cs.RO（2026-04-14）

📊 共 22 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (6) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers	WHOLE-MoMa：利用离线强化学习提升移动操作机器人全身控制性能	whole-body control WBC manipulation
2	Learning Versatile Humanoid Manipulation with Touch Dreaming	提出基于触觉梦想的人形机器人灵巧操作学习框架HTD，提升复杂操作任务性能。	humanoid humanoid robot whole-body control
3	Robotic Manipulation is Vision-to-Geometry Mapping ($f(v) \rightarrow G$): Vision-Geometry Backbones over Language and Video Models	提出视觉-几何模型以解决机器人操作中的几何映射问题	manipulation world model world models
4	XRZero-G0: Pushing the Frontier of Dexterous Robotic Manipulation with Interfaces, Quality and Ratios	XRZero-G0：通过VR界面和数据混合策略提升灵巧机器人操作的数据质量与效率	manipulation teleoperation policy learning	✅
5	Tree Learning: A Multi-Skill Continual Learning Framework for Humanoid Robots	提出Tree Learning框架，解决人形机器人多技能持续学习中的灾难性遗忘问题。	humanoid humanoid robot locomotion
6	Scalable Trajectory Generation for Whole-Body Mobile Manipulation	AutoMoMa：一种可扩展的全身移动操作轨迹生成框架，加速机器人学习。	manipulation mobile manipulation trajectory optimization
7	PAINT: Partner-Agnostic Intent-Aware Cooperative Transport with Legged Robots	PAINT：基于腿式机器人的无需伙伴信息的意图感知协同运输框架	legged robot locomotion manipulation
8	FastGrasp: Learning-based Whole-body Control method for Fast Dexterous Grasping with Mobile Manipulators	FastGrasp：面向移动操作机器人的快速灵巧抓取的学习型全身控制方法	whole-body control manipulation sim-to-real
9	E2E-Fly: An Integrated Training-to-Deployment System for End-to-End Quadrotor Autonomy	E2E-Fly：用于四旋翼无人机端到端自主控制的集成式训练-部署系统	sim-to-real domain randomization reinforcement learning
10	Robotic Nanoparticle Synthesis via Solution-based Processes	提出基于螺旋几何的机器人操作规划框架，用于自动化溶液法纳米颗粒合成。	manipulation motion planning motion representation
11	Asymptotically Stable Gait Generation and Instantaneous Walkability Determination for Planar Almost Linear Biped with Knees	针对膝关节平面近线性双足机器人，提出渐近稳定步态生成与瞬时可行走性判定方法	bipedal biped
12	Evolving the Complete Muscle: Efficient Morphology-Control Co-design for Musculoskeletal Locomotion	提出基于谱设计的肌肉骨骼机器人形态-控制协同优化方法，提升复杂地形下的运动性能。	locomotion

🔬 支柱三：空间感知与语义 (Perception & Semantics) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting	Habitat-GS：基于动态高斯溅射的高保真导航模拟器，用于具身智能体训练。	3D gaussian splatting 3DGS gaussian splatting
14	RMGS-SLAM: Real-time Multi-sensor Gaussian Splatting SLAM	提出RMGS-SLAM，实现大规模场景下实时多传感器融合的3D高斯溅射SLAM	3D gaussian splatting 3DGS gaussian splatting
15	GGD-SLAM: Monocular 3DGS SLAM Powered by Generalizable Motion Model for Dynamic Environments	GGD-SLAM：基于可泛化运动模型的单目3DGS SLAM，用于动态环境	visual SLAM 3D gaussian splatting 3DGS
16	OVAL: Open-Vocabulary Augmented Memory Model for Lifelong Object Goal Navigation	OVAL：面向终身物体目标导航的开放词汇增强记忆模型	open-vocabulary open vocabulary
17	D-BDM: A Direct and Efficient Boundary-Based Occupancy Grid Mapping Framework for LiDARs	D-BDM：一种高效的激光雷达直接边界占用栅格地图构建框架	occupancy grid
18	Reliability-Guided Depth Fusion for Glare-Resilient Navigation Costmaps	提出基于深度可靠性建模的Costmap构建方法，提升反光环境下机器人导航的鲁棒性。	occupancy grid

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

#	题目	一句话要点	标签	🔗	⭐
19	HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models	HazardArena：评估视觉-语言-动作模型中的语义安全性	vision-language-action VLA
20	DeCoNav: Dialog enhanced Long-Horizon Collaborative Vision-Language Navigation	提出DeCoNav，通过对话增强实现长期协作视觉-语言导航。	VLN

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

#	题目	一句话要点	标签	🔗	⭐
21	A Comparison of Reinforcement Learning and Optimal Control Methods for Path Planning	提出基于DDPG的路径规划方法，加速威胁环境下的自主车辆实时决策。	reinforcement learning
22	Learning step-level dynamic soaring in shear flow	提出基于步进式动态滑翔控制策略，实现复杂风切变环境下的自主能量获取飞行	reinforcement learning deep reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页