cs.RO（2026-08-27）

📊 共 27 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (22 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (22 篇)

#题目一句话要点标签🔗⭐
1 SOLO: Stable Omni-terrain Long-Horizon Perceptive Humanoid Locomotion 提出SOLO框架以解决长距离人形机器人在复杂地形中的稳定性问题 humanoid humanoid locomotion locomotion ✅
2 CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators 提出CLAP以解决跨机器人体的物理模拟问题 humanoid bi-manual world model
3 Closing the Loop on the Poppy Humanoid: Bipedal Locomotion with Linear-Quadratic Control and Learned Cost Functions 提出基于LQR控制的闭环行走控制器以解决Poppy人形机器人步态问题 humanoid bipedal biped
4 TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot Manipulation 提出TemporalFlow-VLA以解决长时间机器人操控中的执行历史问题 manipulation motion estimation vision-language-action
5 FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference 提出FlashVLA以解决VLA模型推理延迟和异步执行问题 manipulation flow matching vision-language-action
6 GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation 提出GRAFT以解决细粒度机器人操作的在线适应问题 manipulation vision-language-action VLA
7 Riemann-1.0: An Embodied World Action Model for Physical AI 提出Riemann-1.0以解决物理AI中的世界动作建模问题 manipulation world action model world action models
8 PredVLA: A Sub-Million-Parameter Predictive-Coding Policy for Robot Manipulation 提出PredVLA以解决小参数预算下的机器人操控问题 manipulation vision-language-action language conditioned
9 FLARE: A Failure-Aware Framework for Autonomous Correction and Recovery in Visual-Language Robotic Manipulation 提出FLARE框架以解决视觉语言机器人操作中的错误恢复问题 manipulation vision-language-action VLA
10 Rapid On-Robot Learning for Dynamic Manipulation Skills: Robot Juggling 提出在线学习框架以实现机器人快速学习杂耍技能 manipulation bi-manual sim2real
11 Tensegrity Continuum Robots Enable Task-Adaptive Morphologies for Cooperative Behaviors 提出一种基于张力结构的机器人以实现任务自适应形态 locomotion manipulation loco-manipulation
12 Embodied Scene Rearrangement Planning 提出Embodied Scene Rearrangement Planning以解决机器人场景重排问题 motion planning scene understanding egocentric
13 Active Surface-Driven Reconfigurable Gripper: Robust Grasping and Sequential Manipulation of Thin Objects 提出主动表面驱动的可重构抓手以解决薄物体抓取问题 manipulation
14 Active sensing to characterize the heterogeneity of plant stress 提出主动传感技术以表征植物应激异质性 manipulation motion planning
15 MeshPriorDiT: Hierarchical Modeling for Action-Conditioned Cloth Dynamics 提出MeshPriorDiT以解决布料动态预测中的长程协调问题 manipulation flow matching
16 Pass the Bucket: Efficient, Robust, Local Load Balancing for Teams of Heterogeneous Robots 提出自组织任务共享机制以解决异构机器人负载均衡问题 motion planning
17 PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action Models 提出PHR-VLA以解决视觉语言动作模型的规划视野推理问题 manipulation latent dynamics vision-language-action ✅
18 Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models 提出VLAct以解决机器人数据稀缺问题 humanoid cross-embodiment embodiment transfer
19 GRAFT: Grounded and Efficient Online Reinforcement Adaptation for Fine-Grained Robot Manipulation 提出GRAFT以解决细粒度机器人操作的在线适应问题 manipulation vision-language-action VLA
20 Coordinated Motion Planning for Multi-Arm Systems via Iterative LQ Games 提出迭代LQ博弈框架以解决多臂系统的协调运动规划问题 manipulation motion planning
21 Remote Human and Robot Interaction for Greenhouse Gardening Using Virtual Reality 利用虚拟现实技术提升温室园艺中的人机交互效率 teleoperation VR teleoperation
22 Beyond Relative Geometry: Metric-Aware Geometry Perception for Robotics 提出度量感知几何以解决机器人几何重建不一致问题 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
23 TrapVLA: Trapping Vision-Language-Action Models in Configured Failure Modes 提出Configured Failure Trapping以增强视觉-语言-动作模型的安全性 vision-language-action VLA ✅
24 Relaxation-Aware Multimodal Sensing of Soft Gripper Driven by Structure-Perception-Learning 提出温度耦合的粘弹性力表示以解决软抓手的放松问题 multimodal
25 STEP: State-Aware Task Estimation and Planning with Multi-Modal LLMs for Human-Robot Collaboration 提出STEP以解决人机协作中的状态感知与任务规划问题 large language model
26 RTNav: Towards Real-Time Zero-Shot Object Navigation 提出RTNav以解决实时零-shot物体导航问题 foundation model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
27 Residual Deep Reinforcement Learning-Based Computed Torque Control for a Cable-Driven Lower-Limb Rehabilitation Robot under Disturbances and Parametric Uncertainties 提出基于残差深度强化学习的计算扭矩控制以解决下肢康复机器人问题 reinforcement learning deep reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页