cs.RO（2025-07-01）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗2) 支柱八：物理动画 (Physics-based Animation) (1 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning HumanoidGen：利用LLM推理生成双臂灵巧操作的人形机器人数据 humanoid humanoid robot manipulation
2 VISTA: Open-Vocabulary, Task-Relevant Robot Exploration with Online Semantic Gaussian Splatting VISTA：基于在线语义高斯溅射的开放词汇、任务相关机器人探索 quadruped 3D gaussian splatting gaussian splatting
3 Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion 提出JumpER框架，通过自进化先验强化学习解决单足机器人极端地形跳跃难题 quadruped locomotion reinforcement learning
4 Learning Steerable Imitation Controllers from Unstructured Animal Motions 提出一种从非结构化动物运动数据中学习可控模仿控制器的框架 quadruped legged robot locomotion
5 DexWrist: A Robotic Wrist for Constrained and Dynamic Manipulation 提出DexWrist机器人腕部，提升约束和动态操作中的策略学习效率与成功率。 manipulation dexterous manipulation teleoperation
6 RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation RoboEval：一个用于双臂操作策略评估的结构化、可扩展的模拟基准 manipulation bi-manual bimanual manipulation
7 Search-Based Robot Motion Planning With Distance-Based Adaptive Motion Primitives 提出基于距离自适应运动原语的搜索式机器人运动规划算法 motion planning SMPL
8 I Move Therefore I Learn: Experience-Based Traversability in Outdoor Robotics 提出一种基于经验的户外机器人地形可通行性学习方法，无需预标注数据。 legged robot traversability
9 Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations RIGVid：通过模仿AI生成视频实现机器人操作，无需物理演示。 manipulation
10 DIJE: Dense Image Jacobian Estimation for Robust Robotic Self-Recognition and Visual Servoing 提出DIJE算法，用于机器人自识别和视觉伺服的稠密图像雅可比估计 manipulation bi-manual optical flow
11 PI-WAN: A Physics-Informed Wind-Adaptive Network for Quadrotor Dynamics Prediction in Unknown Environments 提出PI-WAN，用于未知环境中四旋翼动力学精确预测与鲁棒控制。 MPC model predictive control
12 Environment-Aware and Human-Cooperative Swing Control for Lower-Limb Prostheses in Diverse Obstacle Scenarios 提出环境感知与人机协作的下肢假肢步态控制，解决复杂地形障碍物跨越问题 locomotion
13 Automated Behaviour-Driven Acceptance Testing of Robotic Systems 提出基于行为驱动开发的机器人系统自动化验收测试方法 manipulation
14 Parallel Transmission Aware Co-Design: Enhancing Manipulator Performance Through Actuation-Space Optimization 提出并行传输感知的协同设计方法，提升并联机器人动态性能 trajectory optimization

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

#题目一句话要点标签🔗⭐
15 SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound SonoGym：用于机器人超声复杂手术任务的高性能仿真平台 reinforcement learning deep reinforcement learning DRL ✅
16 A Survey: Learning Embodied Intelligence from Physical Simulators and World Models 综述：基于物理仿真器与世界模型的具身智能学习研究进展 world model embodied AI ✅

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

#题目一句话要点标签🔗⭐
17 VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers VQ-VLA：通过扩展向量量化动作标记器提升视觉-语言-动作模型 spatiotemporal vision-language-action VLA ✅

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

#题目一句话要点标签🔗⭐
18 Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding Evo-0：提出一种隐式空间理解的视觉-语言-动作模型，提升机器人操作能力。 depth estimation spatial relationship vision-language-action

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

#题目一句话要点标签🔗⭐
19 2024 NASA SUITS Report: LLM-Driven Immersive Augmented Reality User Interface for Robotics and Space Exploration URSA：基于LLM的沉浸式AR人机交互系统，用于机器人与太空探索 large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页