cs.RO（2026-10-22）

📊 共 55 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (34 🔗6) 支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱三：空间感知与语义 (Perception & Semantics) (5 🔗1) 支柱七：动作重定向 (Motion Retargeting) (4)

🔬 支柱一：机器人控制 (Robot Control) (34 篇)

#题目一句话要点标签🔗⭐
1 LocoManiLab: A Unified Testbed for Data, Policies, Controllers, and Deployment in Humanoid Loco-Manipulation 提出LocoManiLab以解决人形机器人运动与操作协调问题 humanoid humanoid robot locomotion
2 In-Context Learning World Models for Robot Dual-Arm Manipulation of Soft Garment with Partial Observations 提出软物体世界模型以解决机器人双臂操控挑战 manipulation bi-manual dual-arm
3 Robot Motion Transition with Human Motion Prior 提出STAMP框架以解决人形机器人运动过渡问题 humanoid motion tracking locomotion ✅
4 Memory before Goal: Role of Pre-History Memory for Humanoid Loco-Manipulation 提出WholeBodyMem以解决动态场景下人形机器人操控问题 humanoid manipulation loco-manipulation
5 Adaptive Aerial Loco-Manipulation Policy Learning via LLM-Assisted Proactive Task Generation 提出ALMA框架以解决空中运动操控中的动态控制问题 manipulation loco-manipulation policy learning
6 Progress Probes $P^2$: Lightweight Runtime Monitoring for Vision-Language-Action Models 提出轻量级监控方法以解决VLA模型的运行时监控问题 manipulation vision-language-action VLA
7 FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models 提出FocusVLA以解决VLA模型动态视图依赖不足问题 manipulation spatial relationship vision-language-action
8 PATH: Preference-Aware Traversability Estimation for Robotic Teleoperation in Off-Road Navigation 提出PATH-Net以解决越野导航中的可 traversability 估计问题 teleoperation reinforcement learning inverse reinforcement learning
9 Echo: Coupled Action and Task Status Signal Denoising for Vision Language Action Models 提出Echo框架以解决任务状态信号与动作生成的集成问题 manipulation vision-language-action VLA
10 Humanoid Mobility via Attention-based Contacts 提出基于注意力的接触规划以解决类人机器人运动问题 humanoid locomotion reinforcement learning
11 Revisiting Distribution Matching for State-to-Vision Policy Distillation in Laparoscopic Robotic Manipulation 提出状态到视觉的策略蒸馏以解决腹腔机器人操作中的挑战 manipulation reinforcement learning imitation learning
12 SCOPE: Scene-graph Construction Optimized by Plan Error-correction for Robot Long-term Planning Datasets 提出SCOPE以解决机器人长远规划数据集生成问题 motion planning large language model task and motion planning
13 FastHarness: Experience-Driven Review Scheduling for Vision-Language-Action Policies 提出FastHarness以解决机器人系统执行监控效率问题 manipulation vision-language-action
14 Continuous-Time Motion Planning and Steering with Global Convergence 提出GlobMP以解决连续时间运动规划问题 humanoid bi-manual motion planning
15 RGraph-Eval: Task-Grounded Scene Graphs for Evaluating Robot Video Generation 提出RGraph-Eval框架以解决机器人视频生成评估问题 manipulation foundation model multimodal ✅
16 UniFlowWAM: A Unified World-Action Model with Visual Semantics and 4D Geometry 提出UniFlowWAM以解决机器人演示中的3D场景流问题 manipulation bi-manual bimanual manipulation
17 TEAR: Task-Evidence Authority Routing for Robotic Manipulation 提出TEAR以解决机器人操作中的控制权分配问题 manipulation teleoperation
18 Co^2Gen: Collaboratively Generating Task Plans for Decentralized Multi-Robot and Human Collaboration 提出Co^2Gen框架以解决多机器人与人类协作任务规划问题 teleoperation cross-embodiment VLA
19 AstroBench: Benchmarking Free-Floating Capture and Space Robotic Manipulation 提出AstroBench以解决太空机器人抓取与操作问题 manipulation ✅
20 Live Thread Reconstruction for Autonomous Manipulation 提出实时线缆重建方法以解决自主操控中的缠绕问题 manipulation
21 OpenTac: An Open Ecosystem for Customizable, Scalable, and Transferable 3D Tactile Sensing 提出OpenTac以解决3D触觉传感器的可定制性与可扩展性问题 manipulation policy learning
22 Dispersive Tree Agreements for Multi-Robot Coordination 提出分散树协议以解决多机器人协调问题 motion planning
23 Demonstration-Based Robotic Feeding Using Dynamic Movement Primitives 提出基于示范的机器人喂食框架以解决动态运动规划问题 motion planning
24 IORA: Irregular Object Immobilization under Restricted Actuation 提出支持感知抓取框架以解决低自由度手的物体固定问题 manipulation
25 LocoManiLab: A Unified Testbed for Data, Policies, Controllers, and Deployment in Humanoid Loco-Manipulation 提出LocoManiLab以解决人形机器人运动与操作协调评估问题 humanoid humanoid robot locomotion
26 Robot Motion Transition with a Human Motion Prior 提出STAMP框架以解决人形机器人运动连续性问题 humanoid motion tracking locomotion ✅
27 EgoForesight: Effectively Scaling Policy Learning with Noisy Egocentric Actions 提出EgoForesight以解决噪声自我中心动作的政策学习问题 manipulation dexterous manipulation policy learning
28 Multimodal MPC via Bayesian Set Optimization for Dynamic Manipulation of Deformable Linear Objects 提出BM2PC框架以解决可变形线性物体的动态操控问题 manipulation MPC multimodal ✅
29 Not an Accident: Exploiting Safety Filter Inadequacy in Humanoid Robots 提出SIREN工具以解决人形机器人安全过滤器不足问题 humanoid humanoid robot
30 PrefO2O: Zero-Shot Preference-Based Reinforcement Learning via Offline-to-Online Latent Preference Transfer 提出PrefO2O框架以解决偏好标签收集成本高的问题 locomotion manipulation reinforcement learning
31 SEVI: Safe Evidential Real-World Reinforcement Learning 提出SEVI框架以解决现实世界强化学习中的安全问题 manipulation reinforcement learning policy learning
32 RGraph-Eval: Task-Grounded Scene Graphs for Evaluating Robot Video Generation 提出RGraph-Eval以解决机器人视频生成评估中的不一致问题 manipulation foundation model multimodal ✅
33 FORCA: A Force-Aware Coding Agent for Contact-Rich Robot Manipulation 提出FORCA以解决接触丰富机器人操作中的控制逻辑生成问题 manipulation
34 Move, don't think: sample-efficient collision avoidance with lossy proximity sensors 提出基于低分辨率传感器的高效碰撞避免方法 humanoid humanoid robot reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
35 Multimodal Progress-Residual Fusion for Anticipating Navigation Retreat in Robotic Flexible Endoscopy 提出多模态进度残差融合以预测机器人内窥镜导航撤退 multimodal
36 Probabilistic Energy Modeling Unifies Versatile Swarm Control 提出概率能量建模以统一多样化的群体控制方法 zero-shot transfer
37 GelSlim 5.0: Unifying Vision and Touch with a Single Fingertip Camera 提出GelSlim 5.0以解决视觉与触觉融合问题 multimodal
38 Learning Robot Behavior Priors from Non-Robotic Synthetic Data 提出利用合成数据学习机器人行为先验以解决数据瓶颈问题 foundation model
39 LAST-V2X: Language-Driven Adaptive Scenario Synthesis and Testing for Communication-Induced Failures in V2X Safety Applications 提出LAST-V2X以解决V2X安全应用中的通信诱发故障问题 large language model
40 Know When to Escalate: Critic-Guided Adaptive Execution for Cloud-Local Embodied Agents 提出CARE框架以解决云端与本地执行的决策延迟问题 foundation model
41 Full-Weight VLA Fine-Tuning Without an fp32 Master Copy Silently Erases Most Updates 提出无fp32主副本的全权重VLA微调方法以解决更新丢失问题 vision-language-action VLA

