cs.RO（2026-08-25）

📊 共 18 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion 提出CARO框架以解决四足机器人零-shot适应性问题 quadruped locomotion sim-to-real
2 NeurRAFT: Robot Motion Planning via Anchor-Level Flow Matching with Clearance-Aware Preference Tuning 提出NeurRAFT以解决拥挤环境中的机器人运动规划问题 motion planning imitation learning flow matching ✅
3 Fiber Optic Sensing Glove for High Performance Dexterous Manipulation Capture 提出光纤传感手套以解决精细操作手势捕捉问题 manipulation dexterous manipulation bi-manual
4 Gripper-aware Vision Language Action Models 提出MiGA和GVLA以解决机器人抓取策略依赖问题 manipulation vision-language-action VLA
5 Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Models 提出层次技能检索以解决视觉-语言-动作模型适应性不足问题 manipulation vision-language-action VLA ✅
6 Latent Action as Intention Enables Efficient Future Imagination for World Action Models 提出LAWA以解决WAM在未来观察生成中的效率问题 manipulation world action model world action models
7 TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks 提出TrAct以解决机器人控制与视觉预测之间的对接问题 manipulation world model world models
8 GaussianWAM: Distilling Geometry and Semantics from 3D Gaussian Fields into World-Action Models 提出GaussianWAM以增强世界行动模型的几何与语义表示 manipulation representation learning distillation
9 Robust Slip Detection and Material Classification via Spatiotemporal Transformers on a Uniformly-Illuminated Visuo-Tactile Sensor 提出基于时空变换器的稳健滑移检测与材料分类方法 manipulation spatiotemporal
10 VIP: Variation-based Iterative-learning Planning for Robotic Navigation 提出VIP框架以解决复杂环境中的机器人导航问题 motion planning VIP
11 One-Shot Learning from Demonstration of Contact-Rich Robotic Manipulation by Identifying Physical Interactions 提出一种新方法以解决机器人操作中的物理交互建模问题 manipulation
12 A Durable Vision-Based Tactile Fingertip for Robotic Manipulation 提出耐用的视觉触觉指尖以解决机器人操作中的传感器脆弱性问题 manipulation
13 Trajectory-Level Continuous Action Representation for Robotic Manipulation 提出CAT框架以解决机器人操作中的动作表示问题 manipulation
14 Safety-aware Model Predictive Path Integral Control with Signal Temporal Logic 提出安全感知的模型预测路径积分控制以解决复杂任务规划问题 motion planning

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
15 Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning 提出WorldEcho和WorldSync以解决机器人世界模型的动作跟随问题 policy learning world model world models
16 NeuralParker: A Reinforcement Learning Planner for Irregular Parking Environments 提出NeuralParker以解决不规则停车环境中的规划问题 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
17 PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control 提出PonderPounce以解决机器人控制中的上下文记忆问题 vision-language-action VLA large language model
18 Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings 提出Design-to-Plan框架以解决制造过程规划中的信息整合问题 large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页