cs.RO（2026-10-05）

📊 共 50 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (29 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (6) 支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (29 篇)

#题目一句话要点标签🔗⭐
1 I-BFM: Reward-Conditioned Robust Humanoid Interaction via Unsupervised Reinforcement Learning 提出I-BFM以解决人形机器人与物体交互的挑战 humanoid whole-body control motion tracking
2 Dataset-Free Compliant Humanoid Loco-Manipulation with Dynamic Online Posture 提出OCLO以解决无数据依赖的人形机器人运动控制问题 humanoid manipulation loco-manipulation
3 InterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation 提出InterMimicGen以解决人形机器人运动模仿的稀疏性问题 humanoid humanoid robot manipulation
4 Hierarchical Reinforcement Learning for Collision-Free Locomotion of an Underactuated Biped 提出层次化强化学习以解决双足机器人避障问题 bipedal biped locomotion
5 Transporting Unsecured Stacked Payloads with a Quadrupedal Robot via Multi-Objective Reinforcement Learning 提出PAMORT以解决四足机器人运输不稳定负载问题 quadruped legged robot locomotion
6 Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models 提出ACG-Bench以解决双臂协作中的技能重组问题 dual-arm vision-language-action VLA
7 Talk, Render, Act: Integrating Social Gesture and Digital Face with Synchronized Speech for Conversational Humanoid Robot 提出TRABot框架以解决人形机器人多模态交互问题 humanoid humanoid robot motion planning
8 DexForge: High-Fidelity Physics-Informed Dexterous Retargeting 提出DexForge以解决高保真机器人运动重定向问题 manipulation dexterous hand dexterous manipulation ✅
9 When to Switch: Reliable Action-Chunk Extension for Vision-Language-Action Models 提出RACE框架以解决VLA模型中的动作切换不可靠问题 manipulation vision-language-action VLA ✅
10 Demonstration-Calibrated Port-Hamiltonian Retuning for Manipulation Policies 提出PHRetune以优化操作策略的控制增益 manipulation diffusion policy VLA
11 Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action Chunks 提出条件轨迹峰值以解决多模态模仿学习问题 dual-arm imitation learning multimodal
12 DASH: A da Vinci Adapter for Serial-link and Humanoid Robots as an Accessible Platform for Surgical Robotics Research 提出DASH以解决外科机器人研究平台的可及性问题 humanoid humanoid robot
13 Future Anchored Verification and Online Recovery for World Action Models 提出FAVOR框架以解决WAM执行漂移问题 manipulation world action model world action models
14 From Social Reasoning to Embodied Interaction: An Agentic Framework for Social Robots 提出ARISE框架以解决社交机器人互动中的多模态理解问题 humanoid humanoid robot foundation model
15 Dynamics-Aware Adaptive Corridors with Feasibility-Perturbed Trust-Region SQP for Certified Nonholonomic Motion Planning 提出动态感知自适应走廊以解决非完整运动规划问题 motion planning penetration
16 Dual Variational Autoencoders for Efficient Sim-to-Real Transfer in Low-Cost Robotic Navigation 提出双变分自编码器以解决低成本机器人导航的仿真到现实转移问题 sim-to-real domain randomization
17 Bilinear Flow Policy: Distributional Extrapolation for Goal-Conditioned Visuomotor Imitation 提出双线性流策略以解决目标条件模仿学习中的分布外推问题 manipulation imitation learning flow matching
18 Virtual model control for compliant reaching under uncertainties 提出虚拟模型控制以解决不确定环境下的机器人到达问题 legged robot humanoid humanoid robot
19 Execution-Aligned Progressive Noise for Consistent Asynchronous Replanning in Generative Robot Policies 提出执行对齐渐进噪声以解决生成机器人策略中的异步重规划问题 manipulation bi-manual multimodal
20 Physics Residual Dynamics and Reduced Order Whole-Body Planning for Obstacle Aware Human Robot Cloth CoTransportation 提出一种层次化规划框架以解决人机协作运输中的障碍物识别问题 whole-body control dual-arm MPC
21 Towards Robust Prehensile Manipulation in Open-Ended Environments 提出基于质量多样性算法的机器人抓取方法以应对开放环境 manipulation
22 Towards Quadruped-Provided Localization and Active Tracking for Micro-UAVs 提出基于四足机器人定位与主动跟踪的微型无人机解决方案 quadruped
23 Robotizing Human Videos with Physically Consistent Interactions 提出基于物理一致性交互的视频机器人化方法以解决人机交互问题 manipulation diffusion policy
24 Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning 提出Mulligan以解决机器人学习中的数据收集效率问题 manipulation imitation learning
25 Benchmarking Generative Trajectory Models for Active-Inference Control 提出生成主动推理控制模型以解决复杂系统控制问题 manipulation flow matching
26 Learning Coordinated Visuomotor Box-Pushing from Solo Demonstrations 提出基于单机器人演示的多机器人协调推箱方法 manipulation imitation learning
27 AffordCraft: Scalable Construction of Task-Ready Simulation Assets from Single Images 提出AffordCraft以解决机器人学习中的物体建模问题 manipulation
28 MagServo: Uncertainty-Resilient Hierarchical Magnetic Servoing via Learned Latent Representations 提出MagServo以解决磁导航中的不确定性问题 model predictive control
29 FreeSpeed: Training-Free Speed Control for Generative Robot Policies 提出FreeSpeed以解决机器人策略执行速度调整问题 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
30 SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models 提出SimForcing以解决机器人世界模型的运动知识转移问题 policy learning world model world models ✅
31 How (and How Not) to Use Data Augmentation in VLA Post-Training 提出图像增强策略以提升VLA后训练的泛化能力 reinforcement learning vision-language-action VLA
32 Visual Swarm Navigation via Deep Reinforcement Learning and Evolutionary Hybrid Design 提出一种混合设计方法以解决群体机器人自主视觉导航问题 reinforcement learning deep reinforcement learning
33 Adaptive Mean Flow for Responsive Closed-Loop Robot Control 提出自适应均值流以解决机器人控制中的延迟问题 imitation learning flow matching multimodal ✅
34 The Unexpired Plan: A Free Monitor for Accelerated Diffusion Policies 提出一种免费监控机制以加速扩散策略的训练 diffusion policy
35 End-to-End Safe Social Navigation via Multi-Task Reinforcement Learning and Probabilistic Perception 提出JESSI框架以解决自主社交导航中的安全与效率问题 reinforcement learning
36 GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories 提出GAMBIT以解决多机器人轨迹规划问题 reinforcement learning imitation learning