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
42 DiffDreamer: Coupling World Models with Differentiable Simulation for Agile Quadrotor Control 提出DiffDreamer以解决四旋翼控制中的动态预测问题 reinforcement learning world model world models
43 Skeleton-Grounded Latent Action Model for Robot World Models 提出Skeleton-Grounded潜在动作模型以解决机器人世界建模问题 world model world models human-to-robot
44 When One Step Is Enough: An Empirical Study of Euler Integration in Flow-Matching Policies 提出单步动作生成方法以优化流匹配策略 flow matching distillation VLA
45 EBV-CAN: Vision--Language Grounding for Contact-Aided Endoscope Navigation 提出EBV-CAN以解决柔性内窥镜导航中的环境接触问题 behavior cloning MAE
46 See What I Need, Dream What I Want: A Navigation Foundation Model on a Self-Constructed Representation Space 提出RepresentNav以解决导航策略视觉表示设计问题 world model world models JEPA

🔬 支柱三：空间感知与语义 (Perception & Semantics) (5 篇)

#题目一句话要点标签🔗⭐
47 Point-Level Refinable Semantic Mapping for Spatial Understanding 提出在线可细化语义映射框架以解决动态环境中的映射精度问题 semantic mapping semantic map open-vocabulary
48 OASIS: Online Anchor-centric Scene Inference System for Open-Vocabulary Retrieval and Navigation in Dynamic Environments 提出OASIS以解决动态环境中的在线映射与导航问题 open-vocabulary open vocabulary multimodal
49 TRACE: Traversability-aware Reactive Navigation via VLM-driven Adaptive Constraints Estimation 提出TRACE框架以解决复杂森林环境中的自主导航问题 traversability
50 ProTrav: Probabilistic Traversability with Elevation Uncertainty Propagation for Risk-aware Off-road Navigation 提出ProTrav以解决不确定性传播下的越野导航问题 traversability
51 KiRoSe: Using Kinematic Data for Efficient Segmentation of Robot Demonstrations 提出KiRoSe框架以高效分割机器人演示数据 open-vocabulary open vocabulary egocentric ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (4 篇)

#题目一句话要点标签🔗⭐
52 Calibration-free IMU-based Relative Orientation Estimation under Dynamic Human Motion 提出无校准IMU相对定向估计方法以解决动态人类运动中的漂移问题 human motion motion estimation
53 Whole-Body Motion Guided Reference Generation for Uncertainty-Aware Compliant Assistance 提出双环路辅助策略以解决外骨骼可靠性问题 human motion multimodal
54 FLORA: An Open Model Suite for Scaling Robotics Data Engines 提出FLORA以解决机器人数据引擎标注效率问题 human-to-robot foundation model
55 WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot Demonstrations 提出WorldMirror框架以解决机器人学习中的场景构建问题 spatial relationship

⬅️ 返回 cs.RO 首页 · 🏠 返回主页