An experiment in integrated exploration

Makarenko, Alexei; Williams, Stefan B.; Bourgault, F.; Durrant‐Whyte, Hugh

doi:10.1109/irds.2002.1041445

Cited by 240 publications

(154 citation statements)

References 14 publications

Supporting

Mentioning

146

Contrasting

Unclassified

Order By: Relevance

“…In this situation, the robot must gather information to reduce map uncertainty, localize itself, and navigate to reach the goal. This is sometimes called integrated exploration [8]. When the environment is static, integrated exploration belongs to our second category.…”

Section: A Robotic Tasks Studiedmentioning

confidence: 99%

SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces

Kurniawati

Hsu

Lee

2008

Robotics: Science and Systems IV

615

664

View full text Add to dashboard Cite

Abstract-Motion planning in uncertain and dynamic environments is an essential capability for autonomous robots. Partially observable Markov decision processes (POMDPs) provide a principled mathematical framework for solving such problems, but they are often avoided in robotics due to high computational complexity. Our goal is to create practical POMDP algorithms and software for common robotic tasks. To this end, we have developed a new point-based POMDP algorithm that exploits the notion of optimally reachable belief spaces to improve computational efficiency. In simulation, we successfully applied the algorithm to a set of common robotic tasks, including instances of coastal navigation, grasping, mobile robot exploration, and target tracking, all modeled as POMDPs with a large number of states. In most of the instances studied, our algorithm substantially outperformed one of the fastest existing point-based algorithms. A software package implementing our algorithm is available for download at http://motion.comp.nus.edu. sg/projects/pomdp/pomdp.html.

show abstract

Section: A Robotic Tasks Studiedmentioning

confidence: 99%

SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces

Kurniawati

Hsu

Lee

2008

Robotics: Science and Systems IV

615

664

View full text Add to dashboard Cite

show abstract

“…The integrated approach is based on the method presented by Makarenko et al [28]. It consists of integrating the SLAM algorithm in the goal choice by means of including a localizability term in the benefit function:…”

Section: Integrated Approachmentioning

confidence: 99%

MRXT: The Multi-Robot Exploration Tool

Gil

Juliá

Reinoso

2015

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This paper presents the multi-robot eXploration tool (MRXT) [Freely available at http://arvc.umh.es/mrxt], a new mobile robotics simulation tool whose aim is to experiment and understand some well-known multi-robot exploration algorithms. The application is designed to test and compare different multi-robot exploration algorithms as well as SLAM techniques. The application includes a wide range of exploration algorithms that differ in their level of coordination and integration with the SLAM algorithm. The tool is focused on describing the exploration problem in a simple manner so that it is useful for educational or research purposes. In comparison with other simulation tools, MRXT is the first application completely focused on the exploration problem, so it can be easily employed to understand interactively many of the issues regarding this general problem in mobile robotics. Furthermore, the paper describes some examples using the tool.

show abstract

“…Selecting a target location by trading off the benefits and costs in a weighted sum has been previously used in autonomous exploration [20], [21]. By adjusting the parameter α ∈ [0, 1] we can alter the search behavior.…”

Section: A Maximum Utility Nodementioning

confidence: 99%

Searching for objects: Combining multiple cues to object locations using a maximum entropy model

Joho

Burgard

2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-In this paper, we consider the problem of how background knowledge about usual object arrangements can be utilized by a mobile robot to more efficiently find an object in an unknown environment. We decompose the action selection problem during the search into two parts. First, we compute a belief over the location of the object and subsequently use the belief to select the next target location the robot should visit. For the inference part, we utilize a maximum entropy model which models the conditional distribution over possible locations of the target object given the observations made so far. The model is based on co-occurrences of objects and object attributes in different spatial contexts. The parameters are learned by maximizing the data likelihood using gradient ascent. We evaluate our approach by simulated search runs based on data obtained from different real-world environments. Our results show a significant improvement over a standard search technique which does not employ domain-specific background knowledge.

show abstract

An experiment in integrated exploration

Cited by 240 publications

References 14 publications

SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces

SARSOP: Efficient Point-Based POMDP Planning by Approximating Optimally Reachable Belief Spaces

MRXT: The Multi-Robot Exploration Tool

Searching for objects: Combining multiple cues to object locations using a maximum entropy model

Contact Info

Product

Resources

About