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

#题目一句话要点标签🔗⭐
37 Controllable and Photorealistic Pedestrian Risky Motion Generation for End-to-End Driving Safety Evaluation 提出ControlPed框架以解决行人风险动作生成问题 3D gaussian splatting 3DGS gaussian splatting
38 FOCUS: Fine-Grained Open-Vocabulary Change Detection for Uncertainty-Aware Semi-Static Scenes 提出FOCUS框架以解决半静态场景中的对象级变化检测问题 3DGS open-vocabulary open vocabulary
39 Human-in-the-Loop Neuro-Symbolic Drift Anticipation for Reliable Visual SLAM 提出人机协作神经符号框架以解决视觉SLAM漂移问题 visual SLAM large language model
40 Odyssey: A Closed-Loop Benchmark for Long-Horizon Real-World Driving with Explicit Navigation Routes 提出Odyssey基准以解决长时间驾驶评估问题 3DGS vision-language-action VLA
41 Traversability-Aware Cooperative Path Planning for Human-UGV Casualty Evacuation 提出人机联合路径规划以优化救援任务效率 traversability
42 Propagating Elevation-Map Uncertainty Through the Contact Maximum in Closed Form 提出闭式传播方法以解决不确定性地图中的接触最大值问题 elevation map

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

#题目一句话要点标签🔗⭐
43 VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models 提出VLA-ZO以解决视觉-语言-动作模型适应性问题 vision-language-action VLA
44 Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies 揭示视觉-语言机器人策略中的基础差距问题 vision-language-action VLA instruction following
45 What the Guard Misses, the Robot Executes: Implied Harm in VLA Instructions 提出监控机制以解决VLA模型隐含危害问题 vision-language-action VLA
46 Inspect Robots: Evaluating the Capabilities and Safety of Embodied AI 提出Inspect Robots框架以评估具身AI的能力与安全性 embodied AI
47 Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors? 探讨VLAs是否真正理解物体属性或仅仅重放学习行为 VLA
48 Recursive Video In-Context Learning for Agentic Robot 提出递归视频上下文学习以提升机器人任务执行能力 vision-language-action VLA

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
49 Infant simulator with an embodied caregiver: Generating infant-perspective touch and vision during social interaction 提出多模态婴儿模拟器以增强护理者-婴儿互动研究 dyadic interaction egocentric egocentric vision

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

#题目一句话要点标签🔗⭐
50 MarvisNav: Making Memory Visible on Route Choices for Zero-Shot Object Navigation 提出MarvisNav以解决零-shot物体导航中的记忆可视化问题 egocentric ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页