cs.RO（2026-07-14）

📊 共 20 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 FlowWAM: Optical Flow as a Unified Action Representation for World Action Models 提出FlowWAM以解决视频生成中的动作表示问题 manipulation world model world models
2 VistaVLA: Geometry- and Semantic-Aware 3D Gaussian-Grounded VLA for Robotic Manipulation 提出VistaVLA以解决机器人操作中的3D语义理解问题 manipulation policy learning vision-language-action
3 Vision-Based Dribbling for Humanoid Soccer via Privileged Representation Learning 提出基于视觉的机器人控球技术以解决动态对抗问题 humanoid humanoid robot manipulation
4 ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning 提出ExToken以解决VLA-RL框架中的探索停滞问题 manipulation reinforcement learning vision-language-action
5 Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference 提出系统级加速策略以解决视觉-语言-动作推理中的时间冗余问题 manipulation vision-language-action VLA
6 UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies 提出UR-VC以解决时间衍生进度标签不准确问题 manipulation bi-manual policy learning
7 DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation 提出DenseReward以解决机器人操作中的稀疏奖励问题 manipulation model predictive control reinforcement learning
8 StratMamba: Strategic and Reactive Stream Partitioning for Path-Efficient LiDAR-Based Obstacle Avoidance 提出StratMamba以解决复杂环境中的障碍物规避问题 quadruped sim-to-real Unitree
9 Globalized Constrained Stein Variational Inference for Diverse Feasible Robot Motion Planning 提出SteinSQP以解决机器人运动规划中的多样性与可行性问题 motion planning multimodal
10 Model-Based Diffusion Optimal Control for Multi-Robot Motion Planning 提出基于模型的扩散最优控制以解决多机器人运动规划问题 motion planning
11 Deployable Human Preference Alignment in Robotics: Learning Representative Rewards from Diverse Human Preferences 提出PREC框架以解决机器人偏好对齐问题 locomotion representation learning
12 Flatness-Preserving Residual Learning for Real-Time Tight Quadrotor Formation Flight 提出物理信息残差动态学习框架以解决四旋翼编队飞行中的气动干扰问题 model predictive control

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
13 Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel 提出Hi-LeWM以解决长时间目标条件控制中的层次规划问题 world model worldmodel world models
14 ChunkFlow: Towards Continuity-Consistent Chunked Policy Learning 提出ChunkFlow以解决视觉语言动作模型中的边界抖动问题 policy learning VLA ✅
15 Directional Constraints for Efficient Exploration in Safe Reinforcement Learning 提出ATACOM方向约束以提高安全强化学习的效率 reinforcement learning
16 MAMMOTH: A Multi-Modal End-to-End Policy for Off-Road Mobility Robust to Missing Modality 提出MAMMOTH以解决不规则越野环境中的导航问题 diffusion policy traversability

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

#题目一句话要点标签🔗⭐
17 TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors 提出TrustVLA以解决视觉-语言-动作后门攻击问题 vision-language-action VLA OpenVLA
18 Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference 提出Jetson-PI以解决低功耗设备上VLA模型实时控制问题 vision-language-action VLA ✅

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

#题目一句话要点标签🔗⭐
19 Instance-Enriched Semantic Maps for Visual Language Navigation 提出实例丰富的语义地图以解决视觉语言导航中的对象细节不足问题 semantic map open-vocabulary open vocabulary ✅

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

#题目一句话要点标签🔗⭐
20 A Bearing-Strength Method for Motion Estimation of Unknown Energy Emitters 提出基于强度的运动估计方法以解决能量发射器定位问题 motion estimation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页