cs.RO（2026-08-12）

📊 共 13 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (7 篇)

#题目一句话要点标签🔗⭐
1 HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing 提出HandEdit以解决人机手部图像编辑的挑战 manipulation dexterous hand teleoperation
2 Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL 提出基于SMPC示范的稀疏离线到在线RL以解决机器人自主性问题 quadruped humanoid locomotion
3 Policy-Induced Hand Priors in Humanoid Dual-Arm Manipulation: Diagnosing and Mitigating Initial-Pose Dependence 提出手部先验以解决人形双臂操控中的初始姿态依赖问题 humanoid manipulation dual-arm
4 G0.5: One Autoregressive Stream for Robot Reasoning and Action 提出G0.5以解决机器人推理与行动的统一问题 manipulation mobile manipulation flow matching
5 ContactIPM: A Structure-Exploiting Interior-Point Solver for Contact-Implicit Trajectory Optimization 提出ContactIPM以解决接触隐式轨迹优化中的MPCC问题 trajectory optimization
6 DaViNCi: A Dataset Towards Outdoor Vision-and-Language Navigation with Continuous Actions and Dynamic Elements 提出DaViNCi数据集以解决户外视觉语言导航中的动态与连续性问题 sim-to-real VLN ✅
7 Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deployment 提出混合规划架构以提升自动驾驶行为的安全性与可解释性 motion planning

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

#题目一句话要点标签🔗⭐
8 Keep the Future, Drop the Rollout: RIFT for World Action Models 提出RIFT以解决世界动作模型中的视频回放延迟问题 world action model world action models
9 IoT-Enabled Autonomous Maritime Navigation in Smart Ports: A Curriculum-Guided Shared Policy Learning Framework 提出课程引导的共享策略学习框架以解决智能港口自主导航问题 reinforcement learning policy learning
10 Enhancing Visual Domain Robustness in Behaviour Cloning via Saliency-Guided Augmentation 提出RoboSaGA以解决视觉领域鲁棒性不足问题 behavior cloning spatiotemporal ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
11 StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models 提出StellaVLA以解决视觉-语言-动作模型在OOD任务中的适应性问题 human-to-robot cross-embodiment vision-language-action

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
12 Video2Track: From Real-World Interaction Videos to Steerable Adversarial Closed-Track Testing for Automated Driving Systems 提出Video2Track以解决自动驾驶系统闭环测试的复杂性问题 semantic mapping semantic map

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

#题目一句话要点标签🔗⭐
13 D3D-GEN: Robot-Aware Domain-Grounded Interactive 3D World Generation for Social Robotics 提出D3D-GEN以解决社交机器人领域的3D世界生成问题 embodied AI

⬅️ 返回 cs.RO 首页 · 🏠 返回主页