cs.RO（2026-07-16）

📊 共 27 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (19 篇)

#题目一句话要点标签🔗⭐
1 Scaling Behavior Foundation Model for Humanoid Robots 提出行为基础模型以提升类人机器人控制能力 humanoid humanoid robot humanoid control
2 Learning Agile Navigation in Crowded Environments for Quadruped Robots 提出VOP-Nav以解决四足机器人在拥挤环境中的导航问题 quadruped locomotion Unitree
3 Towards Human-like Physical Intelligence: LifelongVision-Language-Action Learning for Robotic Manipulation 提出LifelongVLA框架以解决机器人操控中的塑性与稳定性权衡问题 manipulation vision-language-action VLA
4 DriftWorld: Fast World Modeling through Drifting 提出DriftWorld以解决扩散模型推理速度慢的问题 manipulation world model world models
5 Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color 提出ChromaGuard以解决VLA模型对颜色敏感性的问题 manipulation vision-language-action VLA
6 BridgeFlow: Fast and Robust SE(2)-Equivariant Motion Planning with Flow Matching 提出BridgeFlow以解决机器人运动规划中的等变性问题 motion planning flow matching classifier-free guidance
7 Representation-Aligned Tactile Grounding for Contact-Rich Robotic Manipulation 提出基于表示对齐的触觉基础以解决接触丰富的机器人操作问题 manipulation vision-language-action VLA
8 MIDAS Hand: Modular low-Impedance Direct-drive Anthropomorphic Sensing Hand 提出MIDAS手以解决灵巧操作硬件不足问题 manipulation dexterous hand dexterous manipulation
9 Catch, Throw, Repeat: Planning for Human-Robot Partner Juggling 提出实时规划与控制架构以解决人机合作杂耍问题 trajectory optimization motion planning human motion
10 Reinforcement Learning for the Full Strawberry Harvesting Process: Obstacle Separation, Detachment, and Placement 提出基于强化学习的草莓采摘全流程解决方案 sim-to-real domain randomization reinforcement learning
11 RoboTTT: Context Scaling for Robot Policies 提出RoboTTT以扩展机器人策略的上下文规模 manipulation vision-language-action foundation model
12 AHEAD: Anticipatory Hand-Driven Teleoperation via Human Intent Prediction 提出AHEAD以解决手动遥控中的反应延迟问题 teleoperation VR teleoperation
13 Motion Planning with Model-Based Diffusion via Constraint Optimization and Adaptive Scheduling 提出基于模型的扩散约束优化与自适应调度以解决单机器人运动规划问题 trajectory optimization motion planning
14 Safe Execution of RL Policies Via Acceleration-Based CBF-QP Constraint Enforcement for Real-World Robotic Deployments 提出加速基于CBF-QP的约束执行方法以确保RL策略安全性 legged robot humanoid Unitree
15 NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation 提出NavCMPO以解决地图无关视觉导航中的推理延迟问题 sim-to-real Unitree reinforcement learning
16 Beyond Implicit Force: Evaluating Explicit Force-Torque Proxies in Action Chunking with Transformers 提出显式力矩代理以解决隐式力感知问题 manipulation teleoperation contact-aware
17 DRIFT: Drift and Aggregation for Motion Planning 提出DRIFT以解决多假设运动规划问题 motion planning
18 KineFuse: Kinematic-Aware Haptic Fusion for In-Hand Occluded-Object Pose Tracking 提出KineFuse以解决手部操作中的物体姿态跟踪问题 manipulation in-hand manipulation ✅
19 Hybrid Rigid-Soft Robotic Gripper with Shape Adaptation, Uniform Force Distribution, and Self-Locking Capabilities 提出混合刚性-软性机器人抓手以解决农业自动化中的抓取挑战 manipulation

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

#题目一句话要点标签🔗⭐
20 CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking 提出CosFly-VLA以解决UAV动态目标追踪中的遮挡问题 reinforcement learning curriculum learning vision-language-action
21 Reflex: Real-Time VLA Control through Streaming Inference 提出Reflex框架以解决实时VLA控制问题 flow matching vision-language-action VLA
22 Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control 通过机械解释性和最优控制提升世界行动模型的鲁棒性 world action model world action models

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

#题目一句话要点标签🔗⭐
23 AeroAct: Action-Centered World-Action Models for Language-Conditioned Quadrotor Flight 提出AeroAct以解决语言条件下四旋翼飞行的导航问题 3D gaussian splatting gaussian splatting splatting
24 An Intelligent-Cloud Edge Multimodal Interaction System for Robots 提出云边多模态交互系统以解决机器人在人机交互中的挑战 scene understanding large language model multimodal
25 SoftNav: Injecting 3D Scene Tokens into VLMs for Embodied Navigation 提出SoftNav以解决3D场景信息与VLMs之间的表示差距问题 scene understanding

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

#题目一句话要点标签🔗⭐
26 Communication-Efficient Relative Pose Estimation with Vision Foundation Models for Ephemeral Collaborative Perception 提出通信高效的相对位姿估计方法解决短暂协作感知问题 foundation model
27 Human-Robot Interaction in GenAI Architectures via the Agent-Client Protocol 提出Agent-Client协议以解决人机交互碎片化问题 large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页