| 1 |
Sample-Efficient Robot Skill Learning for Construction Tasks: Benchmarking Hierarchical Reinforcement Learning and Vision-Language-Action VLA Model |
对比VLA模型与强化学习，提升建筑机器人操作技能并实现高效样本利用 |
teleoperation reinforcement learning vision-language-action |
|
|
| 2 |
EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models |
提出EVOLVE-VLA以解决视觉-语言-动作模型适应性不足问题 |
manipulation vision-language-action VLA |
|
|
| 3 |
CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation |
CHIP：通过后见之明扰动实现人型机器人自适应柔顺控制 |
humanoid humanoid robot humanoid control |
|
|
| 4 |
CaFe-TeleVision: A Coarse-to-Fine Teleoperation System with Immersive Situated Visualization for Enhanced Ergonomics |
CaFe-TeleVision：基于粗细粒度控制与沉浸式可视化的人形机器人遥操作系统，提升人机工效 |
humanoid manipulation bi-manual |
✅ |
|
| 5 |
Interactive Motion Planning for Human-Robot Collaboration Based on Human-Centric Configuration Space Ergonomic Field |
提出基于人机协作构型空间人体工学场的交互式运动规划方法 |
bi-manual dual-arm motion planning |
|
|
| 6 |
Synthetic Data Pipelines for Adaptive, Mission-Ready Militarized Humanoids |
Omnia提出一种基于合成数据的流程，加速军用人形机器人的训练和部署。 |
humanoid multimodal |
|
|
| 7 |
Context Representation via Action-Free Transformer encoder-decoder for Meta Reinforcement Learning |
提出CRAFT：一种基于无动作Transformer的元强化学习上下文表示方法 |
manipulation reinforcement learning |
|
|
| 8 |
Fine-Tuning of Neural Network Approximate MPC without Retraining via Bayesian Optimization |
提出基于贝叶斯优化的神经近似MPC调参方法，无需重训练网络。 |
MPC |
|
|
| 9 |
Trajectory Tracking for Multi-Manipulator Systems in Constrained Environments |
提出多速率规划控制框架，解决约束环境下多机械臂系统的轨迹跟踪问题 |
manipulation |
|
|
| 10 |
Autonomous Construction-Site Safety Inspection Using Mobile Robots: A Multilayer VLM-LLM Pipeline |
提出基于多层VLM-LLM流水线的移动机器人自主建筑工地安全巡检方案 |
teleoperation SLAM navigation |
|
|
| 11 |
Impact of Robot Facial-Audio Expressions on Human Robot Trust Dynamics and Trust Repair |
研究机器人面部-音频表情对人机信任动态及修复的影响，面向建筑行业人机协作。 |
quadruped |
|
|