Exploration Transform: A stable exploring algorithm for robots in rescue environments

Abstract

Autonomous robots in rescue environments have to occupied. To generate this map, the algorithm uses the robot's fulfill several task at the same time: They have to localize themselves, odometry data and the sensor readings of a Hokuyo URGbuild maps, detect victims and decide where to go next for further 04LX laser range finder. The map building process uses a parexploration. In this contribution we present an approach that provides a robust solution for the exploration task: Based on the knowledge Tid fitroach the centfscantosthe occupancy Rid. of the environment that the robot has already acquired, the algorithm This approach was successfully tested during the RoboCup calculates a path to the next interesting "frontier". Our comprehensive World Championship 2006, but relied on a remotely controlled approach takes into account the distance to the next frontier and robot. To make the system fully autonomous, the exploration the difficulty of the path for the robot. Those difficulties can result behavior described in the following sections was implemented. from narrow passages but also from wide, open spaces where the sensors cannot detect any landmark. For the native exploration task The paper is organized as follows: In secion II, the related the algorithm is fed with occupancy grids. For the search task, it can work is presented. The different approaches for exploration also process maps that encode additional information, e. g. places that and path planning are explained. In section III the Exploration have not been searched by other sensors yet.

Exploration strategies based on multi-criteria decision making for searching environments in rescue operations

“…In this approach, the evaluation of candidate locations is implicitly encoded in the potential field generation technique. For instance, in Wirth and Pellenz (2007) each cell c is evaluated with respect to every frontier cell f . This is done by computing a cost value depending both on the length and on the safety (vicinity to obstacles) of the path from c to f (the two criteria are combined with a weighted sum).…”

A Visualization‐Based Analysis System for Urban Search & Rescue Mission Planning Support

“…Given the 2D map of the environment, one common approach to path planning is to plan the shortest trajectory and to follow this trajectory stepwise. Wirth et al introduced an exploration strategy and path planner that utilizes occupancy grid maps to reach several targets at the same time [WP07]. We generalized their idea to apply a voxelization technique to the point cloud data instead.…”

Hector Open Source Modules for Autonomous Mapping and Navigation with Rescue Robots

“…We provide the hector exploration planner that is based on the exploration transform approach presented in [10]. In our exploration planner, frontiers towards the front of the robot are weighted favorably, to prevent frequent costly turning of the robot.…”