cs.RO（2026-09-08）

📊 共 28 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (19 🔗5) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱六：视频提取与匹配 (Video Extraction) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (19 篇)

#题目一句话要点标签🔗⭐
1 TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model 提出TANGO以解决复杂环境中的类人机器人导航问题 humanoid humanoid robot whole-body control
2 PGMT: Perceptive General Motion Tracking for Humanoid Robots 提出PGMT以解决复杂地形下人形机器人运动跟踪问题 humanoid humanoid robot motion tracking
3 DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination 提出DeCAL以解决复杂接触动态下的灵巧视觉语言动作问题 manipulation dexterous manipulation contact-aware ✅
4 RoboCousin: Build Your Own Simulation Playground for Robust Bimanual Robotic Manipulation 提出RoboCousin以解决双手机器人操作数据收集难题 manipulation bi-manual bimanual manipulation
5 Bridging Language and Physics: Automated Design of Continuum Robots with Large Language Models 提出AID-SR框架以解决复杂物理交互下的机器人设计问题 locomotion manipulation reinforcement learning ✅
6 Online, Reachability-Aware, Sampling-Based Motion Planning 提出在线可达性感知的采样基础运动规划方法以解决安全性问题 reachability-aware MPC motion planning
7 Model Predictive Control of Tensegrity Robots via Contact-Aware Graph Neural Dynamics Model 提出基于图神经网络的控制方法以解决张力结构机器人导航问题 model predictive control contact-aware
8 AURORA: Active Uncertainty-Driven Re-Orientation for In-Hand Reconstruction 提出AURORA框架以解决机器人手中物体重建中的视觉遮挡问题 manipulation in-hand manipulation 3D reconstruction
9 CAST: Alternating State-Value Targets and Expanded Policy Gradients for Model-Based Reinforcement Learning 提出CAST以提升基于模型的强化学习的价值学习效率 quadruped humanoid Unitree
10 CASD: Chunk-Aligned Semantic Distillation for Multi-StageRobot Manipulation 提出CASD以解决多阶段机器人操作中的语义目标预测问题 manipulation distillation
11 3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints 提出3DWay以解决机器人操作中的3D一致性问题 manipulation VLA ✅
12 Visible-Reachable Workspace for Perception-Aware Humanoid Design 提出可视可达工作空间以解决人形机器人感知问题 humanoid manipulation
13 CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations 提出CALIPER以解决物理推理评估中的不足问题 manipulation world model world models
14 FOCI Policy: Focus on Object-Centric Interactions for Relational Manipulation Policies 提出FOCI策略以解决对象中心交互的关系操控问题 manipulation ✅
15 Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation 提出RoboReel基准以评估机器人观察学习能力 manipulation VLA
16 Ostrich: Taking Large Strides Through Stiff Contact in Differentiable Dynamics 提出Ostrich以解决大时间步长下的接触模拟问题 sim-to-real trajectory optimization
17 Proxy Policy Steering 提出代理策略引导以解决机器人任务适应性问题 manipulation
18 BIFTA: Brain-Inspired Few-Shot Tactile Adaptation for Unknown Sensors 提出BIFTA框架以解决未知传感器适应问题 manipulation
19 OmniNav: Robust Long-Horizon Target Navigation in Dynamic Environments 提出OmniNav以解决动态环境中的长距离目标导航问题 manipulation ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
20 Estimating Semantic Ambiguity via Gaussian Context Distributions for VLM-Driven Traversability Analysis 提出高斯上下文分布以解决语义模糊问题 scene understanding open-vocabulary open vocabulary
21 TASG-Explore: Traversability-Aware Sector-Guided Exploration for Ground Robot on Uneven Terrain 提出TASG-Explore以解决不平坦地形下的自主探索问题 traversability
22 MFVINS: Multiple Fisheye Camera-Based Visual Inertial System 提出MFVINS以解决单目视觉惯性系统的局限性 depth estimation

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
23 DISEIL: Demonstration Distillation for Sample-Efficient Imitation Learning 提出DISEIL以解决样本效率低下的模仿学习问题 imitation learning distillation
24 Graph-Based Safe Reinforcement Learning for Multi-Agent Systems with Time-Varying Topology 提出基于图的安全强化学习框架以解决多智能体动态导航问题 reinforcement learning policy learning
25 Learning to build covering structures with continuous adjustments 提出一种强化学习方法以解决机器人建造中的灵活性问题 reinforcement learning PPO SAC

🔬 支柱六：视频提取与匹配 (Video Extraction) (2 篇)

#题目一句话要点标签🔗⭐
26 DYAD: A Multimodal Dataset of Co-Located Human Assistance 提出DYAD数据集以解决人机协作中的多模态交互问题 egocentric multimodal
27 Safe Task Planning with Long-Term Graph Memory for Embodied Agents 提出SafeMem框架以解决嵌入式智能体的安全任务规划问题 egocentric large language model

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

#题目一句话要点标签🔗⭐
28 Multi-bounce Drum Roll with Optimized Active Tricks to Leverage Soft Embodiment 提出软体机器人鼓手以优化多次反弹技巧实现高效鼓点演奏 PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页