cs.RO（2025-05-22）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 Unified Multi-Rate Model Predictive Control for a Jet-Powered Humanoid Robot 提出一种统一的多速率模型预测控制框架，用于喷气动力人形机器人。 humanoid humanoid robot MPC
2 ManipLVM-R1: Reinforcement Learning for Reasoning in Embodied Manipulation with Large Vision-Language Models 提出ManipLVM-R1，利用强化学习提升具身操作中大型视觉语言模型的推理能力 manipulation reinforcement learning affordance
3 Find the Fruit: Zero-Shot Sim2Real RL for Occlusion-Aware Plant Manipulation 提出基于Sim2Real强化学习的遮挡感知植物操作方法，用于自主采摘。 manipulation sim2real reinforcement learning
4 TacCompress: A Benchmark for Multi-Point Tactile Data Compression in Dexterous Hand TacCompress：针对灵巧手多点触觉数据压缩的基准研究 manipulation dexterous hand dexterous manipulation
5 LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios LiloDriver：面向长尾自动驾驶场景的终身学习闭环运动规划框架 motion planning large language model ✅
6 3D Equivariant Visuomotor Policy Learning via Spherical Projection 提出基于球面投影的3D等变视觉运动策略学习框架，提升单目RGB输入下的机器人操作性能。 manipulation policy learning diffusion policy
7 UAV See, UGV Do: Aerial Imagery and Virtual Teach Enabling Zero-Shot Ground Vehicle Repeat 提出VirT&R，利用无人机影像和NeRF实现零样本地面车辆自主重复导航。 sim-to-real NeRF neural radiance field
8 SpineWave: Harnessing Fish Rigid-Flexible Spinal Kinematics for Enhancing Biomimetic Robotic Locomotion SpineWave：仿生鱼脊柱运动学的水下机器人设计与优化 locomotion
9 SEM: Enhancing Spatial Understanding for Robust Robot Manipulation 提出SEM模型，增强机器人操作的空间理解能力，提升操作鲁棒性 manipulation
10 Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control 提出基于3D Occupancy和学习预测控制的弹性塑性物体操作框架 manipulation

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

#题目一句话要点标签🔗⭐
11 ScanBot: Towards Intelligent Surface Scanning in Embodied Robotic Systems ScanBot：面向具身机器人系统的高精度表面扫描数据集与基准测试 VLA large language model multimodal
12 Human-like Semantic Navigation for Autonomous Driving using Knowledge Representation and Large Language Models 提出基于知识表示和LLM的类人语义导航方法，提升自动驾驶在动态环境下的适应性。 large language model

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

#题目一句话要点标签🔗⭐
13 Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2) Raw2Drive：基于对齐世界模型的强化学习端到端自动驾驶方法 reinforcement learning imitation learning world model
14 VL-SAFE: Vision-Language Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving 提出VL-SAFE，利用视觉-语言模型指导的安全强化学习自动驾驶框架。 reinforcement learning policy learning world model ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
15 D-LIO: 6DoF Direct LiDAR-Inertial Odometry based on Simultaneous Truncated Distance Field Mapping 提出基于快速截断距离场映射的直接激光雷达惯性里程计D-LIO，实现6DoF位姿估计。 LIO

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
16 Monitoring Electrostatic Adhesion Forces via Acoustic Pressure 提出一种基于声压的静电吸附力非接触监测方法，适用于机器人末端执行器。 PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页