cs.RO（2025-12-09）

📊 共 23 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (18 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (18 篇)

#题目一句话要点标签🔗⭐
1 High-Performance Dual-Arm Task and Motion Planning for Tabletop Rearrangement 提出SDAR框架，解决复杂双臂协同桌面重排任务中的任务与运动规划问题 dual-arm motion planning task and motion planning
2 Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation 提出Zero-Splat TeleAssist，实现基于CCTV的零样本语义遥操作 teleoperation world model monocular depth
3 VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer 提出AEGIS架构，通过可插拔安全约束层提升VLA模型在机器人操作中的安全性。 manipulation vision-language-action VLA ✅
4 Learning Robot Manipulation from Audio World Models 提出基于生成式隐空间流匹配模型的机器人音频世界模型，用于提升操作任务性能 manipulation flow matching world model
5 Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model 提出EToT框架，利用具身世界模型实现更可靠的机器人操作规划 manipulation sim2real real2sim
6 Mind to Hand: Purposeful Robotic Control via Embodied Reasoning Lumo-1：通过具身推理实现通用机器人控制，连接“思维”与“行动” bi-manual reinforcement learning cross-embodiment
7 OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transfer OSMO：用于人-机器人技能迁移的开源触觉手套，提升操作任务成功率。 manipulation human-to-robot
8 Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations 提出基于语言的动作表征，弥合机器人控制中的尺度差异。 manipulation motion representation large language model
9 Sim2Swim: Zero-Shot Velocity Control for Agile AUV Maneuvering in 3 Minutes Sim2Swim：3分钟训练零样本水下机器人敏捷速度控制 sim2real domain randomization reinforcement learning
10 RVC-NMPC: Nonlinear Model Predictive Control with Reciprocal Velocity Constraints for Mutual Collision Avoidance in Agile UAV Flight 提出基于RVC约束的NMPC方法，用于敏捷无人机飞行中的相互避障 model predictive control
11 Semantic Trajectory Generation for Goal-Oriented Spacecraft Rendezvous 提出SAGES框架，通过自然语言指令生成满足约束的航天器交会对接轨迹。 trajectory optimization language conditioned
12 ShelfAware: Real-Time Visual-Inertial Semantic Localization in Quasi-Static Environments with Low-Cost Sensors ShelfAware：利用低成本传感器在准静态环境中进行实时视觉惯性语义定位 shared control VIO
13 SensHRPS: Sensing Comfortable Human-Robot Proxemics and Personal Space With Eye-Tracking SensHRPS：利用眼动追踪感知舒适的人机近距离交互和个人空间 humanoid humanoid robot
14 Enabling Autonomous Navigation in a Snake Robot through Visual-Inertial Odometry and Closed-Loop Trajectory Tracking Control 针对蛇形机器人，提出基于视觉惯性里程计和闭环轨迹跟踪的自主导航方案 locomotion teleoperation
15 Masked Generative Policy for Robotic Control 提出掩码生成策略MGP，用于提升机器人控制任务的模仿学习性能。 manipulation imitation learning
16 Data-Driven Dynamic Parameter Learning of manipulator robots 提出基于Transformer的机器人动力学参数数据驱动学习方法，提升Sim-to-Real迁移性能。 sim-to-real
17 Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making 提出MPDiffuser，结合扩散模型规划器与动力学模型，提升离线决策控制性能 quadruped
18 Semantic-Metric Bayesian Risk Fields: Learning Robot Safety from Human Videos with a VLM Prior 提出基于VLM先验的语义-度量贝叶斯风险场，从人类视频中学习机器人安全策略。 trajectory optimization ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
19 A Multi-Robot Platform for Robotic Triage Combining Onboard Sensing and Foundation Models 提出一种结合机载传感与基础模型的多机器人平台，用于灾难现场的机器人分诊 foundation model
20 Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging 提出基于参数融合的视觉-语言-动作机器人策略微调方法，提升泛化能力。 vision-language-action
21 Chat with UAV -- Human-UAV Interaction Based on Large Language Models 提出基于双Agent的大语言模型人机交互框架，提升无人机任务执行灵活性 large language model

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

#题目一句话要点标签🔗⭐
22 Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation 提出DualVLN双系统模型，提升视觉-语言导航的泛化性和实时性。 transformer policy VLN foundation model

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

#题目一句话要点标签🔗⭐
23 Learning Spatiotemporal Tubes for Temporal Reach-Avoid-Stay Tasks using Physics-Informed Neural Networks 提出基于物理信息神经网络的时空管道学习方法，解决时序可达-避免-停留任务。 spatiotemporal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页