Deok Jin Lee

Hybrid Motion Planning Method for Autonomous Robots Using Kinect Based Sensor Fusion and Virtual Plane Approach in Dynamic Environments

A new reactive motion planning method for an autonomous vehicle in dynamic environments is proposed. The new dynamic motion planning method combines a virtual plane based reactive motion planning technique with a sensor fusion based obstacle detection approach, which results in improving robustness and autonomy of vehicle navigation within unpredictable dynamic environments. The key feature of the new reactive motion planning method is based on a local observer in the virtual plane which allows the effective transformation of complex dynamic planning problems into simple stationary in the virtual plane. In addition, a sensor fusion based obstacle detection technique provides the pose estimation of moving obstacles by using a Kinect sensor and a sonar sensor, which helps to improve the accuracy and robustness of the reactive motion planning approach in uncertain dynamic environments. The performance of the proposed method was demonstrated through not only simulation studies but also field experiments using multiple moving obstacles even in hostile environments where conventional method failed.

Trajectory Tracking and Stabilization of a Quadrotor Using Model Predictive Control of Laguerre Functions

This paper presents a solution to stability and trajectory tracking of a quadrotor system using a model predictive controller designed using a type of orthonormal functions called Laguerre functions. A linear model of the quadrotor is derived and used. To check the performance of the controller we compare it with a linear quadratic regulator and a more traditional linear state space MPC. Simulations for trajectory tracking and stability are performed in MATLAB and results provided in this paper.

Intelligent Controller Design for Quad-Rotor Stabilization in Presence of Parameter Variations

The paper presents the mathematical model of a quadrotor unmanned aerial vehicle (UAV) and the design of robust Self-Tuning PID controller based on fuzzy logic, which offers several advantages over certain types of conventional control methods, specifically in dealing with highly nonlinear systems and parameter uncertainty. The proposed controller is applied to the inner and outer loop for heading and position trajectory tracking control to handle the external disturbances caused by the variation in the payload weight during the flight period. The results of the numerical simulation using gazebo physics engine simulator and real-time experiment using AR drone 2.0 test bed demonstrate the effectiveness of this intelligent control strategy which can improve the robustness of the whole system and achieve accurate trajectory tracking control, comparing it with the conventional proportional integral derivative (PID).

Dynamic Modeling and Control Techniques for Multi-Rotor Flying Robots

A multi-rotor is an autonomous flying robot with multiple rotors. Depending on the number of the rotors, multi-rotors are categorized as tri-, quad-, hexa-, and octo-rotor. Given their rapid maneuverability and vertical take-off and landing capabilities, multi-rotors can be used in various applications such as surveillance and reconnaissance in hostile urban areas surrounded by high-rise buildings. In this paper, the unified dynamic model of each tri-, quad-, hexa-, and octo-rotor are presented. Then, based on derived mathematical equations, the operation and control techniques of each multi-rotor are derived and analyzed. For verifying and validating the proposed models, operation and control technique simulations are carried out.

Successive Loop Closure Based Controller Design for an Autonomous Quadrotor Vehicle

In this paper, a new systematic approach for designing a self-tuning controller for an autonomous quadrotor robot is introduced.In order to design the self-tuning controller, first, a linearized dynamic model of a quadrotor about hovering positions is derived, and thenthe successive loop closure approach is applied to design the self-tuning PID controller of the attitude, altitude and velocity for the autonomous flying capability of the flying robot. In addition, nonlinearities of the design model are also imposed in the control loop by takinginto account the saturation of actuators. For the verification of the effectiveness of the proposed controller, various simulation studiesare carried out in terms of the accuracy and robustness.

Nonlinear Attitude Stabilization and Tracking Control Techniques for an Autonomous Hexa-Rotor Vehicle

This paper present nonlinear attitude stabilization and position tracking control techniques for an autonomous hexa-rotor flying vehicle. Due to its stable and robust maneuverability and fault-tolerant capability, hexa-rotor vehicles have received lots of attention and can be used in various applications such as object delivery and reconnaissance in hostile urban areas. In this work, advanced nonlinear control techniques such as sliding mode control and integral backstepping control are presented and their performances are compared in terms of stabilization and position tracking accuracy and robustness to disturbances. For the verification of the proposed control techniques, various simulation studies are demonstrated along with a realistic nonlinear dynamic model.

A Precise Lane Detection Algorithm Based on Top View Image Transformation and Least-Square Approaches

The next promising key issue of the automobile development is a self-driving technique. One of the challenges for intelligent self-driving includes a lane-detecting and lane-keeping capability for advanced driver assistance systems. This paper introduces an efficient and lane detection method designed based on top view image transformation that converts an image from a front view to a top view space. After the top view image transformation, a Hough transformation technique is integrated by using a parabolic model of a curved lane in order to estimate a parametric model of the lane in the top view space. The parameters of the parabolic model are estimated by utilizing a least-square approach. The experimental results show that the newly proposed lane detection method with the top view transformation is very effective in estimating a sharp and curved lane leading to a precise self-driving capability.

Intelligent Control System Design of a Unmanned Quadrotor Robot

This paper presents the position and attitude control of an unmanned aerial vehicle known as a quadrotor. A design methodology is introduced that a fuzzy logic controller in an intelligent way. It offers several advantages over certain types of conventional control methods, specifically in dealing with highly nonlinear systems and modeling uncertainties. The proposed controller was located at a position feedback loop which composed of x,y and z. Plus, it also designed at the angle acceleration loop. Simulation results prove the efficiency of this intelligent control strategy.

Grid Based Path Planning Using CNN & Artificial Potential Field Method

This proposed path planning method combines cellular neural network (CNN) with artificial potential field approach. The fundamental operation based on CNN gray scale image processing and artificial potential is the additional approach for global path-planning. Every point of the environment has a potential value with respect to start and destination position. In the trajectory planning process, a minimum search of potential value of every surrounding neighbor points around a point is done and the neighbor point with the least minimum value is selected as the next location. This procedure is repeated until the goal point is reached. The advantage of using CNN based image processing with artificial potential field function in a vision system is its effectiveness in robot localization while the use of minimum potential value gives a simple yet efficient path planning method. Their feedback criterion is similar to a procedure in filtering the image and it frequently updates the information about obstacles and free path. The parallel processing properties of CNN makes the proposed method robust for real time application.

Memory-based reinforcement learning algorithm for autonomous exploration in unknown environment

In the near future, robots would be seen in almost every area of our life, in different shapes and with different objectives such as entertainment, surveillance, rescue, and navigation. In any shape and with any objective, it is necessary for them to be capable of successful exploration. They should be able to explore efficiently and be able to adapt themselves with changes in their environment. For successful navigation, it is necessary to recognize the difference between similar places of an environment. In order to achieve this goal without increasing the capability of sensors, having a memory is crucial. In this article, an algorithm for autonomous exploration and obstacle avoidance in an unknown environment is proposed. In order to make our self-learner algorithm, a memory-based reinforcement learning method using multilayer neural network is used with the aim of creating an agent having an efficient exploration and obstacle avoidance policy. Furthermore, this agent can automatically adapt itself to the changes of its environment. Finally, in order to test the capability of our algorithm, we have implemented it in a robot similar to a real model, simulated in the robust physics engine simulator of Gazebo.