cs.RO（2026-04-02）

📊 共 14 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10 🔗4) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 Realistic Lip Motion Generation Based on 3D Dynamic Viseme and Coarticulation Modeling for Human-Robot Interaction 提出基于3D动态视位和协同发音建模的唇动生成框架，用于人机交互。 humanoid humanoid robot motion generation ✅
2 AnchorVLA: Anchored Diffusion for Efficient End-to-End Mobile Manipulation AnchorVLA：用于高效端到端移动操作的锚定扩散策略 manipulation mobile manipulation diffusion policy ✅
3 Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior 提出基于可行动作邻域先验的视觉-语言-动作微调方法，提升机器人操作泛化性。 manipulation vision-language-action VLA
4 AURA: Multimodal Shared Autonomy for Real-World Urban Navigation AURA：用于真实城市导航的多模态共享自主系统 teleoperation multimodal
5 Bridging Large-Model Reasoning and Real-Time Control via Agentic Fast-Slow Planning 提出Agentic Fast-Slow Planning框架，桥接大模型推理与车辆实时控制。 MPC model predictive control large language model ✅
6 Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning POCO：通过裁剪目标函数的后验优化，提升生成策略学习的效率与稳定性 manipulation policy learning VLA ✅
7 Smooth Feedback Motion Planning with Reduced Curvature 提出一种曲率优化的反馈运动规划方法，提升机器人运动的平滑性和效率 motion planning
8 Cross-Modal Visuo-Tactile Object Perception 提出跨模态潜在滤波器(CMLF)，用于提升机器人触觉视觉融合的对象属性估计。 manipulation
9 OpenGo: An OpenClaw-Based Robotic Dog with Real-Time Skill Switching OpenGo：一种基于OpenClaw的机器人狗，支持实时技能切换 Unitree
10 Robust Autonomous Control of a Magnetic Millirobot in In Vitro Cardiac Flow 提出基于视觉引导的磁性微型机器人自主控制系统，用于模拟心脏血流环境下的精准导航。 MPC

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
11 HyVGGT-VO: Tightly Coupled Hybrid Dense Visual Odometry with Feed-Forward Models 提出HyVGGT-VO以解决稠密视觉里程计的计算效率与重建能力问题 visual odometry visual SLAM optical flow ✅
12 Stop Wandering: Efficient Vision-Language Navigation via Metacognitive Reasoning 提出MetaNav，通过元认知推理实现高效的视觉-语言导航 semantic map VLN foundation model
13 ROS 2-Based LiDAR Perception Framework for Mobile Robots in Dynamic Production Environments, Utilizing Synthetic Data Generation, Transformation-Equivariant 3D Detection and Multi-Object Tracking 提出基于ROS 2的LiDAR感知框架，用于动态生产环境中移动机器人的鲁棒目标跟踪。 6D pose estimation spatiotemporal

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

#题目一句话要点标签🔗⭐
14 Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving 提出因果场景叙述（CSN）框架，提升VLA自动驾驶模型在复杂环境下的决策能力。 DPO vision-language-action VLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页