cs.RO（2026-10-23）

📊 共 28 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (8) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#题目一句话要点标签🔗⭐
1 ViT-H: Generative Video-To-Humanoid Control with Motion Tracking Feedback 提出ViT-H以解决视频到类人控制的可执行性问题 humanoid humanoid control motion tracking
2 MAST-VLA: Skill-Conditioned Adaptation with Trajectory-Affordance Priors for Multi-Skill Robot Manipulation 提出MAST-VLA以解决多技能机器人操作中的适应性问题 manipulation affordance vision-language-action
3 CoCarry: Contact-Support-Structured Retargeting for Dual-Humanoid Cooperative Carrying 提出CoCarry以解决双人合作搬运中的协调问题 humanoid humanoid control whole-body control
4 From Tabletop to Walking Bot: Deploying a VLA Model on a Legged Manipulator Robot 提出VLA模型以解决四足机器人操控问题 quadruped manipulation loco-manipulation
5 Coupling Execution Horizon and Sampling Depth in Flow-Matching VLA Policies 提出流匹配VLA策略以解决机器人操作中的实时响应与执行稳定性问题 manipulation flow matching vision-language-action ✅
6 DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection 提出DexPort以解决灵巧手数据收集难题 manipulation dexterous hand dexterous manipulation
7 If at First You Don't Succeed, Backtrack: Lightweight Recovery for Frozen VLAs 提出Backtrack以解决冻结VLA模型的失败恢复问题 manipulation flow matching vision-language-action
8 Delay Randomization Widens the Delay Margin of Learned Humanoid Motion Trackers 随机化延迟方法提升学习型人形机器人运动跟踪器的延迟裕度 humanoid humanoid control motion tracking
9 DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning 提出DiscoDemo以解决机器人模仿学习中的演示多样性问题 manipulation reinforcement learning imitation learning ✅
10 HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training 提出HoloBoxing以实现高效的人形拳击训练 humanoid whole-body control reinforcement learning
11 Graphs of Trajectory Bundles for Nonlinear Motion Planning 提出轨迹束图方法以解决非线性运动规划问题 trajectory optimization motion planning
12 DynaSlots: Slot-Centric 3D Dynamics Pretraining for Robot Manipulation 提出DynaSlots以解决机器人操作中的动态建模问题 manipulation visual pre-training ✅
13 RoboCode: Learning Reusable Action Primitives for Robot Manipulation 提出RoboCode以解决机器人操作中的动作重用问题 manipulation diffusion policy
14 Predictive Long-Horizon Progress Modeling with Action-Aware Quantification 提出行动感知量化以解决长时间任务进度反馈问题 manipulation reinforcement learning
15 LogLook: Execution-Grounded Memory for Frontier-Model Robot Planners 提出LogLook以解决机器人规划中的记忆问题 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
16 TravSUITE: Traversability via Self-Supervised, Uncertainty-Aware IRL and Terrain Estimation 提出TravSUITE以解决越野环境中的可通行性分析问题 reinforcement learning inverse reinforcement learning traversability
17 Adaptive World-Models for Anomaly Recognition (AWARE): A Framework for Robot Dynamics Prediction and Introspection 提出AWARE框架以解决关键基础设施异常检测问题 world model world models
18 HGWM: Hierarchical Graph-Guided World Model for Zero-Shot Object Navigation via Graph Matching 提出HGWM以解决零-shot物体导航问题 world model world models
19 From Freehand Demonstrations to Autonomous Robotic Ultrasound: An Anatomy-Anchored Learning Framework 提出解剖锚定模仿学习框架以实现自主机器人超声成像 imitation learning egocentric egocentric vision
20 Geometry-Aware Reinforcement Learning for Close-Fitting Wearable Insertion 提出几何感知强化学习以解决紧身可穿戴物体插入问题 reinforcement learning spatial relationship
21 $R^2E:$ A Role-driven Reward Evolutionary Framework for Automated Reward Function Design 提出R^2E框架以解决强化学习中奖励函数设计问题 reinforcement learning reward design large language model
22 RynnUnify: Towards Unified Embodied Brain 提出RynnUnify以实现统一的具身智能模型 reinforcement learning multimodal
23 Optimization, Optimal Control, and Reinforcement Learning for Robotics 介绍优化、最优控制与强化学习在机器人领域的应用 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
24 When Human Corrections Travel: Safety in Federated VLA Adaptation 提出多模态纠正共享机制以提升联邦VLA适应性安全性 vision-language-action VLA multimodal
25 Do VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems 提出稀疏自编码器以预测物理AI系统的成功与失败 vision-language-action VLA OpenVLA
26 TTT in VLA Models: Exploring Training with Human Demonstrations 结合人类示范的测试时训练方法提升机器人任务执行能力 VLA
27 Natural-Language to Nav2: Operational Policies for Costmap-Based Navigation 提出自然语言政策接口以解决动态导航问题 large language model

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

#题目一句话要点标签🔗⭐
28 OWLS: Open-world Language-conditioned Speed Fields for Zero-Shot Rover Navigation 提出OWLS以解决零样本探测器导航问题 open-vocabulary open vocabulary traversability

⬅️ 返回 cs.RO 首页 · 🏠 返回主页