cs.RO（2026-04-08）

📊 共 15 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 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 Robust Quadruped Locomotion via Evolutionary Reinforcement Learning 提出基于进化强化学习的鲁棒四足机器人运动控制方法，提升环境适应性。 quadruped locomotion reinforcement learning
2 Towards Multi-Object Nonprehensile Transportation via Shared Teleoperation: A Framework Based on Virtual Object Model Predictive Control 提出基于虚拟对象模型预测控制的共享遥操作框架，实现多物体非抓取运输 manipulation MPC model predictive control
3 TAMEn: Tactile-Aware Manipulation Engine for Closed-Loop Data Collection in Contact-Rich Tasks 提出TAMEn触觉感知操作引擎，用于接触丰富任务中的闭环数据收集。 manipulation bi-manual bimanual manipulation
4 Flow Motion Policy: Manipulator Motion Planning with Flow Matching Models 提出基于流匹配模型的Flow Motion Policy，提升机器人操作臂运动规划的成功率和效率。 motion planning flow matching
5 RichMap: A Reachability Map Balancing Precision, Efficiency, and Flexibility for Rich Robot Manipulation Tasks 提出RichMap以解决机器人操作任务中的精度与效率平衡问题 manipulation diffusion policy cross-embodiment
6 RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild 提出RoSHI以解决人类数据收集中的便携性与鲁棒性问题 humanoid policy learning sam 3D
7 Genie Sim PanoRecon: Fast Immersive Scene Generation from Single-View Panorama Genie Sim PanoRecon：基于单视角全景图的快速沉浸式场景生成 manipulation gaussian splatting splatting ✅
8 KITE: Keyframe-Indexed Tokenized Evidence for VLM-Based Robot Failure Analysis KITE：基于关键帧索引Token证据的VLM机器人故障分析方法 dual-arm open-vocabulary open vocabulary ✅
9 BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes BiDexGrasp：提出大规模双臂灵巧抓取数据集和生成模型，解决物体几何尺寸差异下的抓取问题。 bi-manual
10 Robots that learn to evaluate models of collective behavior 提出基于强化学习的机器人框架，通过闭环交互评估鱼群行为模型 sim-to-real reinforcement learning

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
11 Telecom World Models: Unifying Digital Twins, Foundation Models, and Predictive Planning for 6G 提出电信世界模型，融合数字孪生、基础模型与预测规划，赋能6G网络 world model world models large language model
12 Sustainable Transfer Learning for Adaptive Robot Skills 针对自适应机器人技能，提出可持续的迁移学习方法 reinforcement learning zero-shot transfer
13 Learning-Based Strategy for Composite Robot Assembly Skill Adaptation 提出基于学习的复合机器人装配技能自适应策略，解决工业机器人接触力控制难题 reinforcement learning SAC

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

#题目一句话要点标签🔗⭐
14 Infrastructure First: Enabling Embodied AI for Science in the Global South 面向全球南方，提出基础设施优先的具身智能科研方案，解决科研能力瓶颈。 embodied AI foundation 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 CADENCE: Context-Adaptive Depth Estimation for Navigation and Computational Efficiency CADENCE：针对导航和计算效率的情境自适应深度估计 depth estimation monocular depth

⬅️ 返回 cs.RO 首页 · 🏠 返回主页