cs.RO（2025-10-28）

📊 共 18 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 A Survey on Collaborative SLAM with 3D Gaussian Splatting 综述：基于3D高斯溅射的多机器人协同SLAM技术 sim2real distillation 3D gaussian splatting
2 Dynamically-Consistent Trajectory Optimization for Legged Robots via Contact Point Decomposition 提出基于接触点分解的动态一致性轨迹优化方法，用于生成腿式机器人可靠运动 quadruped legged robot trajectory optimization
3 Language-Conditioned Representations and Mixture-of-Experts Policy for Robust Multi-Task Robotic Manipulation 提出LCVR和LMoE-DP框架，提升多任务机器人操作的鲁棒性和效率 manipulation imitation learning diffusion policy
4 Towards Quadrupedal Jumping and Walking for Dynamic Locomotion using Reinforcement Learning 提出基于课程学习的强化学习框架，实现四足机器人动态跳跃与行走 quadruped locomotion sim2real
5 A Humanoid Visual-Tactile-Action Dataset for Contact-Rich Manipulation 提出一种类人视觉-触觉-动作数据集以解决接触丰富操控问题 humanoid humanoid robot manipulation
6 Manipulate as Human: Learning Task-oriented Manipulation Skills by Adversarial Motion Priors 提出基于对抗运动先验的HMAMP方法，学习类人操作技能，解决机器人自然交互问题。 manipulation human motion adversarial motion priors
7 VOCALoco: Viability-Optimized Cost-aware Adaptive Locomotion VOCALoco：面向四足机器人，提出可行性优化和成本感知的自适应步态选择框架 quadruped legged robot locomotion
8 Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames 提出盲folded专家以提升机器人操作与游戏中的泛化能力 manipulation foundation model
9 DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation DynaRend：通过掩码未来渲染学习3D动态，用于机器人操作 manipulation representation learning
10 A Comprehensive Survey on Surgical Digital Twin 全面综述手术数字孪生技术，旨在弥合实验室原型与临床应用之间的差距。 shared control scene understanding multimodal
11 Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World 提出BiBo以解决人形代理在开放环境中交互能力不足的问题 humanoid
12 Embodying Physical Computing into Soft Robots 提出将物理计算融入软体机器人的框架，实现自主智能。 locomotion
13 An Adaptive Inspection Planning Approach Towards Routine Monitoring in Uncertain Environments 提出一种自适应检测规划方法，用于不确定环境下的机器人日常监测 quadruped

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

#题目一句话要点标签🔗⭐
14 LagMemo: Language 3D Gaussian Splatting Memory for Multi-modal Open-vocabulary Multi-goal Visual Navigation 提出LagMemo，利用语言3D高斯溅射记忆实现多模态开放词汇多目标视觉导航 3D gaussian splatting gaussian splatting splatting ✅
15 NVSim: Novel View Synthesis Simulator for Large Scale Indoor Navigation NVSim：提出基于图像序列的大规模室内导航新视角合成模拟器 3D gaussian splatting gaussian splatting splatting

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

#题目一句话要点标签🔗⭐
16 Feature Matching-Based Gait Phase Prediction for Obstacle Crossing Control of Powered Transfemoral Prosthesis 提出基于特征匹配的步态相位预测方法，用于动力式股骨假肢的障碍跨越控制 feature matching

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

#题目一句话要点标签🔗⭐
17 Spatiotemporal Calibration of Doppler Velocity Logs for Underwater Robots 提出统一迭代校准框架，解决水下机器人DVL时空外参高精度标定问题 spatiotemporal

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

#题目一句话要点标签🔗⭐
18 PFEA: An LLM-based High-Level Natural Language Planning and Feedback Embodied Agent for Human-Centered AI PFEA：一种基于LLM的自然语言规划与反馈具身智能体，用于以人为本的AI large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页