Collective Self-detection Scheme for Adaptive Error Detection in a Foraging Swarm of Robots

Lau, Hui Keng; Timmis, Jon; Bate, Iain

doi:10.1007/978-3-642-22371-6_23

Cited by 5 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By contrast, our proposed faultdetection model is distributed in design and consequently scalable as demonstrated with up to a fivefold increase in swarm size. Furthermore, in contrast to other exogenous and distributed fault detection models, our approach is not limited to the detection of specific faults involving complete robot failure [30], and does not require detailed task-performance metrics known a priori [16,32].…”

Section: Discussionmentioning

confidence: 99%

“…By contrast, robots plagued with partial failures have a far greater potential of disrupting the MRS behaviour [20]. In other work, Lau et al [16,32] investigated the detection of errors due to faults in a cooperative foraging MRS operating in a dynamic environment. Various statistical classifiers and kernel density estimation functions were applied to the number of pucks foraged by individual robots, to detect outliers (caused by robot faults).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

To err is robotic, to tolerate immunological: fault detection in multirobot systems

Tarapore¹,

Lima²,

Carneiro³

et al. 2015

Bioinspir. Biomim.

View full text Add to dashboard Cite

Abstract. Fault detection and fault tolerance represent two of the most important and largely unsolved issues in the field of multirobot systems. Efficient, long-term operation requires an accurate, timely detection, and accommodation of abnormally behaving robots. Most existing approaches to fault-tolerance prescribe a characterisation of normal robot behaviours, and train a model to recognise these behaviours. Behaviours unrecognised by the model are consequently labelled abnormal or faulty. Multirobot systems employing these models do not transition well to scenarios involving temporal variations in behaviour (e.g., online learning of new behaviours, or in response to environment perturbations). The vertebrate immune system is a complex distributed system capable of learning to tolerate the organism's tissues even when they change during puberty or metamorphosis, and to mount specific responses to invading pathogens, all without the need of a genetically hardwired characterisation of normality. We present a generic abnormality detection approach based on a model of the adaptive immune system, and evaluate the approach in a swarm of robots. Our results reveal the robust detection of abnormal robots simulating common electro-mechanical and software faults, irrespective of temporal changes in swarm behaviour. Abnormality detection Fault detection in multirobot system2 is shown to be scalable in terms of the number of robots in the swarm, and in terms of the size of the behaviour classification space.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

To err is robotic, to tolerate immunological: fault detection in multirobot systems

Tarapore¹,

Lima²,

Carneiro³

et al. 2015

Bioinspir. Biomim.

View full text Add to dashboard Cite

show abstract

“…As an online data-driven fault detection method, RDA is an efficient algorithm that can process data processing online and solve nonlinear problems. Lau et al applied this method in a collective self-detection scheme for adaptive error detection in a foraging swarm of robots [39], [40]. Results showed that RDA can accurately detect errors with low-rate false alarms and adapt to dynamic environments.…”

mentioning

confidence: 99%

Monitoring for Nonlinear Multiple Modes Process Based on LL-SVDD-MRDA

Tian

Qian

2014

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

This study proposes an online monitoring technique for nonlinear multiple-mode problems in industrial processes. The contributions of the proposed technique are summarized as follows: 1) Lazy learning (LL), a new adaptive local modeling method, is introduced for multiple-mode process monitoring. In this method, multiple modes are separated and accurately modeled online, and the between-mode dynamic process is considered.2) The modified receptor density algorithm (MRDA) exhibiting superior nonlinear ability is introduced to analyze the residuals between the actual system output and the model-predicted output. The simulation of the Tennessee Eastman process with multiple operation modes shows that compared with other techniques mentioned in this study, the proposed technique performs more accurately and is more suitable for nonlinear processes with multiple operation modes.Note to Practitioners-This paper was motivated by the problem of fault detection of chemical process. Most chemical processes are nonlinear processes. Especially in the multiple-mode process, nonlinear is more significant, making the process more difficult to monitor. In this paper, we modify the receptor density algorithm (MRDA) and combine it with support vector data description (SVDD) and LL algorithm to monitor nonlinear multiple operation modes chemical processes. In LL-SVDD-MRDA, LL is introduced to solve multiple operation modes, SVDD is adopted to construct one-dimensional distance statistics to reflect the change in high-dimensional data and MRDA is used for nonlinear data monitoring. Our simulation demonstrates that LL-SVDD-MRDA is a highly competitive method for handling nonlinear multiple operation modes chemical processes monitoring.Index Terms-Between-mode dynamic process, lazy learning (LL), modified receptor density algorithm (MRDA), multiple operation modes, nonlinear, support vector data description (SVDD). 1545-5955

show abstract