cs.RO（2026-07-07）

📊 共 27 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 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) (19 篇)

#题目一句话要点标签🔗⭐
1 DexTele: A Dual-Arm Dexterous Teleoperation System Based on Motion Retargeting and Adaptive Force Control 提出DexTele以解决双臂灵巧遥操作中的运动重定向与抓取问题 dual-arm MPC model predictive control
2 RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation 提出RynnWorld-Teleop以解决机器人学习数据收集瓶颈问题 bi-manual sim2real teleoperation
3 From Foundation to Application: Improving VLA Models in Practice 提出LingBot-VLA 2.0以解决VLA模型在实际应用中的不足 manipulation mobile manipulation dexterous hand
4 ThorArena: Benchmarking Humanoid Physical Interaction with Human Motion-Force Demonstrations 提出ThorArena以解决人形机器人物理交互评估问题 humanoid humanoid robot humanoid control
5 Calf-Integrated Arms for Bimanual Quadruped Loco-Manipulation 提出小腿集成臂以解决四足机器人双手操控问题 quadruped manipulation loco-manipulation
6 RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation 提出RynnWorld-4D以解决机器人操作中的4D动态预测问题 manipulation bi-manual bimanual manipulation
7 WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation 提出WristMimic以解决全身类人控制中的手腕引导操控问题 humanoid humanoid control whole-body control
8 UniLM-Nav: A Unified Framework for Zero-Shot Last-Mile Navigation 提出UniLM-Nav以解决零-shot最后一公里导航问题 quadruped manipulation mobile manipulation
9 Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation 提出Lift3D-VLA以解决VLA模型在3D几何理解中的不足问题 manipulation MAE vision-language-action
10 Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement 提出ActionCache以解决VLA模型实时推理延迟问题 manipulation flow matching vision-language-action
11 LAMP: Latent Motion Prior-Guided Real-World Learning for Dexterous Hand Manipulation 提出LAMP框架以解决灵巧手操作中的学习效率问题 manipulation dexterous hand dexterous manipulation
12 GraspIT: A Dataset Bridging the Sim-to-Real gap and back for Validated Grasping SE(3) Pose Generation 提出GraspIT以解决机器人抓取数据集缺乏真实验证的问题 manipulation sim-to-real policy learning
13 Learning to Throw Objects Safely in Multi-Obstacle Environments 提出潜场状态表示以解决多障碍环境中的安全投掷问题 sim-to-real reinforcement learning SAC
14 MP-MPPI: A Motion Primitive Guided Sampling-Based Optimizer for Model Predictive Control 提出MP-MPPI以解决采样控制器路径规划能力不足的问题 model predictive control
15 EAGOR: Embodied Reasoning in Omni-direction 提出EAGOR以解决360°方向推理问题 legged robot egocentric
16 Clustering-Embedded Model Predictive Path Integral Control: Avoiding Averaging-Induced Failure and Enabling Efficient Cluster Selection for Dynamic Obstacles 提出CE-MPPI以解决动态障碍物下的平均化失败问题 motion planning
17 Responsible Personalisation: The Double-Edged Sword of Personalisation in Human-Robot Interaction 提出基于生命周期的框架以解决人机交互中的个性化伦理风险问题 manipulation
18 OrchardBench: A Physically-Grounded, GPU-Parallel Apple-Orchard Simulation Benchmark for Agricultural Robotics 提出OrchardBench以解决农业机器人果树采摘仿真问题 domain randomization
19 RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures 提出RoboTALES以解决机器人政策学习中的任务对齐问题 manipulation ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
20 SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models 提出SIEVE以解决VLA模型模仿学习中的数据选择问题 imitation learning vision-language-action VLA
21 Optimal Transport Q-Learning for Flow Policy Steering and Acceleration 提出最优传输Q学习以加速流政策优化 flow matching distillation vision-language-action
22 Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure 提出运动学与动力学区分以解决世界模型长时间预测失败问题 world model world models dreamer
23 Hypothesis-driven Model Expansion under Uncertainty for Open-World Robot Planning 提出开放世界规划框架以解决服务机器人知识扩展问题 world model world models foundation model
24 Delay-Aware Active Triangulation with Uncertainty-Driven Multi-Agent Reinforcement Learning for Counter-UAS 提出延迟感知主动三角测量以解决反无人机定位问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
25 Hilti-Trimble-Oxford Dataset: 360 Visual-Inertial Benchmark with Floor Plan Priors for SLAM and Localization 提出Hilti-Trimble-Oxford数据集以解决建筑工地SLAM与定位问题 visual SLAM
26 FORGE: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoning 提出FORGE以解决机器人工具功能泛化问题 affordance

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

#题目一句话要点标签🔗⭐
27 Diagnosing Semantic Handoff Failures in Agent-Orchestrated Vision-Language-Action Skill Composition 提出一种方法以解决机器人技能组合中的语义交接失败问题 vision-language-action VLA language conditioned

⬅️ 返回 cs.RO 首页 · 🏠 返回主页