cs.RO（2026-08-10）

📊 共 26 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱四：生成式动作 (Generative Motion) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1) 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) (17 篇)

#题目一句话要点标签🔗⭐
1 JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling 提出JEPA-WAM以解决机器人控制中的状态转移建模问题 manipulation bi-manual bimanual manipulation
2 Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning 提出能量结构潜在世界模型以解决物理一致性运动规划问题 motion planning world model world models
3 SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation 提出SLIM-0.5B以解决机器人操作中的动作预测问题 manipulation flow matching world model
4 Trajectory Divergence Horizon Decision for Reliable Dual-Arm Surgical Subtask Manipulation 提出轨迹发散视界决策以解决双臂外科子任务操控问题 manipulation dual-arm flow matching
5 Efficient Real-World Online Reinforcement Learning for Robot Manipulation via Centralized Training and Critic Decomposition 提出集中训练与评论员分解以解决机器人操控中的在线强化学习问题 humanoid humanoid robot manipulation ✅
6 WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for Embodied Manipulation 提出WorldSimProbe以解决ACWM模拟器信度评估问题 manipulation world model world models
7 RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance 提出RynnValue以解决机器人学习中的奖励模型瓶颈问题 manipulation cross-embodiment foundation model
8 Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation 提出HyMeS框架以解决机器人操控中的记忆依赖问题 manipulation imitation learning vision-language-action
9 VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction 提出VANE框架以解决闭环操作中的可靠测试时训练问题 manipulation vision-language-action VLA
10 TAMS: Task-Aware Multi-View Adaptive Streaming for Wireless Telerobotic Manipulation 提出TAMS以解决无线遥操作中的带宽限制问题 manipulation teleoperation ✅
11 Nonlinear Model Predictive Control of a Robotic Soft Esophagus 提出基于SINDYC的MPC以解决软食道的控制问题 MPC model predictive control
12 SpeedTuning: Speeding Up Policy Execution with Lightweight Reinforcement Learning 提出SpeedTuning以解决机器人策略执行速度问题 manipulation reinforcement learning imitation learning
13 RoboSeg: Online Part-Level Semantic Reconstruction for Robotic Manipulation via a Single Eye-in-Hand Camera 提出RoboSeg以解决机器人操作中的部件级语义重建问题 manipulation
14 SAFE-CHEM: Uncertainty-Aware Policy Switching for Robust Robotic Chemistry 提出SAFE-CHEM以解决高风险化学实验中的安全问题 manipulation sim-to-real imitation learning
15 Intuitive Directional Sense Presentation to the Torso Using McKibben-Based Surface Haptic Sensation in Immersive Space 提出基于McKibben肌肉的表面触觉感知以解决沉浸空间中的方向感问题 manipulation teleoperation
16 Entanglement-Free Trajectory Planning for Tethered Mobile Robots with a Slack Tether 提出无缠绕轨迹规划算法以解决松弛绳索移动机器人问题 motion planning
17 Graph-Guided Safe Diffuser: Topological Graph Guidance for Safe Diffusion Planning 提出图引导安全扩散器以解决扩散规划中的安全性问题 locomotion

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

#题目一句话要点标签🔗⭐
18 HarnessWAM: Bridging Prediction and Deliberation in World Action Models 提出HarnessWAM以解决WAM中的预测与深思之间的差距问题 world action model world action models
19 Rethink Before You Execute: Adaptive Execution for World Action Models 提出TempoWAM以解决固定执行时间窗口的问题 world action model world action models
20 Latent World Models with Monotone Planning Costs for Image-Goal Navigation 提出基于单调规划成本的潜在世界模型以解决图像目标导航问题 world model world models
21 Predictive safety filter enhanced curriculum learning control for efficient vehicle dynamics controller 提出基于预测安全过滤器的课程学习控制以提升车辆动态控制效率 curriculum learning
22 Task-Oriented Formation Decision via Reinforcement Learning: Herding an Attacking Swarm 提出基于强化学习的任务导向编队决策以解决攻击群体问题 reinforcement learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
23 Particle-Based Conformal Prediction for Contact-Aware Uncertainty Calibration in Stratified Configuration Spaces 提出CaPTURe以解决机器人接触环境中的不确定性校准问题 contact-aware multimodal

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

#题目一句话要点标签🔗⭐
24 ROEVO: Robust Organized Edge Feature-based Visual Odometry Using RGB-D Cameras 提出ROEVO以解决传统边缘特征视觉里程计的不足问题 visual odometry ✅

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

#题目一句话要点标签🔗⭐
25 Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy 提出LLM驱动的验证层以提升机器人自主性安全性 chain-of-thought

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

#题目一句话要点标签🔗⭐
26 Hierarchical Fast--Slow ReAct Agent for Zero-Shot Object-Goal Navigation 提出层次化快慢反应代理以解决零-shot物体目标导航问题 first-person view

⬅️ 返回 cs.RO 首页 · 🏠 返回主页