cs.RO（2026-06-22）

📊 共 40 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (29 🔗7) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (29 篇)

#题目一句话要点标签🔗⭐
1 TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation 提出TEXEDO以解决人形机器人运动生成中的可执行性问题 humanoid humanoid robot Unitree ✅
2 CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation 提出CoorDex以解决连续灵巧人形机器人运动操控问题 humanoid motion tracking locomotion ✅
3 Cloak: Zero-Shot Cross-Embodiment Manipulation by Masking the End-Effector from the VLA 提出Cloak以实现零-shot跨体现操作的视觉语言动作模型 manipulation cross-embodiment embodiment transfer
4 Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI 提出Humanoid-OmniOcc以解决人形机器人环境占用预测问题 humanoid humanoid robot sim-to-real ✅
5 LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models 提出LIBERO-Safety以解决VLA模型的安全性问题 manipulation domain randomization teleoperation
6 SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors 提出SkyJEPA以解决四旋翼长时间控制问题 sim-to-real world model world models
7 LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation 提出LaST-HD以解决机器人操作中的物理动态对齐问题 manipulation dexterous hand world model
8 AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control 提出AdaReP以解决神经世界模型预测控制中的重规划效率问题 manipulation MPC model predictive control
9 dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models 提出dVLA-RL以解决离散扩散视觉-语言-动作模型的强化学习问题 manipulation reinforcement learning vision-language-action
10 HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory 提出HoloAgent-0以解决物理机器人执行中的复杂性问题 humanoid humanoid control manipulation
11 Flow as Flow: Modeling Robot Velocity Fields as Probability Velocity Fields for Flow-Based Object Manipulation 提出Flow as Flow框架以优化机器人流动性场建模 manipulation flow matching cross-embodiment
12 Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents 提出Foresight框架以解决长时间机器人操作中的故障检测问题 manipulation world model world models
13 LP-NavOA: Integrated Local Navigation and Obstacle Avoidance for Humanoid Robots under Limited Perception 提出LP-NavOA以解决人形机器人在有限感知下的导航与避障问题 humanoid humanoid robot locomotion
14 Assistron: Bayesian Shared Autonomy with Off-the-shelf Vision-Language-Action Models 提出Assistron以解决日常活动中的共享自主问题 manipulation teleoperation flow matching ✅
15 KEMO: Event-Driven Keyframe Memory for Long-Horizon Robot Manipulation with VLA Policies 提出KEMO框架以解决长时间机器人操作中的记忆问题 manipulation dual-arm VLA
16 IOI: Decoupling Kinematics and Physics for Interactive World Models 提出IOI以解决交互世界模型中的动力学与运动学耦合问题 teleoperation policy learning world model
17 DexTeleop-0: Force-Aware Bimanual Dexterous Teleoperation with Ego-Centric Perception towards Shared Autonomy 提出DexTeleop-0以解决双手灵巧遥操作中的接触反馈问题 manipulation dexterous manipulation bi-manual
18 HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning 提出HiL-ResRL以解决行为克隆模型在工业应用中的局限性 manipulation reinforcement learning imitation learning
19 Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation 提出潜在动作引导的流匹配策略以解决机器人操作中的结构不匹配问题 manipulation behavior cloning flow matching
20 Asymmetric physics enables efficient learning in quadrupedal robot swarms 提出不对称物理以提高四足机器人群体的学习效率 quadruped locomotion locomotion policy
21 UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models 提出UniFS以解决视觉-语言-动作模型中的频率困境 manipulation vision-language-action VLA ✅
22 Bridging Semantics and Kinematics: A Modular Framework for Zero-Shot Robotic Manipulation 提出模块化框架以解决零-shot语言引导机器人操作问题 manipulation large language model foundation model
23 Distilling Collaborative Dynamics into Latent Space for Implicit Coordination in Decentralized Multi-Agent Manipulation 提出CLS-DP以解决多臂操控中的隐式协调问题 manipulation spatiotemporal
24 Improving Robotic Imitation Learning via Trajectory Standardization 提出信息标准化轨迹重采样方法以改善机器人模仿学习 manipulation policy learning imitation learning ✅
25 TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learning 提出物理启发的轨迹显著性检测器以解决模仿学习数据稀缺问题 manipulation imitation learning ✅
26 Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation 提出See2Act以解决机器人模仿学习中的部分可观测性问题 manipulation sim-to-real imitation learning
27 AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection 提出AutoDex以解决真实环境中灵巧抓取数据收集问题 teleoperation
28 Lessons from the Field: A Case Study of Robotic Intervention in an Industrial Emergency 通过机器人干预解决化工厂紧急事故中的爆炸风险问题 manipulation
29 PanoVine: Whole-Body Visuomotor Control for Soft Growing Vine Robot 提出PanoVine以解决软生长藤机器人自主控制问题 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
30 A Watermark for Vision-Language-Action and World Action Models 提出关键潜在来源验证方法以保护VLA和WAM模型的知识产权 world action model world action models vision-language-action
31 From Pixels to Concepts: Growing Rich 3D Semantic Scene Graph Forests utilizing Foundation Models 利用基础模型构建开放语义关系的3D场景图森林以提升机器人理解能力 world model world models scene understanding
32 Causal Reward World Models: Zero-shot Reward Design for Automated Skill Generation 提出因果奖励世界模型以解决自动化奖励设计问题 reinforcement learning world model world models
33 BiliVLA: Scene-Aware Vision-Language-Action Model with Reinforcement Learning for Autonomous Biliary Endoscopic Navigation 提出BiliVLA以解决自主胆道内窥镜导航问题 reinforcement learning vision-language-action VLA
34 Temporal Logic Guidance for Action-Only Diffusion Policies with World Models 提出基于世界模型的引导方法以优化动作扩散策略 diffusion policy world model world models
35 RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models 提出主动持续学习框架以提升视觉-语言-动作模型的适应性 imitation learning vision-language-action VLA

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
36 Flatness Preserves Instruction Following in Vision-Language-Action Models 提出平坦性优化以解决视觉-语言-动作模型的指令盲目问题 vision-language-action VLA instruction following ✅
37 Real-Time Multimodal Activity-Aware Error Detection in Robot-Assisted Surgery 提出多模态活动感知错误检测框架以提升机器人辅助手术安全性 multimodal
38 Conceptual Design of an Ecosystem for Real Farm Data Collection toward Agricultural AI Foundation Models 提出可持续农场数据收集生态系统以解决农业AI基础模型数据稀缺问题 foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
39 ShotcreteDepth: A Bi-modal Dataset for Robust Robotic Depth Perception in Shotcrete Construction Environments 提出ShotcreteDepth数据集以解决施工环境下深度感知问题 depth estimation ✅

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

#题目一句话要点标签🔗⭐
40 A Vendor-Agnostic LiDAR Data Conversion System with Multi-Signal Detection and Multi-Format Output 提出一种供应商无关的LiDAR数据转换系统以解决多格式兼容问题 PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页