🔬 大学#191 Beijing, 中国
清华大学交叉信息研究院视觉与机器人实验室
Vision and Robotics Lab - Institute for Interdisciplinary Information Sciences
The Vision and Robotics Lab at Tsinghua University's Institute for Interdisciplinary Information Sciences focuses on building universal embodied intelligent agents. Research integrates computer vision and reinforcement learning for robotic perception and autonomous decision-making.
computer visionreinforcement learningembodied AIperceptionlearning
代表性成果
Research in embodied AI, computer vision, and reinforcement learning for robotics
标志性项目
Universal embodied intelligent agents research
近期研究
全部论文 →按本机构专长领域匹配(关键词重叠 + 直接署名)
LEARNING
开放获取
基于视觉的湍急海面敏捷着陆
Dimosthenis Angelis, Leonard Bauersfeld, Davide Scaramuzza 等 4 位作者
2026
OTHER
开放获取
Droneulator:基于RotorPy和Godot 4的便携式农业无人机工作流仿真器
Jacob Swindell, Michael Lowen, Marija Popovic 等 4 位作者
2026
PERCEPTION
开放获取
IntentionNav:从隐式人类指令进行意图驱动对象导航的基准
Lin Qian, Shijie Li, Sihao Lin 等 7 位作者
2026
MANIPULATION
开放获取
Agentic-VLA: 面向视觉-语言-动作模型的高效在线自适应框架
Ruofan Jin, Zaixi Zhang
2026
OTHER
开放获取
NeuroNL2LTL:一种用于线性时序逻辑自然语言翻译的神经符号框架
Paapa Kwesi Quansah, Ernest Bonnah
2026