Designing image-based control systems considering workload variations

Mohamed, Sajid; Awan, Asad Ullah; Goswami, Dip; Basten, Twan

doi:10.1109/cdc40024.2019.9030035

Cited by 9 publications

(21 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SPADe scenario-and platform-aware design approach for non-pipelined IBC systems is proposed in [2], [7] where the concepts of the system-scenario-based design and platform-based design methods for IBC are combined into a co-design approach that jointly develops and optimises the image-processing implementation and the controller design. In this work, we extend the SPADe approach [7] by considering pipelining of the control loop along with parallelism and formalising the IBC system modelling.…”

Section: Related Workmentioning

confidence: 99%

“…The control performance quantifies, in essence, how fast the output y(t) reaches the reference r ref . The control performance can be tuned in the cost function for the control gains' design using the state and input weights [2]. Mean square error (MSE): The MSE is the mean of the cumulative sum of the squared errors, i.e.…”

Section: Phase Margin (Pm)mentioning

confidence: 99%

“…A long processing delay results in dropping some camera frames from processing. Moreover, the sensing delay is variable due to image workload variations [2]. These variations can be captured statistically using a probability distribution [3] (illustrated in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimising Multiprocessor Image-Based Control Through Pipelining and Parallelism

Mohamed

Goswami

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Image-based control (IBC) systems have a long sensing delay due to compute-intensive image processing. Modern multiprocessor IBC implementations consider either parallelisation of the sensing task or pipelining of the control loop to cope with this long delay. However, the impact of both parallelisation and pipelining together on the quality-of-control (QoC) of IBC systems is not explored in the literature. We present a model-based design method for multiprocessor IBC implementation, considering both parallelisation and pipelining together. In particular, we address the following problem: For a given platform allocation, what is the optimal degree of pipelining and degree of parallelisation required to maximise the QoC? The proposed method takes into account image-workload variations, inter-frame dependencies and platform constraints. The application is efficiently modelled and analysed using a scenario-aware dataflow graph, and an implementation-aware switched controller is designed that optimises QoC and guarantees stability. We validate the proposed method using simulations and hardware-in-the-loop experiments, considering a lane-keeping assist system.INDEX TERMS image-based control, switched linear control, scenario-based design, platform-aware design, multiprocessor implementation, hardware-in-the-loop validation

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Phase Margin (Pm)mentioning

confidence: 99%

See 1 more Smart Citation

Optimising Multiprocessor Image-Based Control Through Pipelining and Parallelism

Mohamed

Goswami

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…High SSIM loss denotes images with higher visual difference. QoC evaluation of the proposed IBC system is performed using the following four metrics: [5], [34] and consider both control performance and control energy. For Pareto analysis between QoC and energy, we consider MAE as the default QoC metric as it gives a good indication of the steady-state performance.…”

Section: Quality Metricsmentioning

confidence: 99%

Approximation-Aware Design of an Image-Based Control System

Mohamed

Goswami

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Image-based control (IBC) systems are common in many modern applications. In such systems, image-based sensing imposes massive compute workload, making them challenging to implement on embedded platforms. Approximate image processing is a way to handle this challenge. In essence, approximation reduces the workload at the cost of additional sensor noise. In this work, we propose an approximation-aware design approach for optimizing the energy, memory and performance of an IBC system, making it suitable for embedded implementation. First, we perform compute-and data-centric approximations and evaluate its impact on the energy efficiency, memory utilization and closed-loop qualityof-control (QoC) of the IBC system. We observe that the workload reductions due to approximations allow mapping these lighter approximated IBC tasks to embedded platforms with lower power consumption while still ensuring proper system functionality. Therefore, we explore the interplay between approximations and platform mappings to improve the energy-efficiency of IBC systems. Further, an IBC system operates under several environmental scenarios e.g., weather conditions. We evaluate the sensitivity of the IBC system to our approximation-aware design approach when operated under different scenarios and perform a failure probability (FP) analysis using Monte-Carlo simulations to analyze the robustness of the approximate system. Finally, we design an optimal approximation-aware controller that models the approximation error as sensor noise and show QoC improvements. We demonstrate the effectiveness of our approach using a concrete case-study of a lane keeping assist system (LKAS) using a heterogeneous NVIDIA AGX Xavier embedded platform in a hardware-in-the-loop (HiL) framework. We show energy and memory reduction of up to 92% and 88% respectively, for 44% QoC improvements with respect to the accurate implementation. We show that our approximation-aware design approach has an FP (per km) ≤ 9.6 × 10 −6 %.

show abstract

“…However, in our setting, the computation time of the tasks is not characterised by a single number (the worst case), but by a probability distribution. Based on the observation that occasional delays or data losses can be tolerated by many control systems (Cervin & Eker, 2003;Mohamed, Awan, Goswami, & Basten, 2019), we consider a model in which a job executing beyond its deadline is cancelled without closing the control loop (the same approach used in networked control to deal with packet dropouts by Nilsson and Bernhardsson (1996)).…”

Section: Introductionmentioning

confidence: 99%

Optimal resource allocation for stochastic systems performance optimisation of control tasks undergoing stochastic execution times

Fontanelli

Greco

Palopoli

2020

International Journal of Control

View full text Add to dashboard Cite

The problem addressed in this paper is the optimal allocation of a CPU to a number of software control tasks. Each task is used to implement a feedback controller for a linear and time invariant system and is activated with a fixed period. On every periodic activation, the task executes a job, which collects the output of the system, and produces the control values after executing for a random computation time. If a job's duration exceeds a deadline, then the job is cancelled and the control values are not updated.The systems to be controlled are affected by process noise. Therefore the performance of each control loop can be evaluated through the steady state covariance of the system's state, which depends on the probability with which the task implementing the controller drops its jobs. We show that by making a proper choice for the scheduling algorithm, this probability can be straightforwardly computed as a function of the scheduling parameters. This observation enables the construction of a very efficient procedure for finding the scheduling parameters that attain the optimal tradeoff between the performance of the different control loops.

show abstract

Designing image-based control systems considering workload variations

Abstract: We present an alternate controller synthesis method based on a Markovian jump linear system (MJLS) for-

Cited by 9 publications

References 16 publications

Optimising Multiprocessor Image-Based Control Through Pipelining and Parallelism

Optimising Multiprocessor Image-Based Control Through Pipelining and Parallelism

Approximation-Aware Design of an Image-Based Control System

Optimal resource allocation for stochastic systems performance optimisation of control tasks undergoing stochastic execution times

Contact Info

Product

Resources

About