Jaemann Park

Target Localization Using Ensemble Support Vector Regression in Wireless Sensor Networks

This paper considers a target localization problem whose goal is to estimate the location of an unknown object. It is one of the key issues in applications of wireless sensor networks (WSNs). With recent advances in fabrication technology, deployment of a large WSNs has become economically feasible. On the other hand, this has caused the curse of dimensionality in applying learning algorithms such as support vector regression (SVR). To handle this, we use an ensemble implementation of SVRs for target localization and validate it experimentally. This paper draws a comparison between the conventional SVR method and the proposed method in terms of the accuracy and robustness. Experimental results show that the prediction performance of the proposed method is more accurate and robust to the measurement noise than conventional SVR predictor.

Path tracking for a hydraulic excavator utilizing proportional-derivative and linear quadratic control

This paper presents a three-dimensional path tracking strategy for a hydraulic excavator. It mainly aims to design the controller for allowing the excavator to follow typical working motions of a skillful operator such as leveling and truck loading. The performance of the designed controller is verified through real-time experiments using a 21-ton class excavator in which displacement sensors, electro-proportional pressure reducing valves, and communication devices are incorporated. Basically, proportional-derivative (PD) controller with dead zone compensation is used to control the cylinder displacements and swing angle. In order to enhance the performance, a linear quadratic outer-loop is introduced for boom, arm, and bucket joints, which compensates reference inputs of the nonlinear PD controller. Experiments of individual joints show that the designed outer-loop can provide faster rise time than the nonlinear PD controller itself. Furthermore, experimental results demonstrate the feasibility of the proposed algorithm for achieving autonomous compliant motions of both leveling and truck loading.

Online Learning Control of Hydraulic Excavators Based on Echo-State Networks

In some of recent advances in automation of construction equipment, much research has been conducted on the control of hydraulic excavators in both industry and academia for the benefit of safety and efficiency. However, most relevant works have employed model-based control approaches that require a mathematical representation of the target plant. For hydraulic excavators, obtaining a useful dynamic model for control can be challenging due to the nonlinearity of the hydraulic servo system. With this in mind, this paper investigates the feasibility of an online learning control framework based on echo-state networks (ESNs) to the position control of hydraulic excavators. While ESNs are a class of recurrent neural networks, the training of ESNs corresponds to solving a linear regression problem, thus making it suitable for online implementation. By exploiting the dynamic properties of ESNs, the deployed control framework uses the input and output signals of the plant to learn an inverse model, which is then used to simultaneously generate control inputs to track the desired trajectory. Experiments conducted on a 21-ton class hydraulic excavator show the promising results in that accurate tracking is achieved even in the absence of a dynamic model.

Application of Echo-State Networks to the Position Control of Shape-Memory Alloys

Abstract Shape-memory alloys (SMA) have the ability to generate strain in response to temperature change. However, the relationship between applied temperature and crystalline phase is hysteretic. Obtaining an explicit representation of this highly nonlinear phenomenon for the purpose of control consumes time and effort. Also, the identification process is subject to uncertainties, and furthermore, the dynamic properties of SMAs may change during its lifetime which reduces the reliability of the identification. With this in mind, we employ an online learning control framework for the position control of an SMA wire. The online learning control framework performs an inverse learning of the plant based solely on the input and output signals, and uses this information to generate control inputs. Thus, an explicit representation of the plant is not required and as a result from online learning, the controller adapts to changes of the plant. The specific method with which the inverse learning is employed, is by the use of echo-state networks (ESN). ESNs are a class of recurrent neural networks and are distinguished by their large number of hidden nodes often referred to as a dynamic reservoir. While the originally proposed method of constructing this dynamic reservoir relies on a stochastic sampling process, recent studies have suggested that using a simple and deterministic reservoir also provides sufficient performance. Here, we also investigate the impact of using such simple and deterministic reservoir structure within the online learning control framework. Experiments of the online learning control framework conducted on an SMA wire are presented.

Two distributed guidance approaches for rendezvous of multiple agents

Consensus refers to the agreement upon some specific variable between the agents of the system. In this paper, we adopt consensus techniques in order to derive distributed guidance laws which make multiple agents rendezvous at a desired target point. Such rendezvous maneuver can be applied to a salvo attack of multiple missiles, or cooperative surveillance of multi-UAVs. We propose two distributed rendezvous methods that use different consensus variables, namely the distance-to-go and time-to-go, in order to derive the guidance laws. We show the effectiveness of the proposed methods through numerical simulations.

Actuator reconfiguration control of a robotic vehicle with four independent wheel driving

This article presents a driving algorithm for a four-wheeled independent driving vehicle based on reconfiguration control when a fault occurs. The objective of reconfiguration control is to maintain the same closed-loop characteristic even after actuator failure. Two simulations are conducted: one is for the state following when desired state is given and the other is to track the desired path using unicycle path tracking control. From the results of simulations, the reconfiguration control minimized the performance loss and guaranteed the same state trajectory with the state of non-fault case.

Distributed control for multi-target surveillance using limit cycle

In this paper, we propose a control law that makes multiple non-holonomic vehicles converge to a limit cycle with the same relative phase angle. All the agents use information on only their neighbors with which they can communicate. An adjacency matrix is used to represent the connectivity among the agents. With the phase portrait of the limit cycle and the heading angles of the vehicles, we derive the control law to make the vehicles move toward the limit cycle, and using information of neighbors we derived control input to make vehicles have the same relative phase angle. The potential field method is used for collision avoidance. The effectiveness of the proposed control law is shown using computer simulations.

Design of a Path Tracking Scheme and Collision Avoidance Controller for Autonomous Vehicles

Abstract This paper presents an obstacle avoidance scheme for autonomous vehicles as an active safety procedure in unknown environments. The obstacle avoidance problem is treated using a nonlinear model predictive framework in which simplified dynamics are used to predict the state of the actual vehicle over the look-ahead horizon. Due to the slight dissimilarity between the simplified model used for trajectory generation and the actual vehicle trajectory, a separate tracking controller is designed to track the generated trajectory. The longitudinal dynamics of the vehicle is controlled using the inverse dynamics of the vehicle power-train model and the lateral controller is designed based on the linear quadratic regulator. In the nonlinear model predictive framework, the threat of local obstacles is augmented into the performance index using a parallax-based method. The simulation results show that the presented model-predictive-control-based trajectory generation and tracking controller, together, give satisfactory performance in terms of obstacle avoidance when applied to the full nonlinear vehicle model.

Formation Flight Control of Unmanned Aerial Vehicles Using Model Predictive Control

This paper studies the feasibility of using the nonlinear model predictive control as a formation flight control algorithm for unmanned aerial vehicles. The optimal control inputs for formation flight are calculated through the cost function which incorporates the relative positions of the individual vehicles to maintain a desired formation and also the inequality constraints on inputs and states using the Karush-Kuhn-Tucker conditions. In the nonlinear model predictive control setting, the optimal control inputs are implemented in a receding horizon manner, which is suitable for dealing with dynamic constraints. Numerical simulations are executed for the validation of the proposed scheme.