Plume mapping via hidden markov methods

Farrell, Jay A.; Pang, Shuo; Li, Wei

doi:10.1109/tsmcb.2003.810873

Cited by 150 publications

(99 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This process continues until the probability distribution of the source reduces to a Dirac function. Infotaxis [6], Hidden Markov Models [7] and Kernel methods [8], are the main examples of this category. Although these techniques are very promising with a great potential in terms of research, they suffer from high computational costs and the need of accurate localization information for the sampling points.…”

Section: Introductionmentioning

confidence: 99%

A 3-D bio-inspired odor source localization and its validation in realistic environmental conditions

Rahbar

Marjovi

Kibleur

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Finding the source of gaseous compounds released in the air with robots finds several applications in various critical situations, such as search and rescue. While the distribution of gas in the air is inherently a 3D phenomenon, most of the previous works have downgraded the problem into 2D search, using only ground robots. In this paper, we have designed a bio-inspired 3D algorithm involving cross-wind Lévy Walk, spiralling and upwind surge. The algorithm has been validated using high-fidelity simulations, and evaluated in a wind tunnel which represents a realistic controlled environment, under different conditions in terms of wind speed, source release rates and odor threshold. Studying success rate and execution time, the results show that the proposed method outperforms its 2D counterpart and is robust to the various setup conditions, especially to the source release rate and the odor threshold.

show abstract

Section: Introductionmentioning

confidence: 99%

A 3-D bio-inspired odor source localization and its validation in realistic environmental conditions

Rahbar

Marjovi

Kibleur

et al. 2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…Simulation is an effective tool, particularly to test the behaviour of complex systems that are difficult or not practical to test experimentally in real environments, like the searching of odour sources in large outdoor spaces. Farrell et al (2003) for example shown the utilization of hidden Markov methods to locate an odour source in a simulated environment. Marques et al (2002a) used a Genetic Algorithm to coordinate a group of mobile robots searching for an odour source.…”

Section: Searching Odour Sources With Multiple Robotsmentioning

confidence: 99%

Particle swarm-based olfactory guided search

2006

View full text Add to dashboard Cite

This article presents a new algorithm for searching odour sources across large search spaces with groups of mobile robots. The proposed algorithm is inspired in the particle swarm optimization (PSO) method. In this method, the search space is sampled by dynamic particles that use their knowledge about the previous sampled space and share this knowledge with other neighbour searching particles allowing the emergence of efficient local searching behaviours. In this case, chemical searching cues about the potential existence of upwind odour sources are exchanged. By default, the agents tend to avoid each other, leading to the emergence of exploration behaviours when no chemical cue exists in the neighbourhood. This behaviour improves the global searching performance.The article explains the relevance of searching odour sources with autonomous agents and identifies the main difficulties for solving this problem. A major difficulty is related with the chaotic nature of the odour transport in the atmosphere due to turbulent phenomena. The characteristics of this problem are described in detail and a simulation framework for testing and analysing different odour searching algorithms was constructed. The proposed PSO-based searching algorithm and modified versions of gradient-based searching and biased random walk-based searching strategies were tested in different environmental conditions and

show abstract

“…Most of the works concerning olfactory search have focused on odor plume tracking [15]- [20] and mapping [21]- [23], whereas plume finding has received little attention. Bio-inspired [16], [17], concentration gradient climbing (chemotaxis) and up-wind directed search (anemotaxis [19], [24], [25]) are the most common approaches to track odor plumes by mobile robots.…”

Section: Introductionmentioning

confidence: 99%

Optimal Swarm Formation for Odor Plume Finding

Marjovi

Marques

2014

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Abstract-This paper presents an analytical approach to the problem of odor plume finding by a network of swarm robotic gas sensors and finds an optimal configuration for them, given a set of assumptions. Considering cross-wind movement for the swarm, we found that the best spatial formation of robots in finding odor plumes is diagonal line configuration with equal distance between each pair of neighboring robots. We show that the distance between neighboring pairs in the line topology depends mainly on the wind speed and the environmental conditions, whereas, the number of robots and the swarm's crosswind movement distance do not show significant impact on optimal configurations. These solutions were analyzed and verified by simulations and experimentally validated in a reduced scale realistic environment using a set of mobile robots.

show abstract

Plume mapping via hidden markov methods

Cited by 150 publications

References 40 publications

A 3-D bio-inspired odor source localization and its validation in realistic environmental conditions

A 3-D bio-inspired odor source localization and its validation in realistic environmental conditions

Particle swarm-based olfactory guided search

Optimal Swarm Formation for Odor Plume Finding

Contact Info

Product

Resources

About