cs.RO（2026-08-13）

📊 共 21 篇论文 | 🔗 1 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) (5) 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) (11 篇)

#题目一句话要点标签🔗⭐
1 HumanoidVLN: A Physics-Grounded Simulator and Benchmark for Vision-Language Navigation Across Diverse Humanoid Embodiments 提出HumanoidVLN以解决人形机器人视觉语言导航中的物理约束问题 humanoid humanoid robot bipedal ✅
2 H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models 提出H2R-Bench以解决人机操作视频生成的跨体现问题 manipulation world model world models
3 NestDex: Nested Policy Learning with Copilot Assisted Teleoperation for Dexterous Manipulation 提出NestDex以解决灵巧操作中的演示收集难题 manipulation dexterous manipulation teleoperation
4 HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark 提出HumanTracker以解决人类动作跟踪评估不足问题 humanoid motion tracking teleoperation
5 S2-HWM: Sparse Event-Structured Hierarchical World Model for Long-Horizon Surgical Robot Manipulation 提出S2-HWM以解决长时间段外科机器人操作中的稀疏奖励问题 manipulation world model world models
6 Decoding Task Progress from VLA Representations 提出线性探测器以解码视觉语言行动模型的任务进展 manipulation vision-language-action VLA
7 ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models 提出ContactGuard以解决机器人接触前执行监控问题 manipulation world model world models
8 Predictive Relative-Velocity Steering for Safe Robotic Manipulator Teleoperation in Dynamic Environments 提出预测相对速度引导以解决动态环境中的安全遥操作问题 teleoperation
9 Deliberate Practice: Learning Robot Skills under a Budget 提出Deliberate Practice算法以解决机器人技能学习预算限制问题 manipulation
10 FAM-DQ: A Dual-Quadrotor-Based Fully Actuated Aerial Manipulator for High-Torque Interaction 提出FAM-DQ以解决高扭矩空中操控问题 manipulation
11 hint$^2$: Hierarchical World Models for Inference-Time Temporal Logic Guidance 提出hint$^2$以解决机器人执行复杂指令的挑战 manipulation world model world models

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
12 FIRE-VLA: Failure-Informed Self-Evolution for Vision-Language-Action Models in Autonomous Driving 提出FIRE-VLA框架以解决自主驾驶中的失败信息利用问题 reinforcement learning distillation vision-language-action
13 Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learning 提出Temporal GRPO以解决轨迹级信用混淆问题 reinforcement learning vision-language-action VLA
14 BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving 提出BrainWAM以解决自主驾驶中的语义约束与预测动态协调问题 world model world models world action model
15 Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning 提出Seeker以解决视觉瓶颈问题，提升策略学习效率 policy learning affordance
16 Graph-MambaNav: Spatial-Temporal Graph Mamba Leveraging Object-Relation Knowledge for Object-Goal Navigation 提出Graph-MambaNav以解决目标导向导航中的信息传播问题 Mamba

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

#题目一句话要点标签🔗⭐
17 SAP-Nav: Spatial Semantic Representation Meets Active Perception for Hierarchical Open-Vocabulary Object Navigation 提出SAP-Nav以解决层次化开放词汇目标导航问题 open-vocabulary open vocabulary
18 FUSE: Active Functional Affordance Grounding through Adaptive Semantic-Geometric Evidence Acquisition 提出FUSE以解决主动功能可供性定位问题 affordance
19 Genetic Fuzzy System-Based Multi-Robot Coordination for Planetary Missions 提出基于遗传模糊系统的多机器人协调方法以优化行星任务 elevation map traversability

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

#题目一句话要点标签🔗⭐
20 AirForesight: Current-to-Future Spatial Map Imagination with Cross-Space Planning Consistency for UAV-VLN 提出AirForesight框架以解决无人机视觉语言导航中的空间推理问题 VLN large language model
21 ASPIRE-VINS: Adaptive Spline-based Visual-inertial Navigation System With Robust 3D Measurement Residuals 提出ASPIRE-VINS以解决视觉惯性导航系统的灵活性不足问题 TAMP

⬅️ 返回 cs.RO 首页 · 🏠 返回主页