← Search

Chiaki Hirayama

2 accepted papers

2023

Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models

ICRA 2023poster

The deployment of Reinforcement Learning to robotics applications faces the difficulty of reward engineering. Therefore, approaches have focused on creating reward functions by Learning from Observations (LfO) which is the task of learning policies from expert trajectories that only contain state se…

Cited by 7SourceScholar
2023

Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidance

IROS 2023poster

There are two major challenges for scaling up robot navigation around dynamic obstacles: the complex interaction dynamics of the obstacles can be hard to model analytically, and the complexity of planning and control grows exponentially in the number of obstacles. Data-driven and learning-based meth…

Cited by 16SourceScholar