Machine-learning based approaches for self-tuning trajectory tracking controllers under terrain changes in repetitive tasks

Prado, Alvaro; Michałek, Maciej Marcin; Cheein, Fernando Auat

doi:10.1016/j.engappai.2017.09.013

Cited by 22 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some specifically mention some software fault-tolerance measures. The measures include input checker [16], output checker [17,18], replication [19], design diversity [20], and voting [21]. However, in many of these papers, the details of the measures are not described very rigorously.…”

Section: Previous Workmentioning

confidence: 99%

Section: Fault-tolerance Solution Proposalsmentioning

confidence: 99%

“…Output checker (used by Prado et al [17] and Li et al [18], also known as acceptance test [11]) is a component which detects errors by assessing ML model's outputs and prevents errors from propagating further into other parts of the system. For example, Prado et al [17] set the software to limit the speed and steering angle of an electric vehicle to certain maxima, no matter what the ML-based controller output. In addition to this hard limit approach, we include whether errors of a ML model could be detected by comparing the outputs to historical data or by using another ML model, trained to detect unexpected behaviour of the primary ML model.…”

Section: Fault-tolerance Solution Proposalsmentioning

confidence: 99%

See 2 more Smart Citations

On Misbehaviour and Fault Tolerance in Machine Learning Systems

Myllyaho¹,

Raatikainen²,

Männistö³

et al. 2021

Preprint

View full text Add to dashboard Cite

Machine learning (ML) provides us with numerous opportunities, allowing ML systems to adapt to new situations and contexts. At the same time, this adaptability raises uncertainties concerning the run-time product quality or dependability, such as reliability and security, of these systems. Systems can be tested and monitored, but this does not provide protection against faults and failures in adapted ML systems themselves. We studied software designs that aim at introducing fault tolerance in ML systems so that possible problems in ML components of the systems can be avoided. The research was conducted as a case study, and its data was collected through five semi-structured interviews with experienced software architects. We present a conceptualisation of the misbehaviour of ML systems, the perceived role of fault tolerance, and the designs used. Common patterns to incorporating ML components in design in a fault tolerant fashion have started to emerge. ML models are, for example, guarded by monitoring the inputs and their distribution, and enforcing business rules on acceptable outputs. Multiple, specialised ML models are used to adapt to the variations and changes in the surrounding world, and simpler fall-over techniques like default outputs are put in place to have systems up and running in the face of problems. However, the general role of these patterns is not widely acknowledged. This is mainly due to the relative immaturity of using ML as part of a complete software system: the field still lacks established frameworks and practices beyond training to implement, operate, and maintain the software that utilises ML. ML software engineering needs further analysis and development on all fronts.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Fault-tolerance Solution Proposalsmentioning

confidence: 99%

Section: Fault-tolerance Solution Proposalsmentioning

confidence: 99%

See 1 more Smart Citation

On Misbehaviour and Fault Tolerance in Machine Learning Systems

Myllyaho¹,

Raatikainen²,

Männistö³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, a complete study using experimental and simulation approve was presented for utilising the wireless power transfer (WPT) in the charging system of the electric vehicle (EV) based on resonators with coupled electric fields [1]. The smart system is required now for optimum control of EV [2]. The smart system is also required for fast charging of the EV by detecting the maximum value of the transferred power [1].…”

Section: Introductionmentioning

confidence: 99%

Advanced automation system for charging electric vehicles based on machine vision and finite element method

Talaat

Arafa

Metwally

2020

IET Electric Power Applications

View full text Add to dashboard Cite

Electric vehicle (EV) technology proposed itself as a great solution for the predictable shortage in traditional energy sources. Using wireless power transfer (WPT) technology for charging the battery can be considered as a good solution to overcome the battery charging time problem. The considered WPT technique in this research is an inductive magnetic resonance (IMR). The problem now is to design a smart controller system that enables the EVs to obtain the optimum value of WPT by using the machine vision and the technology of Internet of Things (IOT). The utilisation technique of the maximum WPT in this research based on the simulation study of the magnetic flux density between the sending and receiving coils of the WPT system. Maximum efficiency of IMR method depends directly on the ideality of coils alignment. To achieve this alignment, a smart controller has been introduced with four integrated controlling layers. Coordinating an image processing technique with smart embedded sensing elements is considered the main solution key to better positioning. National instrument packages NI LabVIEW and NI vision are considered to fully control the system. NI Data Dashboard enables creating a wireless link using the concept of IOT to a smartphone running simple graphical user interface.

show abstract

“…However, finding such distances was an off-line procedure, as the vehicle did not update the way-points as it traversed the agricultural field. It remains as an open field of study to explore what would happen if such a distance is real-time adjusted according to the energy availability of the system, since, as reported in [26], the stability of the controller could be compromised, as well as actuator saturation problems could arise.…”

mentioning

confidence: 99%

Profiling the Instantaneous Power Consumption of Electric Machinery in Agricultural Environments: An Algebraic Approach

2019

View full text Add to dashboard Cite

One of the upcoming challenges in precision agriculture is the development of electric machinery able to replace traditional combustion engines. This step toward green agriculture practices still has to face the lifetime of the batteries. Despite their technological advancement, batteries’ charges do not last as long as fueled engines. The route planning problem (RPP), for example, has to be re-thought according to the available energy resources since the machinery might exhaust its power without finishing the route. This work focuses in part on such a vast problem by proposing and testing an algebraic, yet simple technique to obtain instantaneous power consumption (IPC) profiles to be used by the RPP. The technique presented herein uses the knowledge of the terrain, the kinematic and dynamic constraints of the vehicle, and its electric model. The methodology followed is later validated in a real grove—i.e., trees cultivated in rows—showing that our power profiling technique reaches errors smaller than 10% when estimating the IPC and the associated energy required. This result can lead to better decisions by the farmer.

show abstract

Machine-learning based approaches for self-tuning trajectory tracking controllers under terrain changes in repetitive tasks

Cited by 22 publications

References 36 publications

On Misbehaviour and Fault Tolerance in Machine Learning Systems

On Misbehaviour and Fault Tolerance in Machine Learning Systems

Advanced automation system for charging electric vehicles based on machine vision and finite element method

Profiling the Instantaneous Power Consumption of Electric Machinery in Agricultural Environments: An Algebraic Approach

Contact Info

Product

Resources

About