cs.RO（2026-08-05）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 GASP: GPU-Accelerated Safe Planner for Real-Time Collision-Aware Motion Generation with Latent Trajectory Sampling 提出GASP以解决实时碰撞感知运动生成问题 trajectory optimization reinforcement learning motion generation
2 BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation 提出BridgeVLA++以解决3D操作中的数据效率和记忆问题 manipulation bi-manual bimanual manipulation ✅
3 Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models 提出Mind-VLA以解决视觉-语言-动作模型中的目标对象理解问题 manipulation VGGT vision-language-action
4 RORA: Realistic Object Reconstruction with Articulation 提出RORA以解决物体关节重建问题 motion tracking manipulation dexterous hand
5 SSC: A Verifiable Structured Representation for Bimanual Manipulation Labelling 提出结构化子任务链以解决双手操作标注的可验证性问题 manipulation bi-manual bimanual manipulation
6 DreamWAM: Beyond RGB Future Prediction for World Action Models 提出DreamWAM以解决未来状态预测中的RGB依赖问题 manipulation world model world models ✅
7 Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models 提出显式语言记忆以解决长时间规划中的挑战 sim-to-real vision-language-action VLA
8 Retrieve in Time, Correct in Frequency 提出RTCF框架以解决长时间操作中的执行误差问题 manipulation vision-language-action VLA
9 SCOPE: Field-of-View-Aware Path Planning in Unknown 3D Environments via Safety-Volume Certification 提出SCOPE以解决未知3D环境中的安全路径规划问题 trajectory optimization

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

#题目一句话要点标签🔗⭐
10 Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies 提出闭环目标与控制审计以解决任务向量否定问题 flow matching vision-language-action VLA
11 AI-based single-shot structured-light depth reconstruction for real-time laparoscopic surgical guidance 提出基于AI的单次结构光深度重建以解决实时腹腔镜手术引导问题 MAE depth estimation monocular depth
12 Structured LLM Reasoning for Zero-Shot Human--Robot Coordination Under Hidden Goals 提出结构化大语言模型以解决零-shot人机协作问题 reinforcement learning large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
13 GUARD: Grounding Uncertainty and Ablation-Based Risk Detection for Diffusion-Based VLAs 提出GUARD以解决扩散基础视觉语言行动的风险检测问题 vision-language-action VLA multimodal

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
14 SpikingNav: Robust Embodied Navigation with Spiking Neural Policies 提出SpikingNav以解决视觉干扰下的导航鲁棒性问题 egocentric

⬅️ 返回 cs.RO 首页 · 🏠 返回主页