cs.RO（2026-09-09）

📊 共 23 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#题目一句话要点标签🔗⭐
1 ViBe: Visual Behavior Adaptation for Perceptive Humanoid Whole-Body Control 提出ViBe框架以解决人形机器人感知控制问题 humanoid whole-body control motion tracking
2 Learning Terrain-Adaptive Humanoid Locomotion on Granular Terrain 提出基于物理的接触模型以解决人形机器人在颗粒地形上的行走问题 humanoid humanoid locomotion locomotion ✅
3 HaWMPO: Hallucination-Aware World Model-based Policy Optimization for Generalist Robot Policy 提出HaWMPO以解决长时间预测中的幻觉问题 manipulation reinforcement learning policy learning
4 DUET-DINO: Simultaneous Cross-View World Modeling for Latent Planning in Robot Manipulation 提出DUET-DINO以解决机器人操作中的跨视图世界建模问题 manipulation world model world models ✅
5 SwingBot: Learning Whole-Body Brachiation for Humanoid Robots 提出SwingBot以解决高自由度人形机器人全身摆荡问题 humanoid humanoid robot locomotion
6 FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects 提出FolDeX基准以解决长时间变形物体操控问题 manipulation bi-manual embodied AI
7 Frame-Coded Legged Locomotion over Noisy Terrain 提出帧编码方法以解决嘈杂地形下的多足运动问题 legged locomotion locomotion
8 GTA-2: A Multi-VLM Framework for Synthesizing Robot Manipulation Skills via Grounded Task Axes 提出GTA-2框架以合成机器人操作技能 manipulation VLA Code as Policies
9 Compact Visuotactile World Models for Lifting: Prediction, Reward Alignment, and Force Constraints 提出紧凑的视触觉世界模型以提升机器人抓取性能 manipulation world model world models
10 Show-Harness: Just a VLM Agent Can Play Robots 提出Show-Harness以实现视觉语言模型的机器人控制 manipulation teleoperation cross-embodiment
11 PccDiffuser: Multi-solution Motion Planning for Continuum Robots 提出PccDiffuser以解决连续机器人多解运动规划问题 motion planning multimodal
12 Deformable Object Manipulation under Partial Observability via Real-Time Full-Shape Estimation 提出cRVAE以解决可变形物体在部分可观测下的操控问题 manipulation Unitree
13 Adaptive Shared Control with Online Bounded-Rational Human Behavior Estimation 提出自适应共享控制以解决人机协作中的非理性行为问题 shared control
14 Assembling Two Parts in One Hand 提出基于强化学习的单手物体组装方法以解决手指协调问题 dexterous hand domain randomization reinforcement learning ✅
15 Grounding Generated Video Plans in Simulation Towards Versatile Dexterous Controllers 提出基于生成视频的手-物体交互跟踪方法以解决控制器灵活性问题 manipulation HOI ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
16 Frequency-Conditioned Flow Matching for Vision-Language-Action Models 提出FreqFM框架以解决VLA模型频率异质性问题 flow matching vision-language-action VLA
17 JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction 提出JEPA Policy以解决传统模仿学习中的未来表示约束问题 imitation learning behavior cloning diffusion policy
18 Multi-Agent Reinforcement Learning for Autonomous UAV Exploration in Wildfire Response 提出深度强化学习框架以解决无人机在野火响应中的自主探索问题 reinforcement learning deep reinforcement learning DRL
19 HiRAD: A Flexible Large-Scale AGV Routing System 提出HiRAD以解决大规模AGV调度问题 reinforcement learning spatiotemporal

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

#题目一句话要点标签🔗⭐
20 A Confidence-Aware Multimodal Fusion Framework for Industrial Human-Robot Collaboration 提出信心感知多模态融合框架以提升工业人机协作中的意图预测 multimodal
21 RoboDrop: Curating VLA Post-Training Data via Local Gradient Compatibility 提出RoboDrop以解决VLA模型后训练数据质量问题 VLA
22 CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making 提出CT-SAFR框架以解决自主机器人推理安全性问题 chain-of-thought

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

#题目一句话要点标签🔗⭐
23 Odometer-Agnostic Drift Correction Using OpenStreetMap Lane Geometry 提出一种轻量级方法以解决长时间里程计漂移问题 visual odometry

⬅️ 返回 cs.RO 首页 · 🏠 返回主页