cs.RO（2026-03-23）

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

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection 提出基于关节力矩空间扰动注入的Sim-to-Real方法，提升人形机器人运动策略的鲁棒性 humanoid humanoid locomotion locomotion
2 Make Tracking Easy: Neural Motion Retargeting for Humanoid Whole-body Control 提出NMR框架，通过神经运动重定向实现人型机器人全身控制 humanoid humanoid robot whole-body control
3 UniDex: A Robot Foundation Suite for Universal Dexterous Hand Control from Egocentric Human Videos UniDex：基于自中心人类视频的通用灵巧手控制机器人基础套件 manipulation dexterous hand dexterous manipulation
4 BiPreManip: Learning Affordance-Based Bimanual Preparatory Manipulation through Anticipatory Collaboration BiPreManip：通过预测协作学习基于可供性的双臂预备操作 manipulation bi-manual bimanual manipulation
5 MEVIUS2: Practical Open-Source Quadruped Robot with Sheet Metal Welding and Multimodal Perception MEVIUS2：实用开源四足机器人，采用钣金焊接和多模态感知 quadruped reinforcement learning multimodal ✅
6 ROBOGATE: Adaptive Failure Discovery for Safe Robot Policy Deployment via Two-Stage Boundary-Focused Sampling ROBOGATE：通过两阶段边界聚焦采样自适应发现故障，保障机器人策略安全部署 manipulation vision-language-action VLA
7 Can a Robot Walk the Robotic Dog: Triple-Zero Collaborative Navigation for Heterogeneous Multi-Agent Systems 提出Triple-Zero协同导航框架，实现异构多机器人零样本协同路径规划 quadruped humanoid humanoid robot ✅
8 DexDrummer: In-Hand, Contact-Rich, and Long-Horizon Dexterous Robot Drumming DexDrummer：提出一种能进行手内、接触丰富、长时程灵巧机器人鼓乐演奏的框架。 manipulation dexterous manipulation bi-manual
9 Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning 提出闭环语言强化学习框架，用于解决机器人任务级规划中的不确定性问题。 manipulation reinforcement learning large language model
10 RAFL: Generalizable Sim-to-Real of Soft Robots with Residual Acceleration Field Learning RAFL：基于残差加速度场学习的软体机器人Sim-to-Real泛化 sim-to-real
11 Auction-Based Task Allocation with Energy-Conscientious Trajectory Optimization for AMR Fleets 提出基于拍卖的任务分配与节能轨迹优化框架，提升AMR车队效率。 trajectory optimization
12 Optimal Solutions for the Moving Target Vehicle Routing Problem with Obstacles via Lazy Branch and Price 提出Lazy BPRC算法，解决带障碍的移动目标车辆路径规划问题，实现最优解。 motion planning
13 RTD-RAX: Fast, Safe Trajectory Planning for Systems under Unknown Disturbances RTD-RAX：面向未知扰动系统的快速安全轨迹规划 trajectory optimization

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
14 VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models 提出VP-VLA以解决视觉-语言-动作模型的空间精度问题 vision-language-action VLA visual grounding
15 SafePilot: A Framework for Assuring LLM-enabled Cyber-Physical Systems SafePilot：用于保障LLM驱动的CPS安全性的分层神经符号框架 large language model

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

#题目一句话要点标签🔗⭐
16 Do World Action Models Generalize Better than VLAs? A Robustness Study 对比研究世界行动模型与视觉-语言-行动模型在机器人任务中的泛化鲁棒性 world model spatiotemporal vision-language-action
17 Cross-Modal Reinforcement Learning for Navigation with Degraded Depth Measurements 提出基于跨模态强化学习的导航方法，解决深度信息退化场景下的机器人导航问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
18 Memory-Efficient Boundary Map for Large-Scale Occupancy Grid Mapping 提出一种内存高效的边界地图方法，用于大规模占据栅格地图构建。 occupancy grid ✅
19 IGV-RRT: Prior-Real-Time Observation Fusion for Active Object Search in Changing Environments 提出IGV-RRT，融合先验知识与实时观测，解决动态环境中主动目标搜索问题 semantic mapping semantic map

⬅️ 返回 cs.RO 首页 · 🏠 返回主页