cs.RO（2026-07-29）

📊 共 17 篇论文

🎯 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) (2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation 提出CheckVLA以解决长时间移动操控中的执行验证问题 manipulation mobile manipulation world model
2 RLMM-Flow: A Flow-based Mobile Manipulation Framework with Latent-Space Reinforcement Learning 提出RLMM-Flow以解决移动操控中的多模态动作生成问题 manipulation mobile manipulation motion planning
3 Explicit Kinematic Guidance from Analytic Concepts for Vision-Language-Action Models 提出显式运动学引导以解决视觉-语言-动作模型的空间感知问题 manipulation reinforcement learning vision-language-action
4 ContactFlow: A video action conditioning that transfers across embodiments 提出Contact Flow以解决视频动作条件化的跨实体转移问题 manipulation world model world models
5 Reinforcement Learning on Cost-Constrained Quadrupedal Hardware 提出生物启发方法以解决低成本四足机器人控制中的延迟问题 quadruped locomotion sim-to-real
6 DLAM: Distributional Latent Actions with Temporal Constraints 提出DLAM以解决机器人动作标注数据稀缺问题 manipulation policy learning flow matching
7 Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots 提出Speech2Grasp以解决人形机器人语音抓取检测问题 humanoid humanoid robot
8 SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perception 提出SymmGrid以加速机器人学习过程 humanoid manipulation policy learning
9 Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA 提出运动学监督专家路由以解决MoE增强VLA中的专家路由问题 manipulation VLA
10 Risk-Aware Motion Planning with Learned Trajectory Primitives and Probabilistic Safety Assessment 提出基于RBFN的运动规划框架以提高城市驾驶安全性 MPC motion planning
11 Self-Adaptive Learning and Model Predictive Control for Tracking Unknown Dynamics with No Regret 提出自适应在线学习与模型预测控制以追踪未知动态 model predictive control
12 Practice Makes Policies: Bootstrapping and Consolidating Robotic Capabilities from Zero Human Demonstrations 提出HERO以解决机器人自我提升能力的挑战 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
13 RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models 提出RL²以解决VLA模型在复杂任务中的性能下降问题 reinforcement learning offline RL imitation learning
14 ActSWM: Action-Sensitive World Models for Long-Horizon Planning in Open-World Games 提出ActSWM以解决长时间规划中的上下文崩溃问题 world model world models latent dynamics

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

#题目一句话要点标签🔗⭐
15 From Uncertainty to Determinism: Coarse-to-Fine Visual Floorplan Localization without Ray Matching 提出粗到细的视觉平面图定位方法以解决多模态姿态分布问题 egocentric multimodal

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

#题目一句话要点标签🔗⭐
16 Controlled Experiments on Lane Changing by Transitional Autonomous Vehicle: Dataset and Behavioral Insights 提出NC-tALC数据集以研究过渡自动驾驶车辆的变道行为 TAMP

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

#题目一句话要点标签🔗⭐
17 Sensor-Placement-Agnostic Sonomyography: Toward Continuous High-Dimensional Control by Users with Tetraplegia 提出传感器位置无关的声肌图控制系统以解决四肢瘫痪用户的高维控制问题 optical flow

⬅️ 返回 cs.RO 首页 · 🏠 返回主页