cs.RO（2025-10-01）

📊 共 24 篇论文 | 🔗 2 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) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱三：空间感知与语义 (Perception & Semantics) (3)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators VLA-RFT：基于世界模型和验证奖励的视觉-语言-动作强化微调 sim-to-real reinforcement learning imitation learning ✅
2 Conflict-Based Search as a Protocol: A Multi-Agent Motion Planning Protocol for Heterogeneous Agents, Solvers, and Independent Tasks 提出基于冲突搜索协议的多智能体异构运动规划方法 motion planning reinforcement learning
3 Hybrid Training for Vision-Language-Action Models 提出混合训练HyT框架，加速视觉-语言-动作模型推理，兼顾性能与效率。 manipulation vision-language-action large language model
4 HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy HAMLET：将视觉-语言-动作模型转化为历史感知策略，提升机器人操作性能 manipulation contrastive learning vision-language-action
5 Shared Object Manipulation with a Team of Collaborative Quadrupeds 提出基于腿式机器人团队的共享物体操作方法，解决复杂环境下的物体搬运问题 quadruped manipulation loco-manipulation
6 AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation AFFORD2ACT：提出基于可供性的自动关键点选择方法，用于通用且轻量级的机器人操作 manipulation policy learning affordance
7 From Human Hands to Robot Arms: Manipulation Skills Transfer via Trajectory Alignment Traj2Action：通过轨迹对齐实现人手操作技能向机器人手臂的迁移 manipulation policy learning human-to-robot
8 Safe Motion Planning and Control Using Predictive and Adaptive Barrier Methods for Autonomous Surface Vessels 提出基于预测和自适应控制屏障函数的自主水面艇安全运动规划方法 MPC model predictive control motion planning
9 RTFF: Random-to-Target Fabric Flattening Policy using Dual-Arm Manipulator 提出RTFF策略，利用双臂机器人实现任意褶皱织物到目标平整状态的对齐 manipulation dual-arm imitation learning ✅
10 Differentiable Skill Optimisation for Powder Manipulation in Laboratory Automation 提出基于可微技能优化的粉末操作方法，用于实验室自动化。 manipulation reinforcement learning
11 Prometheus: Universal, Open-Source Mocap-Based Teleoperation System with Force Feedback for Dataset Collection in Robot Learning Prometheus：基于动捕和力反馈的通用开源遥操作系统，用于机器人学习数据集采集 teleoperation imitation learning
12 GRITS: A Spillage-Aware Guided Diffusion Policy for Robot Food Scooping Tasks GRITS：一种用于机器人食物舀取任务的防溢出引导扩散策略 manipulation diffusion policy
13 CroSTAta: Cross-State Transition Attention Transformer for Robotic Manipulation 提出Cross-State Transition Attention Transformer以解决机器人操作中的执行变异问题 manipulation
14 How Well do Diffusion Policies Learn Kinematic Constraint Manifolds? 研究扩散策略学习运动学约束流形的能力，揭示数据集质量和大小的影响。 bi-manual imitation learning

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

#题目一句话要点标签🔗⭐
15 Integrating Offline Pre-Training with Online Fine-Tuning: A Reinforcement Learning Approach for Robot Social Navigation 提出基于RTG预测的离线-在线强化学习算法，用于提升机器人社交导航能力 reinforcement learning offline reinforcement learning
16 Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition 提出通用策略组合（GPC），无需额外训练即可提升扩散或Flow模型机器人策略性能。 flow matching vision-language-action VLA
17 Online Hierarchical Policy Learning using Physics Priors for Robot Navigation in Unknown Environments 提出基于物理先验的在线分层策略学习方法，用于未知环境下的机器人导航。 policy learning imitation learning
18 VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation 提出VENTURA以解决机器人导航任务中的适应性问题 behavior cloning foundation model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
19 Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation NeuRO：面向视觉导航，通过鲁棒优化应对不确定性，提升泛化性 embodied AI
20 INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models INSIGHT：提出一种基于序列内省的VLA模型帮助触发生成框架 vision-language-action VLA
21 MultiPhysio-HRC: Multimodal Physiological Signals Dataset for industrial Human-Robot Collaboration MultiPhysio-HRC：用于工业人机协作的多模态生理信号数据集 multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
22 VL-KnG: Visual Scene Understanding for Navigation Goal Identification using Spatiotemporal Knowledge Graphs VL-KnG：利用时空知识图谱进行视觉场景理解，实现导航目标识别 scene understanding spatiotemporal
23 Kilometer-Scale GNSS-Denied UAV Navigation via Heightmap Gradients: A Winning System from the SPRIN-D Challenge 提出基于高度图梯度的GNSS拒止无人机导航系统，赢得SPRIN-D挑战赛。 height map
24 Semantic Visual Simultaneous Localization and Mapping: A Survey on State of the Art, Challenges, and Future Directions 综述语义视觉SLAM技术，分析现状、挑战与未来方向 visual SLAM large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页