Hongjian Liu
Papers
2
Total Citations
4
H-Index
2
About
Hongjian Liu is a researcher advancing the frontier of intelligent robot navigation through deep reinforcement learning (DRL). His work directly tackles a critical limitation in autonomous systems: the local minimum problem and the inefficiency of fixed-interval command execution. Liu’s key contributions lie in developing novel semi-Markov models that introduce adaptive timing into DRL-based navigation. In his highly cited 2021 paper, he proposed the Adaptive Execution Duration (AED) framework, which allows a robot to dynamically decide how long to follow a command rather than acting at uniform intervals. He then extended this concept in his 2023 work with the Adaptive Forward Simulation Time (AFST) model, which further refines navigation by simulating future states to avoid dead ends. Though early in his career, Liu’s work is already recognized for its practical impact, offering a more robust and efficient path for robots operating in unknown, cluttered environments. His research is essential reading for anyone working on the intersection of reinforcement learning and real-world robotic autonomy.
Research Focus
Key Achievements
Top Papers
- 1
- 2