cs.RO（2026-06-30）

📊 共 34 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (23 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (23 篇)

#题目一句话要点标签🔗⭐
1 Human-as-Humanoid: Enabling Zero-Shot Humanoid Learning from Ego-Exo Human Videos with Human-Aligned Embodiments 提出Human-as-Humanoid框架以解决高自由度人形机器人学习问题 humanoid manipulation bi-manual ✅
2 Reinforcement Learning-Based Control for an Inline Skating Humanoid Robot 提出基于强化学习的控制方法以解决人形机器人滑行问题 quadruped humanoid humanoid robot
3 RoboTacDex: A Dexterous Visual-Tactile-Action Dataset for Humanoid Manipulation 提出RoboTacDex数据集以提升人形机器人灵巧操作能力 humanoid humanoid robot manipulation
4 Labimus: A Simulation and Benchmark for Humanoid Dexterous Manipulation in Chemical Laboratory 提出Labimus以解决化学实验室人形机器人灵巧操作评估问题 humanoid humanoid robot manipulation
5 Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models 提出Z-1框架以提升视觉-语言-动作模型的强化学习效率 manipulation reinforcement learning behavior cloning
6 FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion 提出FastDSAC以解决强化学习中的策略塑性问题 humanoid humanoid locomotion locomotion
7 UniTacVLA: Unified Tactile Understanding and Prediction in Vision Language Action Models 提出UniTacVLA以解决接触丰富的灵巧操作问题 manipulation dexterous manipulation vision-language-action
8 DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation 提出DVG-WM以解决机器人操控中的视频生成效率问题 manipulation flow matching world model
9 Freeform Preference Learning for Robotic Manipulation 提出自由形式偏好学习以解决机器人操作中的奖励设计问题 manipulation preference learning reward design ✅
10 OopsieVerse: A Safety Benchmark with Damage-Aware Simulation for Robot Manipulation 提出OOPSIEVERSE以解决机器人操作中的安全性问题 manipulation sim-to-real reinforcement learning
11 3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance 提出3D HAMSTER以解决2D引导下的机器人操控问题 manipulation vision-language-action VLA ✅
12 LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music 提出基于大语言模型的多模态人机交互机器人动作合成框架 quadruped large language model multimodal
13 Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors 提出高效的世界动作模型以解决仿真到现实的转移问题 manipulation sim-to-real domain randomization
14 Learning Locomotion on Discrete Terrain via Minimal Proximity Sensing 通过最小接近传感器提升四足机器人在离散地形上的行走能力 quadruped locomotion reinforcement learning
15 HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation 提出HABIT数据集以解决机器人缺乏人类意识的问题 manipulation spatiotemporal
16 ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning 提出ChronoFlow-Policy以解决视觉运动策略学习中的时间统一问题 manipulation policy learning diffusion policy
17 ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies 提出ELASTIC以解决生成控制策略的测试时间计算自适应分配问题 manipulation reinforcement learning diffusion policy
18 CoDex: Learning Compositional Dexterous Functional Manipulation without Demonstrations 提出CoDex以解决无示范的复杂物体操控问题 manipulation reinforcement learning
19 Robustness of Robotic Manipulation: Foundations and Frontiers 提出系统化研究以提升机器人操作的鲁棒性 manipulation policy learning
20 Stage-Transition Dense Reward Modeling for Reinforcement Learning 提出阶段转换密集奖励建模以解决稀疏奖励问题 manipulation reinforcement learning
21 Improving path-tracking performance of an articulated tractor-trailer system using a non-linear kinematic model 提出非线性运动学模型以提升关节式拖车系统的路径跟踪性能 model predictive control
22 TactX: Learning Shared Tactile Representations Across Diverse Sensors 提出TactX以解决传感器间触觉表示转移问题 manipulation
23 Machine Learning-based Feedback Linearization Control of Quadrotor Subject to Unmodeled Dynamics 提出基于机器学习的反馈线性化控制以解决四旋翼未建模动态问题 actuator dynamics

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
24 Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation 提出一种新方法以解决视觉-语言-动作模型的参数冗余问题 vision-language-action VLA OpenVLA
25 MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents 提出MIRTH框架以解决视觉-语言-动作代理中的时间短视问题 vision-language-action VLA multimodal ✅
26 A Modular Vision-Language-Action Robotics Framework for Indoor Environments 提出模块化视觉-语言-动作机器人框架以解决室内环境中的任务执行问题 vision-language-action VLA
27 A Large-Language-Model Supported Personalized Driving Framework for Lane Change in Highway Scenarios 提出基于大语言模型的个性化驾驶框架以解决高速公路变道问题 large language model ✅
28 UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation 提出UniTac以解决触觉理解与生成的多模态融合问题 multimodal
29 MVP-Nav: Multi-layer Value Map Planner Navigator 提出MVP-Nav以解决RGB-only感知下的零-shot目标导航问题 foundation model
30 Communication-Aware Robot Execution for Cloud Inference under Spatially Heterogeneous Connectivity 提出请求-响应窗口以解决机器人云推理中的连接异质性问题 foundation model

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

#题目一句话要点标签🔗⭐
31 Adapting Generalist Robot Policies with Semantic Reinforcement Learning 提出语义强化学习以适应通用机器人策略解决复杂任务 reinforcement learning VLA
32 DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments 提出DynFly以解决UAV视觉语言导航中的轨迹生成问题 flow matching VLN multimodal
33 LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields 提出LeCropFollow以解决农业机器人在非结构化作物田导航问题 reinforcement learning zero-shot transfer ✅
34 Plan Right, Then Plan Tight: Symbolic RL for Efficient Embodied Reasoning 提出基于BDDL的符号强化学习以提升机器人任务规划效率 reinforcement learning reward design

⬅️ 返回 cs.RO 首页 · 🏠 返回主页