Planning exploration strategies for simultaneous localization and mapping

Abstract

In this paper, we present techniques that allow one or multiple mobile robots to efficiently explore and model their environment. While much existing research in the area of Simultaneous Localization and Mapping (SLAM) focuses on issues related to uncertainty in sensor data, our work focuses on the problem of planning optimal exploration strategies. We develop a utility function that measures the quality of proposed sensing locations, give a randomized algorithm for selecting an optimal next sensing location, and provide methods for extracting features from sensor data and merging these into an incrementally constructed map.We have also provide an efficient algorithm driven by our utility function. This algorithm is able to explore several steps ahead without incurring too high a computational cost. We have compared that exploration strategy with a totally greedy algorithm that optimizes our utility function with a one-step-look ahead.The planning algorithms which have been developed operate using simple but flexible models of the robot sensors and actuator abilities. Techniques that allow implementation of these sensor models on top of the capabilities of actual sensors have been provided.All of the proposed algorithms have been implemented either on real robots (for the case of individual robots) or in simulation (for the case of multiple robots), and experimental results are given.

A Scouting Strategy for Real-Time Strategy Games

“…A MCDM strategy for choosing NBV is presented in [4] by using Choquet Integral [7] to combine criterion utilities. [21] presents a one-step-look-ahead strategy by generate a search tree from candidate positions during exploration. [14] formulates finding exploration paths in planar grid environment as a search problem, in which the occupation state of global grids is testing when doing next step planning.…”

“…[14] formulates finding exploration paths in planar grid environment as a search problem, in which the occupation state of global grids is testing when doing next step planning. As investigated, frontier-based map representation method is proved to be an effective way to filter candidate positions for evaluation [1,2,4,8,10,21]. Comparing to grid-based map presentation, choosing potential next points along frontiers intuitively provides more chances to gather knowledge of unknown areas.…”

Moving From ‘How to go There?’ to ‘Where to go?’: Towards Increased Autonomy of Mobile Robots

“…Authors in [31] use an utility function that evaluates a sequence of m candidate locations (poses) with the following multiplicative function:…”

Combined Vision and Frontier-Based Exploration Strategies for Semantic Mapping

“…In the second approach, exploration is viewed as a sequence of steps, each one composed of a movement towards a location and of an observation with which the robot acquires data about the environment. The exploration of an unknown environment using a 2D scanning laser sensor is often performed using the frontier-based exploration algorithm [2] or an exploration strategy choosing the next best position for the robot given the utility of this position for the mapping problem [3]. In the context of our project, the exploration should take into account the need to search for objects.…”