cs.RO（2026-09-03）

📊 共 22 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation 提出FWBC-VLA以解决接触丰富的运动操控问题 legged robot whole-body control WBC
2 MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex Terrains 提出多模态扩散策略以解决自主四足机器人复杂地形导航问题 quadruped locomotion parkour
3 WISE: World-model-guided Imagination Scheduling for Efficient Post-training of Vision-Language-Action Models 提出WISE以解决视觉-语言-动作模型后训练效率问题 manipulation reinforcement learning world model
4 Establishing a Dynamic Multimodal HRI Dataset for Engagement Analysis with a Humanoid Robot 构建动态多模态HRI数据集以分析人机交互中的用户参与度 humanoid humanoid robot multimodal
5 GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation 提出GIFT以解决机器人操作中的动作充分性差距问题 manipulation world model world models ✅
6 Scaling Bimanual Household Manipulation from 1,500 hours of Demonstrations to On-Policy Corrections 提出XR-2模型以解决双手家庭操作中的数据稀缺问题 manipulation bi-manual bimanual manipulation
7 BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI 提出数据驱动的形态控制共设计框架以优化类人机器人运动 humanoid humanoid robot whole-body control
8 MINERVA: How Small Can a Manipulation Policy Be and Still Solve LIBERO? 提出MINERVA以解决LIBERO基准的模型容量问题 manipulation flow matching distillation
9 Long-Horizon Consistent and Interaction-Aware World Models for Multi-Style End-to-End Driving 提出StyleDrive以解决长时间一致性和多样化驾驶风格问题 sim-to-real reinforcement learning world model
10 QLAUN: A Research-Oriented, Robust, Agile, Modular, and Affordable Torque-Controlled Quadruped Robot 提出QLAUN以解决四足机器人研究的成本与灵活性问题 quadruped legged robot locomotion
11 R2S-Eval: Robot Evaluation with Real-to-Sim Calibration via Vision-Language Models 提出R2S-Eval以解决机器人评估中的效率与稳定性问题 manipulation vision-language-action VLA
12 ARTiS: An Adaptive Robotic Gripper for Enhanced Tool Manipulation in Disassembly Applications 提出ARTiS以解决机器人工具操作中的抓取挑战 manipulation ✅
13 Predictive Zonotope Reduction: Precise Runtime Monitoring under Uncertainty 提出预测性锥体约简方法以解决不确定性监控问题 model predictive control distillation
14 FailBench: How Reliable are VLMs at Judging Robot Task Success? 提出FailBench基准以评估视觉语言模型在机器人任务成功判断中的可靠性 manipulation

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

#题目一句话要点标签🔗⭐
15 Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models 提出统一机器人学习框架以解决系统碎片化问题 policy learning world model world models
16 Revisiting Topological Graphs for Macro Action based Closed-loop Reinforcement Learning of Vision Language Navigation in Continuous Environment 提出基于拓扑图的宏观动作闭环强化学习以解决视觉语言导航问题 reinforcement learning PPO imitation learning
17 A hybrid pipeline for dynamic ontology-based semantic mapping 提出一种混合管道以解决动态本体语义映射问题 world model world models semantic mapping
18 Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning 提出一种基于JEPA的世界模型以解决机器人目标规划问题 world model worldmodel world models

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
19 A comparative study on the accuracy & repeatability of mobile robotic platforms for the delivery of precision NDE measurement 提出激光跟踪评估工作流程以提升移动机器人精度 visual odometry
20 RoughSense: Lightweight Terrain-Induced Rover Vibration Prediction Using Point Clouds and IMU Feedback 提出轻量级方法以实现实时地形引起的探测器振动预测 traversability

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

#题目一句话要点标签🔗⭐
21 Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps 提出AGC-VLN以解决空地协作视觉语言导航问题 first-person view VLA VLN ✅

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

#题目一句话要点标签🔗⭐
22 Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp Synthesis 提出AdaRoboVLG以解决机器人抓取中的任务适应性问题 foundation model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页