cs.RO（2025-03-25）

📊 共 12 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (7) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (7 篇)

#题目一句话要点标签🔗⭐
1 Gemini Robotics: Bringing AI into the Physical World Gemini Robotics：将AI引入物理世界，构建通用机器人 manipulation open-vocabulary open vocabulary
2 Boosting Robotic Manipulation Generalization with Minimal Costly Data 提出RoboTron-Platter框架，利用低成本空间推理数据提升机器人操作泛化性。 manipulation embodied AI vision-language-action
3 RoboFlamingo-Plus: Fusion of Depth and RGB Perception with Vision-Language Models for Enhanced Robotic Manipulation RoboFlamingo-Plus：融合深度与RGB信息的视觉-语言模型，提升机器人操作性能 manipulation multimodal
4 CubeRobot: Grounding Language in Rubik's Cube Manipulation via Vision-Language Model 提出CubeRobot，利用视觉-语言模型解决魔方操作中的语言理解与执行问题 manipulation multimodal
5 Learning Scene-Level Signed Directional Distance Function with Ellipsoidal Priors and Neural Residuals 提出基于椭球先验和神经残差的场景级有向距离函数学习方法 trajectory optimization NeRF neural radiance field
6 Visuo-Tactile Object Pose Estimation for a Multi-Finger Robot Hand with Low-Resolution In-Hand Tactile Sensing 提出一种结合视觉和低分辨率触觉的多指机器人手物体姿态估计方法 manipulation in-hand manipulation
7 Benchmarking Multi-Object Grasping 提出多物体抓取基准测试，评估机器人操作能力 manipulation

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

#题目一句话要点标签🔗⭐
8 Semi-SMD: Semi-Supervised Metric Depth Estimation via Surrounding Cameras for Autonomous Driving Semi-SMD：面向自动驾驶，利用环视相机实现半监督度量深度估计 world model depth estimation monocular depth ✅
9 Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy Dita：通过扩散Transformer扩展通用视觉-语言-动作策略 policy learning cross-embodiment vision-language-action
10 Towards Uncertainty Unification: A Case Study for Preference Learning 提出不确定性统一偏好学习框架，提升人机交互中机器人对人类偏好的预测精度。 preference learning

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

#题目一句话要点标签🔗⭐
11 A Multi-Agent Framework Integrating Large Language Models and Generative AI for Accelerated Metamaterial Design 提出CrossMatAgent，一个融合大语言模型和生成AI的多智能体框架，加速超材料设计。 large language model multimodal
12 Body Discovery of Embodied AI 提出具身AI的“身体发现”挑战，利用因果推断实现动态环境中机器人身体识别。 embodied AI

⬅️ 返回 cs.RO 首页 · 🏠 返回主页