Geometric Map-Assisted Localization for Mobile Robots Based on Uniform-Gaussian Distribution

Active Mapping and Robot Exploration: A Survey

“…This is an attempt to efficiently represent the environment without losing much information, but it hampers trajectory calculation and the overall management of the data. So, in practice, not many works make use of this method and the occupancy grid map option is preferred [ 188 , 189 ]. All the same, additional data for active mapping purposes, e.g., information gain values, may also be stored, which opens up a wide range of possibilities for designing ASLAM algorithms [ 190 ].…”

“…This is an attempt to efficiently represent the environment without losing much information, but it hampers trajectory calculation and the overall management of the data. So, in practice, not many works make use of this method and the occupancy grid map option is preferred [ 188 , 189 ].…”

Heading Reference-Assisted Pose Estimation for Ground Vehicles

“…The existing solution on enhancing VO performance falls on i) improving VO components including feature detection, matching, outlier removal or pose optimization; and ii) seeking assistance from other approaches or databases [4] such as lidar [5], Global Positioning System (GPS) [6], digital maps [7], [8], Inertial Navigation System (INS) and many others [9]- [20]. Benefiting from its self-contained property, many Visual-Inertial Odometry (VIO) schemes have been proposed to reduce drift in VO.…”

An OGM‐Based Visual Navigation System with Reduced Homographies and Accurate Computations for Mobile Robots

“…Maps (POLMs). In the beginning, an unknown environment has a OGM with a general occupancy probability that is equal to 0.5, which corresponds to an unknown occupancy state for all POLMs and its grid-elements, according to (4). To sense an environment through a POGM that requires generating several POLMs, the whole process is as follows (see Figure 10).…”

“…Robot navigation is an important task that allows robots to perform activities such as localization, path planning, collision avoidance [1], and people finding [2]. Here, environment modeling plays a key role and several methods have been proposed, e.g., Occupancy Grid Mapping (OGM) [3], Geometric Mapping (GM) [4], and Topological Mapping (TM) [5], with the former being the predominant one. The OGM method creates maps from environments which have been sensed by either a sonar [3,6] or a different sensor such as laser range finder (e.g., Laser Imaging Detection and Ranging (LIDAR)) [7][8][9][10][11], ultrasonic [12], radar [13], and vision [14][15][16][17][18], as well as using a combination of them [19][20][21][22][23][24].…”