cs.RO（2025-10-22）

📊 共 12 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (5 篇)

#题目一句话要点标签🔗⭐
1 GigaBrain-0: A World Model-Powered Vision-Language-Action Model GigaBrain-0：基于世界模型赋能的视觉-语言-动作通用机器人模型 manipulation mobile manipulation sim2real
2 Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning 利用离线强化学习，通过非专家数据增强模仿学习的鲁棒性 manipulation reinforcement learning policy learning ✅
3 Push Anything: Single- and Multi-Object Pushing From First Sight with Contact-Implicit MPC 提出C3+算法，通过接触隐式MPC实现对多种物体的单/多目标精准推移操作 manipulation MPC model predictive control ✅
4 Optimizing Prosthetic Wrist Movement: A Model Predictive Control Approach 提出基于模型预测控制的义肢腕部运动优化方法，提升灵活性和用户控制。 MPC model predictive control predictive model
5 TARMAC: A Taxonomy for Robot Manipulation in Chemistry 提出TARMAC化学机器人操作分类法，提升化学实验自动化水平。 manipulation

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

#题目一句话要点标签🔗⭐
6 ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling ProTerrain：概率物理信息粗糙地形建模，提升机器人导航不确定性预测 world model traversability motion prediction
7 SEA: Semantic Map Prediction for Active Exploration of Uncertain Areas SEA：基于语义地图预测的主动探索不确定区域方法 reinforcement learning semantic map
8 Imitation Learning Policy based on Multi-Step Consistent Integration Shortcut Model 提出基于多步一致性积分捷径模型的模仿学习策略，加速机器人策略推理。 imitation learning flow matching distillation
9 Hierarchical DLO Routing with Reinforcement Learning and In-Context Vision-language Models 提出层次化DLO路由框架以解决长时间规划问题 reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
10 Learning Affordances at Inference-Time for Vision-Language-Action Models 提出LITEN，通过推理时学习机器人操作策略，提升VLA模型在复杂任务中的表现 affordance vision-language-action VLA
11 GRASPLAT: Enabling dexterous grasping through novel view synthesis GRASPLAT：通过新视角合成实现灵巧抓取的机器人方法 3D gaussian splatting gaussian splatting splatting ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
12 LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments LaViRA：用于连续环境零样本视觉语言导航的语言-视觉-机器人动作转换框架 vision-language-navigation VLN large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页