cs.RO（2026-07-20）

📊 共 74 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (48 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (9) 支柱三：空间感知与语义 (Perception & Semantics) (8) 支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (48 篇)

#题目一句话要点标签🔗⭐
1 Handroid: Bridging Dexterous Hand and Humanoid 提出Handroid以整合灵巧手与类人机器人功能 humanoid humanoid robot humanoid locomotion
2 A Systematic Study of Large Language Models for Task and Motion Planning With PDDLStream 提出16种算法以优化任务与运动规划中的大语言模型应用 motion planning large language model task and motion planning
3 Worlds in One Demo: A Synthetic Data Engine for Learning Open-World Mobile Manipulation 提出WANDA以解决开放世界移动操控数据收集问题 manipulation mobile manipulation motion planning
4 RAVEN: Reinforcement-Adaptive Visibility-Graph Planning for Robust Humanoid Navigation with Collision-Free MPC 提出RAVEN以解决动态环境下人形机器人导航问题 humanoid locomotion MPC
5 Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories 提出Xiaomi-Robotics-1以解决机器人在未知环境中的任务执行问题 manipulation mobile manipulation vision-language-action
6 Interaction-Aware Whole-Body Control for Compliant Object Transport 提出交互感知的全身控制方法以解决物体运输问题 humanoid whole-body control WBC
7 VTAP Gripper: Synergizing Fingertip Sensing and a Visuo-Tactile Active Palm for Dexterous In-Hand Manipulation 提出VTAP抓手以解决灵巧抓取与操作问题 manipulation in-hand manipulation teleoperation
8 AC-VLA: Robust Out-of-Distribution Action Execution via Compositional Learning 提出AC-VLA以解决机器人操作中的OOD泛化问题 manipulation vision-language-action VLA
9 Let the Body Follow: Coupled Egocentric Control for Whole-Body Robot Teleoperation 提出耦合自我中心控制以解决全身机器人遥操作协调问题 manipulation teleoperation egocentric
10 NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception 提出NeuralActuator以解决机器人动力学与外部力感知问题 sim-to-real actuator dynamics teleoperation
11 SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training 提出SLAC以解决高自由度机器人强化学习的安全与效率问题 manipulation mobile manipulation bi-manual
12 IMBench: A Benchmark for Intuitive Robotic Manipulation 提出IMBench以解决直观机器人操控能力评估问题 manipulation vision-language-action foundation model
13 Simultaneous Calibration of Noise Covariance and Kinematics for State Estimation of Legged Robots via Bi-level Optimization 提出双层优化框架以解决腿式机器人状态估计中的噪声协方差和运动学标定问题 quadruped legged robot humanoid
14 RhinoVLA Technical Report 提出RhinoVLA以解决边缘硬件上VLA模型实时部署问题 manipulation vision-language-action VLA
15 Difference-Based Relational Learning for Zero-Shot Object-Goal Visual Navigation With Direct Sim-to-Real Transfer 提出T-DRN以解决零-shot目标视觉导航中的sim-to-real问题 sim-to-real reinforcement learning deep reinforcement learning
16 A Task-Space Receding Horizon Controller for Fast Collision Avoidance 提出任务空间递归视野控制器以解决快速避障问题 sim-to-real MPC model predictive control
17 Dynamics-Aware Meta-Imitation for Generalization to Unseen Robotic Manipulation 提出动态感知元模仿框架以解决机器人操作泛化问题 manipulation imitation learning multimodal
18 Connectivity Maintenance and Recovery for Multi-Robot Motion Planning 提出基于Bézier的运动规划算法以解决多机器人连通性维护问题 MPC motion planning traversability
19 Data and Learning Where it Matters for Contact-Rich Manipulation 提出针对接触丰富操作的自动化数据收集方法以提升精度 manipulation reinforcement learning deep reinforcement learning
20 EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot Navigation 提出EmbodiedDiffusion以解决异构机器人导航中的可 traversability 估计问题 quadruped traversability
21 Robust and Efficient MuJoCo-based Model Predictive Control via Web of Affine Spaces Derivatives 提出WASP导数以提升MuJoCo模型预测控制的效率与鲁棒性 MPC model predictive control
22 PACE: Persona Adaptation through Conversational Elicitation in Human-Robot Interaction 提出PACE框架以解决人机交互中的个性化适应问题 humanoid humanoid robot multimodal
23 NeuroCommitSSM: Decision-Centric Shared Autonomy for Safe Assistive Manipulation via EEG-EMG-ET Commit Readiness 提出NeuroCommitSSM以解决安全辅助操控中的决策执行问题 manipulation
24 Multi-Objective Kinodynamic Motion Planning with Asymptotic Pareto Optimality 提出统一算法框架以解决多目标运动规划问题 motion planning
25 BayesContact: Uncertain Pose Estimation via Visuo-Tactile Proposals and Simulation-based Inference 提出BayesContact以解决不确定姿态估计问题 manipulation multimodal
26 Sym2Real: Symbolic Dynamics with Residual Learning for Data-Efficient Adaptive Control 提出Sym2Real框架以解决低级控制器适应性不足问题 sim-to-real sim2real
27 MuxGel: Simultaneous Dual-Modal Visuo-Tactile Sensing via Spatially Multiplexing and Deep Reconstruction 提出MuxGel以解决视觉与触觉传感融合问题 manipulation sim-to-real
28 VTLoc: Learning-based Tactile Contact Localization in Visual Point Clouds 提出VTLoc以解决视觉与触觉接触定位问题 manipulation
