cs.RO（2026-06-17）

📊 共 26 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (22) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (22 篇)

#题目一句话要点标签🔗⭐
1 HALOMI: Learning Humanoid Loco-Manipulation with Active Perception from Human Demonstrations 提出HALOMI框架以解决人形机器人运动操控中的感知与执行问题 humanoid humanoid robot manipulation
2 Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement 提出对象中心残差强化学习以解决零-shot模拟到现实的VLA增强问题 manipulation sim-to-real teleoperation
3 Sensor Configuration Matters: A Systematic Evaluation of Multimodal SLAM on Quadruped Robots 系统评估多模态SLAM以提升四足机器人导航性能 quadruped legged locomotion locomotion
4 HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Vision 提出HT-Bench以解决机器人触觉表示学习的基准问题 manipulation dexterous manipulation representation learning
5 Mobile Pedipulation for Object Sliding via Hierarchical Control on a Wheeled Bipedal Robot 提出分层控制框架以实现轮式双足机器人物体滑动 bipedal biped locomotion
6 Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation 提出可逆神经网络适配器以解决机器人操控中的高维动作生成问题 manipulation flow matching vision-language-action
7 SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation 提出SC3-Eval以解决机器人基础模型评估问题 manipulation world model world models
8 A Scalable Embodied Intelligence Platform for Seamless Real-to-Sim-to-Real Transfer of Household Mobile Manipulation Tasks 提出BestMan平台以解决家庭移动操控任务的真实-仿真-真实转移问题 manipulation mobile manipulation sim-to-real
9 Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning 提出零-shot框架以解决长时间灵巧操作问题 manipulation dexterous manipulation affordance
10 Do as I Do: Dexterous Manipulation Data from Everyday Human Videos 提出DO AS I DO以解决机器人灵巧操作数据生成问题 manipulation dexterous manipulation egocentric
11 DREAM-Chunk: Reactive Action Chunking with Latent World Model 提出DREAM-Chunk以解决动作块执行中的不确定性问题 manipulation world model world models
12 Generating Natural and Expressive Robot Gestures through Iterative Reinforcement Learning with Human Feedback using LLMs 通过人类反馈的迭代强化学习生成自然且富有表现力的机器人手势 humanoid humanoid robot reinforcement learning
13 SRL: Combining SLIP Model and Reinforcement Learning for Agile Robotic Jumping 提出SRL框架以解决机器人跳跃在复杂环境中的稳定性问题 quadruped bipedal biped
14 Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation 评估强化学习中的动作空间以优化视觉基础机器人操作 manipulation sim-to-real reinforcement learning
15 TactSpace: Learning a Physics-enriched Shared Latent Space for Tactile Sim-to-Real Transfer 提出TactSpace框架以解决触觉传感器仿真与现实转移问题 manipulation sim-to-real representation learning
16 ReSiReg: Towards Spatially Consistent Semantics in Language-Conditioned Robotic Tasks 提出ReSiReg以解决语言条件下机器人任务的空间一致性问题 manipulation language conditioned
17 ZiMPedance: Impedance-Aware ZMP Modeling and Control for Payload Carrying with Quadruped Robots 提出ZiMPedance以解决四足机器人负载运输中的稳定性问题 quadruped locomotion model predictive control
18 Seeing Through Occlusion: Deterministic Arm Kinematic Correction for Robot Teleoperation 提出臂运动学修正方法以解决自遮挡问题 teleoperation depth estimation
19 Modeling Branches for Active Manipulation using Iterative Parameter Estimation 提出一种迭代参数估计方法以优化植物枝条的主动操控 manipulation
20 Constant Time-Delay Leader Following with Neural Networks and Invariant Extended Kalman Filters for Arbitrary Trajectories 提出一种常时延轨迹跟踪方法以解决车辆编队问题 model predictive control
21 High-Degree-of-Freedom Lightweight Bioinspired Leg for Enhanced Mobility in Small Robots 提出一种新型微型平行腿机制以解决微机器人运动能力不足的问题 locomotion
22 DNN Koopman-Based Deviation Compensation for UGV Path Tracking Control on Coupled Slope and Potholed Road 提出DNN Koopman补偿策略以解决UGV路径跟踪控制问题 model predictive control

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

#题目一句话要点标签🔗⭐
23 ROBOSHACKLES: A Safety Dataset for Human-Injury Prevention in Embodied Foundation Models 提出ROBOSHACKLES以解决人类伤害预防问题 scene understanding foundation model multimodal ✅
24 GCNGrasp-VP: Affordance-Guided View Planning for Efficient Task-Oriented Grasping 提出GCNGrasp-VP以解决任务导向抓取中的视角遮挡问题 scene reconstruction affordance ✅
25 EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation 提出EffiNav以解决高效目标物体导航问题 open-vocabulary open vocabulary

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

#题目一句话要点标签🔗⭐
26 A Mixed-Reality Testbed for Autonomous Vehicles 提出混合现实测试平台以验证自主车辆的算法 multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页