cs.RO（2025-09-09）

📊 共 16 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9 🔗3) 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) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 Graph-Fused Vision-Language-Action for Policy Reasoning in Multi-Arm Robotic Manipulation 提出Graph-Fused VLA框架，解决双臂机器人从人类演示中学习复杂操作策略的问题。 manipulation bi-manual dual-arm
2 Text2Touch: Tactile In-Hand Manipulation with LLM-Designed Reward Functions Text2Touch：利用LLM设计的奖励函数实现触觉灵巧手内操作 manipulation dexterous manipulation in-hand manipulation ✅
3 TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models 提出扭矩感知视觉-语言-动作模型(TA-VLA)，提升机器人操作中力觉反馈的利用率。 manipulation vision-language-action VLA
4 Decoding RobKiNet: Insights into Efficient Training of Robotic Kinematics Informed Neural Network RobKiNet：一种基于运动学知识的神经网络，用于提升机器人构型空间采样效率 motion planning reinforcement learning deep reinforcement learning
5 OmniMap: A General Mapping Framework Integrating Optics, Geometry, and Semantics OmniMap：提出一种融合光学、几何和语义信息的通用建图框架。 manipulation 3DGS scene understanding
6 Diffusion-Guided Multi-Arm Motion Planning 提出扩散引导的多臂运动规划DG-MAP，解决高维状态空间下的多臂协作规划问题。 dual-arm motion planning
7 TransMPC: Transformer-based Explicit MPC with Variable Prediction Horizon TransMPC：基于Transformer的可变预测步长显式模型预测控制 MPC model predictive control
8 RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction RaC：通过扩展恢复与纠正能力实现机器人长时程任务学习 bi-manual teleoperation imitation learning ✅
9 Safe and Non-Conservative Contingency Planning for Autonomous Vehicles via Online Learning-Based Reachable Set Barriers 提出基于在线学习可达集屏障的自动驾驶车辆安全应急规划方法 trajectory optimization ✅

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

#题目一句话要点标签🔗⭐
10 Zero-Shot Metric Depth Estimation via Monocular Visual-Inertial Rescaling for Autonomous Aerial Navigation 提出基于视觉惯性重标定的零样本单目深度估计方法，用于自主飞行器避障 depth estimation metric depth
11 Attribute-based Object Grounding and Robot Grasp Detection with Spatial Reasoning 提出基于属性的对象定位与机器人抓取框架OGRG，解决复杂场景下的语言指定抓取问题。 affordance grasp prediction
12 Aerial-ground Cross-modal Localization: Dataset, Ground-truth, and Benchmark 提出大规模跨模态定位数据集与基准，促进航空-地面视觉定位研究 visual odometry

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

#题目一句话要点标签🔗⭐
13 Can SSD-Mamba2 Unlock Reinforcement Learning for End-to-End Motion Control? 提出基于SSD-Mamba2的视觉驱动强化学习框架，用于端到端运动控制。 reinforcement learning Mamba cross-embodiment
14 Quadrotor Navigation using Reinforcement Learning with Privileged Information 提出一种基于强化学习和特权信息的四旋翼导航方法，解决复杂环境下自主导航问题。 reinforcement learning privileged information differentiable simulation
15 Fault Tolerant Control of a Quadcopter using Reinforcement Learning 提出基于强化学习的四旋翼容错控制框架，提升单桨失效下的鲁棒性。 reinforcement learning

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
16 PySensors 2.0: A Python Package for Sparse Sensor Placement PySensors 2.0：用于稀疏传感器放置的Python软件包，支持空间约束和不确定性量化。 sparse sensors

⬅️ 返回 cs.RO 首页 · 🏠 返回主页