cs.RO（2026-04-15）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 Beyond Conservative Automated Driving in Multi-Agent Scenarios via Coupled Model Predictive Control and Deep Reinforcement Learning 提出基于耦合MPC与深度强化学习的自动驾驶方法，提升多智能体场景下的安全性和效率。 MPC model predictive control reinforcement learning
2 UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception UMI-3D：扩展通用操作界面至3D空间感知，提升具身操作数据采集的鲁棒性 manipulation visual SLAM spatiotemporal
3 Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection 提出Goal2Skill框架，通过自适应规划与反思实现长时程操作任务 manipulation vision-language-action VLA
4 RobotPan: A 360$^\circ$ Surround-View Robotic Vision System for Embodied Perception RobotPan：面向具身感知的360°全景机器人视觉系统 locomotion manipulation loco-manipulation
5 Scale-Invariant Sampling in Multi-Arm Bandit Motion Planning for Object Extraction 提出尺度不变采样策略，解决狭窄空间内物体提取的运动规划问题 motion planning
6 Evolvable Embodied Agent for Robotic Manipulation via Long Short-Term Reflection and Optimization 提出EEAgent框架，通过长短期反射优化实现机器人操作的自进化 manipulation
7 Stability Principle Underlying Passive Dynamic Walking of Rimless Wheel 基于被动动态步行的无轮缘轮稳定性原理研究 dynamic walking
8 A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies 分析Sim-to-Real协同训练机制，提升生成式机器人策略性能 manipulation cross-embodiment

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

#题目一句话要点标签🔗⭐
9 Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap 无人机视觉-语言导航综述：梳理技术演进与未来研究方向 world model world models vision-language-action
10 EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development EmbodiedClaw：用于具身AI开发的对话式工作流执行框架 policy learning embodied AI
11 Failure Identification in Imitation Learning Via Statistical and Semantic Filtering FIDeL：结合统计与语义过滤的模仿学习失败识别方法 imitation learning multimodal

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

#题目一句话要点标签🔗⭐
12 RadarSplat-RIO: Indoor Radar-Inertial Odometry with Gaussian Splatting-Based Radar Bundle Adjustment 提出RadarSplat-RIO以解决室内雷达惯性测距中的漂移问题 visual odometry gaussian splatting splatting

⬅️ 返回 cs.RO 首页 · 🏠 返回主页