A Lidar-Based Decision-Making Method for Road Boundary Detection Using Multiple Kalman Filters
Yeonsik Kang, Chi-Won Roh, SeungBeum Suh, Bongsob Song
IF 7.2
IEEE Transactions on Industrial Electronics
In this paper, a novel decision-making method is proposed for autonomous mobile robot navigation in an urban area where global positioning system (GPS) measurements are unreliable. The proposed method uses lidar measurements of the road's surface to detect road boundaries. An interacting multiple model method is proposed to determine the existence of a curb based on a probability threshold and to accurately estimate the roadside curb position. The decision outcome is used to determine the source of references suitable for reliable and seamless navigation. The performance of the decision-making algorithm is verified through extensive experiments with a mobile robot autonomously navigating through campus roads with several intersections and unreliable GPS measurements. Our experimental results demonstrate the reliability and good tracking performance of the proposed algorithm for autonomous urban navigation.
Humanoid Path Planning From HRI Perspective: A Scalable Approach via Waypoints With a Time Index
Soohyun Ryu, Yeonsik Kang, Sin-Jung Kim, Keonyong Lee, Bum-Jae You, Nakju Lett Doh
IF 10.5
IEEE Transactions on Cybernetics
This paper proposes a path planner for a humanoid robot to enhance its performance in terms of the human-robot interaction perspective. From the human point of view, the proposed method uses the time index that can generate a path that humans feel to be natural. In terms of the robot, the proposed method yields a waypoint-based path, the simplicity of which enables accurate tracking even for humanoid robots with complex dynamics. From an environmental perspective through which interactions occur, the proposed method can be easily expanded to a wide area. Overall, the proposed method can be described as a scalable path planner via waypoints with a time index for humanoid robots. Experiments have been conducted in test beds where the robot encounters unexpected exceptional situations. Throughout these trials, the robot successfully reached the goal location while iteratively replanning the path.
Dependable Humanoid Navigation System Based on Bipedal Locomotion
Yeonsik Kang, Hyunsoo Kim, Soohyun Ryu, Nakju Lett Doh, Yonghwan Oh, Bum-Jae You
IF 7.2
IEEE Transactions on Industrial Electronics
In this paper, a dependable humanoid navigation system is proposed by considering many difficulties in humanoid navigation based on bipedal locomotion in an uncertain environment. In particular, we propose a layered architecture to resolve complicated problems through a hierarchical manner. Within the proposed software architecture, a walking path planner, a walking footstep planner, and a walking pattern generator are integrated in a hierarchy to create a reliable motion that overcomes foot slippage and localization sensor noise. Each layer is designed to overcome difficulties originating from bipedal locomotion such as unstable dynamics, inclusion of a sinusoidal noise component in the localization sensor measurement, and disturbance regarding discrete footstepping. The designed navigation system is implemented on a human-sized experimental humanoid platform and is tested for the evaluation of its reliability and robustness in various tasks.
Linear Tracking for a Fixed-Wing UAV Using Nonlinear Model Predictive Control
Yeonsik Kang, J. Karl Hedrick
IF 3.9
IEEE Transactions on Control Systems Technology
In this paper, a nonlinear model predictive control (NMPC) is used to design a high-level controller for a fixed-wing unmanned aerial vehicle (UAV). Given the kinematic model of the UAV dynamics, which is used as a model of the UAV with low-level autopilot avionics, the control objective of the NMPC is determined to track a desired line. After the error dynamics are derived, the problem of tracking a desired line is transformed into a problem of regulating the error from the desired line. A stability analysis follows to provide the conditions that can assure the closed-loop stability of the designed high-level NMPC. Furthermore, the control objective is extended to track adjoined multiple line segments. The simulation results demonstrate that the UAV controlled by the NMPC converged rapidly with a small overshoot. The performance of the NMPC was also verified through realistic ¿hardware in the loop simulation.¿
A Lidar-Based Decision-Making Method for Road Boundary Detection Using Multiple Kalman Filters
Yeonsik Kang, Chi-Won Roh, SeungBeum Suh, Bongsob Song
IF 7.2
IEEE Transactions on Industrial Electronics
In this paper, a novel decision-making method is proposed for autonomous mobile robot navigation in an urban area where global positioning system (GPS) measurements are unreliable. The proposed method uses lidar measurements of the road's surface to detect road boundaries. An interacting multiple model method is proposed to determine the existence of a curb based on a probability threshold and to accurately estimate the roadside curb position. The decision outcome is used to determine the source of references suitable for reliable and seamless navigation. The performance of the decision-making algorithm is verified through extensive experiments with a mobile robot autonomously navigating through campus roads with several intersections and unreliable GPS measurements. Our experimental results demonstrate the reliability and good tracking performance of the proposed algorithm for autonomous urban navigation.
Humanoid Path Planning From HRI Perspective: A Scalable Approach via Waypoints With a Time Index
Soohyun Ryu, Yeonsik Kang, Sin-Jung Kim, Keonyong Lee, Bum-Jae You, Nakju Lett Doh
IF 10.5
IEEE Transactions on Cybernetics
This paper proposes a path planner for a humanoid robot to enhance its performance in terms of the human-robot interaction perspective. From the human point of view, the proposed method uses the time index that can generate a path that humans feel to be natural. In terms of the robot, the proposed method yields a waypoint-based path, the simplicity of which enables accurate tracking even for humanoid robots with complex dynamics. From an environmental perspective through which interactions occur, the proposed method can be easily expanded to a wide area. Overall, the proposed method can be described as a scalable path planner via waypoints with a time index for humanoid robots. Experiments have been conducted in test beds where the robot encounters unexpected exceptional situations. Throughout these trials, the robot successfully reached the goal location while iteratively replanning the path.
