cs.RO（2025-05-18）

📊 共 15 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning 提出基于视觉强化学习的感知灵巧控制框架，使模拟人形机器人涌现主动感知和操作能力 humanoid whole-body control manipulation
2 Robust Reinforcement Learning-Based Locomotion for Resource-Constrained Quadrupeds with Exteroceptive Sensing 针对资源受限四足机器人，提出基于外感知的鲁棒强化学习运动控制方法。 quadruped locomotion reinforcement learning
3 Adaptive MPC-based quadrupedal robot control under periodic disturbances 提出基于自适应MPC的四足机器人控制方法，应对周期性扰动 quadruped locomotion MPC ✅
4 Design of a 3-DOF Hopping Robot with an Optimized Gearbox: An Intermediate Platform Toward Bipedal Robots 设计优化齿轮箱的三自由度跳跃机器人，为双足机器人开发提供中间平台。 bipedal biped reinforcement learning
5 PartDexTOG: Generating Dexterous Task-Oriented Grasping via Language-driven Part Analysis PartDexTOG：提出一种基于语言驱动部件分析的灵巧手任务导向抓取方法 manipulation dexterous hand penetration
6 Learning Impact-Rich Rotational Maneuvers via Centroidal Velocity Rewards and Sim-to-Real Techniques: A One-Leg Hopper Flip Case Study 提出基于质心速度奖励和Sim-to-Real技术学习高冲击旋转动作，以单腿跳跃机器人翻转为例。 sim-to-real centroidal dynamics reinforcement learning
7 RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction 提出RoboFAC框架，用于机器人操作失败分析与纠正，提升VLA模型在真实场景下的鲁棒性。 manipulation vision-language-action VLA
8 A Robot Simulation Environment for Virtual Reality Enhanced Underwater Manipulation and Seabed Intervention Tasks 提出(MARUN)2水下机器人仿真环境，支持VR增强的水下操作与海底干预任务 manipulation
9 Scene-Adaptive Motion Planning with Explicit Mixture of Experts and Interaction-Oriented Optimization 提出EMoE-Planner，通过显式混合专家和交互优化实现场景自适应的运动规划。 motion planning

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

#题目一句话要点标签🔗⭐
10 Spatial-LLaVA: Enhancing Large Language Models with Spatial Referring Expressions for Visual Understanding Spatial-LLaVA：利用空间指称表达式增强大型语言模型视觉理解能力 scene understanding spatial relationship large language model
11 Is Semantic SLAM Ready for Embedded Systems ? A Comparative Survey 面向嵌入式系统的语义SLAM性能评估与优化方向探索 visual SLAM 3D gaussian splatting gaussian splatting
12 Structureless VIO 提出一种无结构VIO，在提升计算效率的同时保持或提升定位精度。 visual odometry VIO

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
13 MTIL: Encoding Full History with Mamba for Temporal Imitation Learning 提出MTIL，利用Mamba编码完整历史信息，解决时序模仿学习中的长程依赖问题。 imitation learning diffusion policy world model

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

#题目一句话要点标签🔗⭐
14 BadNAVer: Exploring Jailbreak Attacks On Vision-and-Language Navigation 提出BadNAVer框架，探索针对视觉-语言导航中MLLM驱动导航器的越狱攻击 VLN large language model multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 Behavior Synthesis via Contact-Aware Fisher Information Maximization 提出基于接触感知的Fisher信息最大化方法，用于机器人行为合成以提升物体参数学习。 contact-aware

⬅️ 返回 cs.RO 首页 · 🏠 返回主页