Author: alphonsus

Introduction A typical robot navigation problem involves specifying a goal position, planning an obstacle-free trajectory from the robot’s current position … Continue ReadingMap-Independent Online Generation of Alternate Paths for Fast Local Planning

A linear system can be expressed in a linear differential equation as     Where is the state vector. It … Continue ReadingLinear Quadratic Regulator (LQR)

Why you need Bayesian Optimization Imagine yourself in this situation: You are supposed to optimize an objective function but you … Continue ReadingBayesian Optimization

Why is RL important? The underlying goal of RL is to develop a learning system that can learn on its … Continue ReadingRL Notes

Policy search methods enable a robot to perform a wide range of tasks. But in practice, applying policy search methods … Continue Reading[Paper Review] End-To-End Training of Deep Visuomotor Policies