arXiv subjects

Hyungjin Yoon

Publications and source records attributed to Hyungjin Yoon.

3 recordsLinked to original sources

arXiv2021

Control Barrier Function Augmentation in Sampling-based Control Algorithm for Sample Efficiency

For a nonlinear stochastic path planning problem, sampling-based algorithms generate thousands of random sample trajectories to find the optimal path while guaranteeing safety by Lagrangian penalty methods. However, the sampling-based algorithm can perform poorly in obstacle-rich environments because most samples might violate safety constraints, invalidating the corresponding samples. To improve the sample efficiency of sampling-based algorithms in cluttered environments, we propose an algorithm based on model predictive path integral control and control barrier functions. The proposed algorithm needs fewer samples and time-steps and has a better performance in cluttered environments compared to the original model predictive path integral control algorithm.

eess.SY↗

arXiv2021

Backup Plan Constrained Model Predictive Control

This article proposes a new safety concept: backup plan safety. The backup plan safety is defined as the ability to complete one of the alternative missions in the case of primary mission abortion. To incorporate this new safety concept in control problems, we formulate a feasibility maximization problem that adopts additional (virtual) input horizons toward the alternative missions on top of the input horizon toward the primary mission. Cost functions for the primary and alternative missions construct multiple objectives, and multi-horizon inputs evaluate them. To address the feasibility maximization problem, we develop a multi-horizon multi-objective model predictive path integral control (3M) algorithm. Model predictive path integral control (MPPI) is a sampling-based scheme that can help the proposed algorithm deal with nonlinear dynamic systems and achieve computational efficiency by parallel computation. Simulations of the aerial vehicle and ground vehicle control problems demonstrate the new concept of backup plan safety and the performance of the proposed algorithm.

eess.SY↗

arXiv2018

Primal-Dual Algorithm for Distributed Reinforcement Learning: Distributed GTD

The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for multi-agent Markov decision processes (MDPs). The temporal difference (TD) learning is a reinforcement learning (RL) algorithm which learns an infinite horizon discounted cost function (or value function) for a given fixed policy without the model knowledge. In the distributed RL case each agent receives local reward through a local processing. Information exchange over sparse communication network allows the agents to learn the global value function corresponding to a global reward, which is a sum of local rewards. In this paper, the problem is converted into a constrained convex optimization problem with a consensus constraint. Then, we propose a primal-dual distributed GTD algorithm and prove that it almost surely converges to a set of stationary points of the optimization problem.

math.OC↗