cs.RO(2026-02-14)

📊 共 18 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一:机器人控制 (Robot Control) (11 🔗1) 支柱二:RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三:空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一:机器人控制 (Robot Control) (11 篇)

#题目一句话要点标签🔗
1 Humanoid Hanoi: Investigating Shared Whole-Body Control for Skill-Based Box Rearrangement 提出基于共享全身控制的人形机器人技能化箱子重排框架,解决长时程任务难题 humanoid humanoid robot whole-body control
2 Semantic-Contact Fields for Category-Level Generalizable Tactile Tool Manipulation 提出语义-接触场(SCFields)以实现类别级通用触觉工具操作 manipulation sim-to-real diffusion policy
3 Impact-Robust Posture Optimization for Aerial Manipulation 提出一种冲击鲁棒的姿态优化方法,提升空中操作机器人的抗冲击能力。 quadruped humanoid humanoid robot
4 A Kung Fu Athlete Bot That Can Do It All Day: Highly Dynamic, Balance-Challenging Motion Dataset and Autonomous Fall-Resilient Tracking 提出KungFuAthlete数据集与融合高动态运动跟踪和跌倒恢复的机器人控制策略 humanoid humanoid robot fall recovery
5 HybridFlow: A Two-Step Generative Policy for Robotic Manipulation HybridFlow:一种用于机器人操作的两步生成策略,提升交互速度与精度。 manipulation diffusion policy flow matching
6 Symmetry-Aware Fusion of Vision and Tactile Sensing via Bilateral Force Priors for Robotic Manipulation 提出基于双边力先验的对称感知视觉触觉融合方法,用于机器人操作中的插入任务。 manipulation multimodal
7 Hierarchical Audio-Visual-Proprioceptive Fusion for Precise Robotic Manipulation 提出一种层级音视频触觉融合框架,用于提升机器人操作的精确性。 manipulation multimodal
8 UAV-SEAD: State Estimation Anomaly Dataset for UAVs UAV-SEAD:用于无人机状态估计异常检测的大规模真实世界数据集 manipulation visual odometry optical flow
9 Push-Placement: A Hybrid Approach Integrating Prehensile and Non-Prehensile Manipulation for Object Rearrangement 提出Push-Placement混合操作原语,提升物体重排任务效率 manipulation
10 AgentRob: From Virtual Forum Agents to Hijacked Physical Robots AgentRob:通过在线论坛将LLM智能体与物理机器人连接,实现新型人机交互 Unitree large language model
11 XIT: Exploration and Exploitation Informed Trees for Active Gas Distribution Mapping in Unknown Environments 提出XIT算法,通过探索-利用平衡树规划实现未知环境下的主动气体分布测绘。 teleoperation

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

#题目一句话要点标签🔗
12 MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer 提出MOTIF,通过学习动作模体实现少样本跨具身迁移 flow matching cross-embodiment embodiment transfer
13 TactAlign: Human-to-Robot Policy Transfer via Tactile Alignment 提出TactAlign以解决人机触觉信号转移问题 policy learning privileged information human-to-robot
14 From Snapshot Sensing to Persistent EM World Modeling: A Generative-Space Perspective for ISAC 提出基于生成空间的ISAC框架,实现持久电磁环境建模 world model

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

#题目一句话要点标签🔗
15 High-fidelity 3D reconstruction for planetary exploration 提出基于NeRF和Gaussian Splatting的行星探测高保真3D重建方案 gaussian splatting splatting NeRF
16 ONRAP: Occupancy-driven Noise-Resilient Autonomous Path Planning ONRAP:基于占据栅格的抗噪声自主路径规划,提升动态环境下的导航可靠性。 occupancy grid

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

#题目一句话要点标签🔗
17 Ontological grounding for sound and natural robot explanations via large language models 提出一种融合本体推理与大语言模型的混合框架,用于生成语义对齐且自然的机器人解释。 large language model
18 The More the Merrier: Running Multiple Neuromorphic Components On-Chip for Robotic Control 提出基于脉冲神经网络状态机的片上机器人控制方案,解决多网络协同问题 multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页