Papers
2
Total Citations
4
H-Index
2
About
Ziyang Tao is advancing the frontier of intelligent robot navigation by tackling one of the field’s most persistent challenges: the local minimum problem. His research centers on deep reinforcement learning (DRL) for autonomous systems, with a specific focus on developing adaptive, semi-Markov decision models that break free from the constraints of fixed-interval command execution. In his highly cited 2021 work, Tao introduced the Adaptive Execution Duration (AED) framework, which allows a robot to dynamically determine how long to follow a given command—a significant departure from traditional uniform execution models. This innovation directly addresses the inefficiencies and dead-ends that plague conventional navigation algorithms in unknown environments. Building on this, his 2023 paper proposed the Adaptive Forward Simulation Time (AFST) method, further refining how robots plan and execute movements to escape local minima. Though early in his career, Tao’s contributions are already recognized for their practical impact, offering a more robust and flexible blueprint for autonomous navigation. His work is essential reading for researchers seeking to move beyond static DRL policies toward truly adaptive, real-world robotic intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2