29 Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation 提出持久对象标记化方法以解决人形机器人长时间操控问题 humanoid manipulation loco-manipulation
30 MEVION: Low-Cost Open-Source Data Collection System for Powerful and High-Speed Dual-Arm Manipulation 提出MEVION以解决双臂机器人数据收集的高成本与低效问题 quadruped manipulation dual-arm ✅
31 Isaac Sim-to-Real: Reinforcement Learning based Locomotion for Quadrupeds 提出基于强化学习的四足机器人运动控制框架以解决仿真与现实间的差距 quadruped legged locomotion whole-body control
32 FM-VLA: Force-based Memory for Vision-Language-Action Models in Contact-Rich Manipulation 提出FM-VLA以解决接触丰富操作中的时间上下文推理问题 manipulation vision-language-action VLA ✅
33 RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model 提出RynnBrain 1.1以提升机器人感知与推理能力 manipulation Unitree cross-embodiment
34 Optimization of sim-to-real transfer in the humanoid robot NICO 提出基于YOLO的物体检测优化NICO机器人抓取能力 humanoid humanoid robot sim-to-real
35 From Sign Language Generation to Humanoid Execution: Vision-Language Guided Retargeting with Collision Mitigation 提出基于视觉语言的重定向方法以解决手语生成中的碰撞问题 humanoid humanoid robot physically plausible
36 Predictive Training with Latent Imagination for Visual Quadruped Navigation 提出预测训练与潜在想象以解决视觉四足机器人导航问题 quadruped legged robot sim-to-real
37 Imitation of Arm Gestures by the Semi-Humanoid Robot NICO 提出基于MediaPipe的手臂动作模仿系统以提升人机交互 humanoid humanoid robot
38 Task-Space Constrained Stochastic Trajectory Optimization for Time-Optimal Forestry Crane Motion Planning 提出TSC-VP-STO以解决林业起重机运动规划中的时间最优问题 trajectory optimization motion planning
39 HCPG-Flow:Hierarchical Contact-Progress Guidance for Flow-Policy Robot Manipulation 提出HCPG-Flow以解决机器人操作中的动作选择问题 manipulation SAC multimodal ✅
40 World Translation: Minimizing Sim-to-Real Gap with Backward Dynamics Extraction and Unpaired Domain Translation 提出世界翻译以解决仿真与现实间的差距问题 quadruped humanoid sim-to-real
41 RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning 提出RoboHarness以解决异构机器人策略的长时间规划问题 model predictive control motion planning VLA
42 Learning Adaptive Safety Margins for Visual Navigation 提出自适应安全边际学习方法以解决机器人视觉导航问题 humanoid Unitree teacher-student
43 Manifold-Guided Motion Planning for Tight Assemblies 提出CMG-RRT以解决紧凑装配中的运动规划问题 motion planning
44 ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation 提出ConceptTree框架以解决机器人操控决策透明性问题 manipulation
45 Finite-Time Curvature-Constrained Vector Field for Saturation-Free Motion Planning of Nonholonomic Robots 提出有限时间曲率约束向量场以解决非完整机器人运动规划问题 motion planning
46 Disturbance-Aware Flight for Aerial Robots in Narrow Space 提出一种干扰感知飞行框架以解决狭窄空间中的自主飞行问题 model predictive control motion planning
47 Predicting Grasping Compliance in Robotic Hands through Analytical-Model-Informed Neural Networks 提出基于分析模型的神经网络以解决机器人抓取合规性问题 manipulation predictive model
48 Technical Design Review of Duke Robotics Club's Oogway & Crush: AUVs for RoboSub 2026 提出Oogway与Crush以实现RoboSub 2026的多目标自主任务 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
49 Human-Inspired Neuro-Symbolic World Modeling and Logic Reasoning for Interpretable Safe UAV Landing Site Assessment 提出NeuroSymLand以解决无人机安全着陆场地评估问题 world model world models large language model
50 Learning Reach-Avoid Task with Reinforcement Learning: Vectorized Simulation and Benchmark 提出基于深度强化学习的复杂环境下的达避任务基准 reinforcement learning deep reinforcement learning DRL
51 GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch 提出GigaWorld-Policy-0.5以提高机器人控制的推理效率 policy learning world model world models
52 Risk-Aware Preference Learning for Stochastic Outcomes 提出风险感知偏好学习以解决机器人导航中的安全问题 preference learning
53 AEGIS: Assay-Aware Protocol Validation and Runtime Monitoring for Open-Source Liquid Handling Robots 提出AEGIS以解决开放源代码液体处理机器人中的协议验证与监控问题 world model world models
54 VLN-AVP: Zero-Shot Vision-Language Navigation with Hybrid Long-Short-Term Memory for Autonomous Valet Parking 提出VLN-AVP以解决自主代客泊车中的地图依赖问题 policy learning open-vocabulary open vocabulary
55 Patch Policy: Efficient Embodied Control via Dense Visual Representations 提出Patch Policy以高效利用密集视觉特征解决机器人控制问题 representation learning visual pre-training vision-language-action
56 GeoWorldAD: Geometry World Action Model for Autonomous Driving 提出GeoWorldAD以解决自主驾驶中的几何基础规划问题 world model world models world action model
57 Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation 提出无训练选择性测试时间缩放框架以优化机器人控制决策 world action model world action models foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (8 篇)