Dependable Humanoid Navigation System Based on Bipedal Locomotion
Yeonsik Kang, Hyunsoo Kim, Soohyun Ryu, Nakju Lett Doh, Yonghwan Oh, Bum-Jae You
IF 7.2
IEEE Transactions on Industrial Electronics
In this paper, a dependable humanoid navigation system is proposed by considering many difficulties in humanoid navigation based on bipedal locomotion in an uncertain environment. In particular, we propose a layered architecture to resolve complicated problems through a hierarchical manner. Within the proposed software architecture, a walking path planner, a walking footstep planner, and a walking pattern generator are integrated in a hierarchy to create a reliable motion that overcomes foot slippage and localization sensor noise. Each layer is designed to overcome difficulties originating from bipedal locomotion such as unstable dynamics, inclusion of a sinusoidal noise component in the localization sensor measurement, and disturbance regarding discrete footstepping. The designed navigation system is implemented on a human-sized experimental humanoid platform and is tested for the evaluation of its reliability and robustness in various tasks.
Linear Tracking for a Fixed-Wing UAV Using Nonlinear Model Predictive Control
Yeonsik Kang, J. Karl Hedrick
IF 3.9
IEEE Transactions on Control Systems Technology
In this paper, a nonlinear model predictive control (NMPC) is used to design a high-level controller for a fixed-wing unmanned aerial vehicle (UAV). Given the kinematic model of the UAV dynamics, which is used as a model of the UAV with low-level autopilot avionics, the control objective of the NMPC is determined to track a desired line. After the error dynamics are derived, the problem of tracking a desired line is transformed into a problem of regulating the error from the desired line. A stability analysis follows to provide the conditions that can assure the closed-loop stability of the designed high-level NMPC. Furthermore, the control objective is extended to track adjoined multiple line segments. The simulation results demonstrate that the UAV controlled by the NMPC converged rapidly with a small overshoot. The performance of the NMPC was also verified through realistic ¿hardware in the loop simulation.¿
Unified Semantic-Dynamic Occupancy Grid Map for Autonomous Vehicles Using LiDAR Semantic Data and Dempster-Shafer Theory
Kyungjae Ahn, Jongjin Won, Sejong Heo, Yeonsik Kang
IF 3.6
IEEE Access
Accurate and comprehensive recognition of dynamic and static objects is essential for the safety and efficiency of autonomous vehicles. However, deep learning-based semantic segmentation, which extracts semantic information from LiDAR point clouds, often struggles to maintain high accuracy due to the complexity of distinguishing target objects from nearby entities the point cloud data. This study presents a method of updating Semantic Dynamic Occupancy Grid Map (SDOGM), which simultaneously incorporates an object’s semantic and dynamic information into a unified grid map. For the robust estimation of the object’s semantic information occupying the grid cell, a combination rule is proposed based on Dempster-Shafer evidence theory. Additionally, the dynamic states of objects occupying the grid cell are updated through a particle filter-based method. This approach effectively distinguishes closely positioned objects by clustering grids according to class-specific characteristics.We evaluated the performance of speed estimation and object recognition using the urban nuScenes dataset. The results demonstrate that the proposed method recognizes a variety of surrounding objects, estimate their velocities, in complex urban environments.
Inverse Reinforcement Learning with Dynamic Occupancy Grid Map for Urban Local Path Planning: A CNN Model Approach
Geontak Lee, Soongyu Kim, Dayeon Seo, Yeonsik Kang
In urban environments characterized by various dynamic variables such as moving vehicles, pedestrians, and bicycles, path planning for collision avoidance is essential for autonomous driving. Enhancing the stability of the route can be achieved by incorporating not only information about recognized surrounding objects but also dynamic information during the path planning process. Therefore, this study proposes a convolutional neural network-based local path planning technique for autonomous vehicles in urban environments using a dynamic occupancy grid map (DOGM). This approach ensures precision in path generation by considering the occupancy and speed of various objects. During the learning process, we implemented inverse reinforcement learning by combining trajectory information driven by expert intentions with environmental information obtained from DOGM through a combination of convolution layers. This demonstrates the feasibility of designing stable paths with low collision rates in urban areas. Particularly noteworthy is the superior performance achieved when DOGM is used as input data for deep learning, surpassing conventional algorithms.
Dynamic Occupancy Grid Map with Semantic Information Using Deep Learning-Based BEVFusion Method with Camera and LiDAR Fusion
Harin Jang, Taehyun Kim, Kyungjae Ahn, Soo Jeon, Yeonsik Kang
IF 3.5
Sensors
In the field of robotics and autonomous driving, dynamic occupancy grid maps (DOGMs) are typically used to represent the position and velocity information of objects. Although three-dimensional light detection and ranging (LiDAR) sensor-based DOGMs have been actively researched, they have limitations, as they cannot classify types of objects. Therefore, in this study, a deep learning-based camera-LiDAR sensor fusion technique is employed as input to DOGMs. Consequently, not only the position and velocity information of objects but also their class information can be updated, expanding the application areas of DOGMs. Moreover, unclassified LiDAR point measurements contribute to the formation of a map of the surrounding environment, improving the reliability of perception by registering objects that were not classified by deep learning. To achieve this, we developed update rules on the basis of the Dempster-Shafer evidence theory, incorporating class information and the uncertainty of objects occupying grid cells. Furthermore, we analyzed the accuracy of the velocity estimation using two update models. One assigns the occupancy probability only to the edges of the oriented bounding box, whereas the other assigns the occupancy probability to the entire area of the box. The performance of the developed perception technique is evaluated using the public nuScenes dataset. The developed DOGM with object class information will help autonomous vehicles to navigate in complex urban driving environments by providing them with rich information, such as the class and velocity of nearby obstacles.
