出离线强化学习框架以解决城市环境下自动泊车问题 reinforcement learning offline reinforcement learning conservative q-learning
70 Feeling Terrain Before Crossing: World Models for Off-Road Navigation 提出Feel-WM以解决越野导航中的机器人感知问题 world model world models
71 EmbodiedMind: Adaptive Data Curation and Prefix-Tree Reinforcement Learning for Efficient Embodied Intelligence 提出EmbodiedMind以解决嵌入式智能训练中的数据利用效率问题 reinforcement learning foundation model
72 RTK-Vision PPO for Autonomous Micro UAV Recovery on an Airborne Carrier 提出RTK-Vision PPO框架以实现自主微型无人机在空中载体上的回收 reinforcement learning PPO
73 Hybrid Residual Reinforcement Learning for Contact-Rich Robotic Book Insertion 提出混合残差强化学习以解决接触丰富的机器人书籍插入问题 reinforcement learning PPO
74 StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation 提出StageGuard以解决长时间机器人任务的阶段转换问题 distillation
75 Semantic SLAM in Precision Agriculture using Bayesian Inference 提出基于贝叶斯推断的语义SLAM框架以解决精准农业问题 world model world models
76 GR2PO: Group Relative Return Policy Optimization for Continuous Robot Control 提出GR2PO以解决连续机器人控制中的价值网络依赖问题 reinforcement learning policy learning
77 Demonstration Synthesis from a Single Scan via Gaussian Splatting for Visuomotor Policy Learning 提出GaussianFactory以解决演示合成成本高的问题 policy learning diffusion policy 3D gaussian splatting

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
78 Co-VLA: Consensus-based Federated Training for Vision-Language-Action Models 提出Co-VLA以解决异构机器人数据分布下的联合训练问题 vision-language-action VLA
79 Navi-Agent: Unlocalized Monocular Navigation Agent 提出Navi-Agent以解决未知环境中的视觉语言导航问题 VLN
80 GPT-6-Astra in a Navigation Workflow: Behavioral Analysis in Zero-Shot Vision-and-Language Navigation in Continuous Environments 提出GPT-6-Astra以解决零-shot视觉语言导航问题 VLN
81 Navi-Agent: Unlocalized Monocular Navigation Agent 提出Navi-Agent以解决未知环境中的导航问题 VLN
82 How Far Can GPT-6-Astra Go? Evaluating Capabilities in Zero-Shot Vision-and-Language Navigation 提出GPT-6-Astra以解决零-shot视觉语言导航问题 VLN

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

#题目一句话要点标签🔗⭐
83 HEROIC: Heterogeneous Evidential Reasoning for Open-Vocabulary Identification and Cross-Robot Collaboration 提出HEROIC框架以解决多机器人协作中的开放词汇识别问题 open-vocabulary open vocabulary
84 Worst-Case Hidden-Vehicle Trajectory Search in Spatiotemporal Occlusion Regions 提出HC-MTS以解决自主驾驶中的遮挡区域最坏情况轨迹搜索问题 semantic map spatiotemporal
85 PIVOT: Physically Informed Vision-Language Off-Road Traversability for Field Robot Navigation 提出PIVOT系统以解决野外机器人导航中的地形评估问题 traversability
86 Noctif3R: Feed-Forward Monocular Real-Time SLAM for Photon-Limited Scenes on Embedded Hardware 提出Noctif3R以解决低光照环境下的实时单目SLAM问题 DROID-SLAM VGGT

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
87 Bayesian Continuum Robot Dynamics and State Estimation 提出基于贝叶斯方法的连续机器人动力学与状态估计 spatiotemporal
88 Adapting Rigid-Body Dynamics Derivatives for Constraint Embedding Closed-Chain Models 提出适应刚体动力学导数的约束嵌入闭链模型算法 differentiable simulation

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

#题目一句话要点标签🔗⭐
89 INSPECT: Learning Robot View Selection from Assistant Use 提出INSPECT以解决机器人视角选择问题 egocentric ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页