#题目一句话要点标签🔗⭐
58 Instance-Enriched Semantic Maps for Visual Language Navigation 提出实例丰富的语义地图以解决视觉语言导航中的对象细节不足问题 semantic map open-vocabulary open vocabulary
59 Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps 提出视觉-语言-运动地图以解决动态场景查询问题 open-vocabulary open vocabulary
60 Beyond Frontiers: Scene-Anomaly Guided Autonomous Exploration 提出SCAGE框架以解决3D环境探索中的结构异常问题 3D reconstruction
61 ContactFusion: Stochastic Poisson Surface Maps from Visual and Contact Sensing 提出ContactFusion以解决机器人装配中的接触感知问题 scene understanding
62 Distilling Global Traversability Priors for Image-based Affordance Prediction in Off-road Environments 提出基于图像的可行性预测方法以解决越野导航问题 traversability affordance first-person view
63 Does Robust VIO Need More Learning? Geometry-Verified Visual Measurements under Distribution Shift 提出最小学习立体VIO框架以应对分布变化问题 VIO
64 Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking 提出Seg2Grasp以解决动态环境下的吸力抓取问题 open-vocabulary open vocabulary
65 SLAM in Low-Light Environments: Project Report 提出低光照环境下SLAM系统的性能评估与改进方案 VIO feature matching

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
66 Think at 5 Hz, Act at 20 Hz: Asynchronous Fast-Slow Vision-Language-Action Inference for Closed-Loop Driving 提出快速-慢速视觉-语言-动作推理架构以解决闭环驾驶延迟问题 vision-language-action large language model instruction following
67 Can LLMs Prove Robotic Path Planning Optimality? A Benchmark for Research-Level Algorithm Verification 提出基准评估以验证机器人路径规划算法的最优性 large language model chain-of-thought
68 Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference 提出Jetson-PI以解决低功耗设备上VLA模型的实时控制问题 vision-language-action VLA
69 A Generative Partially Specified Finite State Machine Approach to Complex Behaviour Planning 提出生成部分指定有限状态机以解决复杂行为规划问题 large language model
70 EGO: a Recursive and Self-Referential Cognitive Architecture for Artificial General Intelligence 提出EGO架构以克服现有AGI系统的局限性 large language model
71 Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models 提出视觉-语言-动作模型的推理机制以增强鲁棒性 vision-language-action VLA chain-of-thought

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
72 Holistic Fusion: Task- and Setup-Agnostic Robot Localization and State Estimation with Factor Graphs 提出Holistic Fusion以解决机器人定位与状态估计问题 motion estimation multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
73 Scalable Open-Source Visuotactile Sensor for 6-Axis Contact Wrench Estimation in Tensegrity Robots 提出可扩展的开源视觉触觉传感器以解决紧张结构机器人接触扭矩估计问题 contact-aware

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
74 Continuously Stable Structure through Plastic Deformation 提出连续稳定结构以解决软抓手稳定性问题 PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页