cs.RO（2026-06-15）

📊 共 36 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (30 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (30 篇)

#题目一句话要点标签🔗⭐
1 ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning 提出ROVE框架以解决人类干预在类人操控中的挑战 humanoid manipulation dexterous hand
2 ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion 提出ADAPT框架以解决人形机器人在干扰下的运动稳定性问题 humanoid humanoid locomotion locomotion
3 Geometric Action Model for Robot Policy Learning 提出几何动作模型以解决机器人政策学习中的3D几何问题 manipulation policy learning world model
4 T-Rex: Tactile-Reactive Dexterous Manipulation 提出T-Rex以解决机器人触觉反应不足问题 manipulation dexterous manipulation VQ-VAE
5 VENOM: Versatile Embodied Network for Omni-bodied Motion tracking 提出VENOM以解决多种类人形机器人运动跟踪问题 humanoid humanoid robot motion tracking
6 V2P-Manip: Learning Dexterous Manipulation from Monocular Human Videos 提出V2P-Manip以解决自主机器人灵巧操作问题 manipulation dexterous hand dexterous manipulation
7 TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation 提出TopoRetarget以解决手部交互保留的重定向问题 manipulation dexterous manipulation reinforcement learning
8 R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies 提出R2RDreamer以解决空间泛化的2D操作策略问题 manipulation sim-to-real dreamer
9 Agile Fall Recovery for Quadrotors with Bidirectional Thrust via Reinforcement Learning 提出基于强化学习的四旋翼灵活落地恢复方法 sim-to-real fall recovery reinforcement learning
10 WaveSync: Constrained Wavefront Optimization for Synchronized Co-Speech Gestures in Humanoid Robots 提出WaveSync以解决人形机器人同步共语手势问题 humanoid humanoid robot motion planning ✅
11 APEX: Adaptive Policy Execution for Precise Manipulation 提出APEX框架以解决执行差距问题 manipulation imitation learning vision-language-action
12 Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes 提出分层优势加权方法以解决稀疏结果下的在线强化学习问题 bi-manual behavior cloning VLA
13 HOLO-MPPI: Multi-Scenario Motion Planning via Hierarchical Policy Optimization 提出HOLO-MPPI以解决多场景运动规划问题 motion planning reinforcement learning policy learning
14 Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning 提出视频基础最优传输方法以提高偏好强化学习的反馈效率 locomotion manipulation reinforcement learning
15 Steering Generative Reinforcement Learning into Stable Robotic Controller 提出SteerGenPO以解决高维机器人控制中的不稳定性问题 locomotion Unitree reinforcement learning
16 ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in Manipulation Policies 提出ATOM-Bench以评估机器人操作中的原子技能与组合泛化能力 manipulation dual-arm foundation model
17 RHO: Your Coding Agent is Secretly a Roboticist 提出RHO以解决实时机器人控制中的代码生成问题 teleoperation large language model Code as Policies
18 Reinforcement Learning with Inner-loop Dynamics Estimator for Aerial Manipulation under Uncertainty 提出层次控制框架以解决不确定性下的空中操作问题 manipulation reinforcement learning
19 PolyMerge: Compressing 3D Gaussian Splats with Polytope Coverings for Provably Safe Resource-Constrained Navigation 提出PolyMerge以解决资源受限环境下的安全导航问题 motion planning 3D gaussian splatting 3DGS ✅
20 Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks 提出PRISM以解决长时间任务中的短期记忆问题 manipulation imitation learning vision-language-action ✅
21 HATS: A Human-Agent Teleoperation System for Multi-Arm Data Collection 提出HATS系统以解决多臂操作中的数据收集问题 manipulation teleoperation
22 Training and Evaluating Diffusion Policies with Long Context Lengths 提出长上下文长度的扩散策略以解决模仿学习中的记忆问题 manipulation imitation learning diffusion policy
23 PATCH: Action-Chunk-Conditioned Latent Patch Innovation Monitoring for Robot Manipulation 提出PATCH以解决机器人操作中的干扰监测问题 manipulation ✅
24 Elastic ODYN: Differentiable Optimization for Infeasible Control and Learning in Robotics 提出Elastic ODYN以解决机器人控制中的不可行性问题 quadruped humanoid trajectory optimization
25 Robots that Collaborate: Sequential Asymmetric Imitation for Learning Coupled Robot Policies 提出顺序非对称模仿以解决机器人协作问题 manipulation mobile manipulation bi-manual ✅
26 An Augmented Reality Brain-Robot Interface for Generalist Robot Arm Manipulation 提出增强现实脑-机器人接口以解决通用机器人臂操控问题 manipulation ✅
27 ExoTraj: A General Lower-limb Exoskeleton Assistance Policy for Complex Environments 提出ExoTraj以解决复杂环境下下肢外骨骼的适应性辅助问题 model predictive control trajectory optimization flow matching
28 SemGeoNav:A Safety-Guided Visual Navigation Approach with Semantic Reasoning and Geometric Planning 提出SemGeoNav以解决视觉导航中的安全性与可靠性问题 quadruped Unitree
29 ART-Glove: Articulated Tactile Glove for Contact-Grounded Dexterous Interaction Capture 提出ART-Glove以捕捉接触基础的灵巧交互 manipulation dexterous manipulation
30 SGM-SLAM: Scene Graph Matching for Data-Efficient Distributed SLAM 提出SGM-SLAM以解决数据效率低下的分布式SLAM问题 legged robot

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
31 ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curation 提出ATHENA以解决机器人数据管理中的多任务影响函数计算瓶颈问题 imitation learning vision-language-action VLA
32 Human Universal Grasping 提出HUG模型以实现人类通用抓取能力 flow matching MANO egocentric
33 Pride and Prejudice: Toward an Information-Theoretic Framework for Mutually Communicative Driver Behavior Modeling 提出信息论框架以解决混合自主驾驶中的沟通问题 reinforcement learning inverse reinforcement learning affordance

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

#题目一句话要点标签🔗⭐
34 CrossMaps: Confidence-Aware Open-Vocabulary Semantic Mapping for Rover Navigation 提出CrossMaps以解决探测器导航中的语义映射问题 semantic mapping semantic map open-vocabulary
35 DIFF-IPPO: Diffusion-Based Informative Path Planning with Open-Vocabulary Belief Maps 提出DIFF-IPPO以解决非高斯信念图的路径规划问题 open-vocabulary open vocabulary multimodal

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

#题目一句话要点标签🔗⭐
36 SoK: Security and Privacy of Foundation-Model-Powered Robots 提出F-E-S-G框架以解决基础模型驱动机器人安全与隐私问题 foundation model multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页