Hanging Guo
Papers
1
Total Citations
11
H-Index
1
About
Hanging Guo is a researcher advancing the field of robotics and autonomous navigation through deep imitation learning. Their key research focuses on enabling robots to learn complex behaviors from expert demonstrations, with a particular emphasis on multi-task learning for indoor self-navigation. Guo’s most cited work, "Shared Multi-Task Imitation Learning for Indoor Self-Navigation" (2018, 11 citations), addresses a critical limitation in traditional imitation learning frameworks: the inability of a single model to perform multiple tasks. By developing a shared multi-task learning approach, Guo demonstrated how robots can simultaneously learn lane following, obstacle avoidance, and other navigation skills from a unified model, significantly enhancing their versatility and adaptability in real-world environments. This contribution has implications for the development of more capable and efficient autonomous systems, from service robots to autonomous vehicles. Guo’s work stands out for its practical approach to overcoming the scalability challenges in robot learning, offering a pathway toward more intelligent and flexible machines that can operate in dynamic, unstructured settings.
Research Focus
Key Achievements
Top Papers
- 1Shared Multi-Task Imitation Learning for Indoor Self-Navigation11 citations · 2018