Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware

Alessandra Maria Lanz; Matias Ou; Mattia Nicolella; Renato Mancuso

doi:10.4230/LIPIcs.CVIT.2016.23

Publications Memory & Shared-Resource Management

Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware

Alessandra Maria Lanz, Matias Ou, Mattia Nicolella, Renato Mancuso

Industrial Session of the 38th Euromicro Conference on Real-Time Systems (ECRTS 2026), July 2026, Lund, Sweden

Read the PDF Publisher page (DOI) Code and artifacts Cite

Figure 2 Top-down (XY ) trajectories from one representative trial of each condition, aligned to the Vicon ground truth (black) via the Umeyama similarity transform. Solo and Controlled track the ground truth closely. The Uncontrolled run collapses due to an internal loop unrelated to the true camera motion which is the failure mode the controller is designed to prevent.

Abstract

We present a user-space feedback controller for protecting the tracking accuracy of OV 2 SLAM, the visual SLAM component of the Arm AR HUD Industrial Challenge, when it runs alongside competing workloads. The controller monitors the SLAM pipeline at five function-entry checkpoints using Linux uprobes, measures per-frame progress against a pre-calibrated solo-run baseline, and pauses the interfering workload via SIGSTOP/SIGCONT when progress falls below a threshold. We implement and evaluate the controller on a Xilinx ZCU102 development board (quad-core ARM Cortex-A53, 1 MB shared L2 cache) running Ubuntu 22.04 and ROS2 Humble, using a synthetic memory-bandwidth aggressor as the interfering workload. Under uncontrolled interference, mean trajectory RMSE rises to 1.03 m with 3 out of 5 trials diverging. With the controller active, mean RMSE drops to 0.095 m with no trials diverging. All tools are written in C and run entirely in user space, requiring no kernel modifications and no recompilation of the SLAM binary.

Code and hardware artifacts

Cite this paper

@inproceedings{UPROG_ecrts-ic-26,
  title     = {{Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware}},
  author    = {Lanz, Alessandra Maria and Ou, Matias and Nicolella, Mattia and Mancuso, Renato},
  booktitle = {Industrial Session of the 38th Euromicro Conference on Real-Time Systems (ECRTS 2026)},
  year      = 2026,
  month     = jul,
  address   = {Lund, Sweden},
  doi       = {10.4230/LIPIcs.CVIT.2016.23},
  url       = {https://doi.org/10.4230/LIPIcs.CVIT.2016.23}
}

Download .bib

TY  - CONF
AU  - Lanz, Alessandra Maria
AU  - Ou, Matias
AU  - Nicolella, Mattia
AU  - Mancuso, Renato
TI  - Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware
T2  - Industrial Session of the 38th Euromicro Conference on Real-Time Systems (ECRTS 2026)
PY  - 2026
DA  - 2026/07//
CY  - Lund, Sweden
DO  - 10.4230/LIPIcs.CVIT.2016.23
UR  - https://doi.org/10.4230/LIPIcs.CVIT.2016.23
AB  - We present a user-space feedback controller for protecting the tracking accuracy of OV 2 SLAM, the visual SLAM component of the Arm AR HUD Industrial Challenge, when it runs alongside competing workloads. The controller monitors the SLAM pipeline at five function-entry checkpoints using Linux uprobes, measures per-frame progress against a pre-calibrated solo-run baseline, and pauses the interfering workload via SIGSTOP/SIGCONT when progress falls below a threshold. We implement and evaluate the controller on a Xilinx ZCU102 development board (quad-core ARM Cortex-A53, 1 MB shared L2 cache) running Ubuntu 22.04 and ROS2 Humble, using a synthetic memory-bandwidth aggressor as the interfering workload. Under uncontrolled interference, mean trajectory RMSE rises to 1.03 m with 3 out of 5 trials diverging. With the controller active, mean RMSE drops to 0.095 m with no trials diverging. All tools are written in C and run entirely in user space, requiring no kernel modifications and no recompilation of the SLAM binary.
ER  -

Download .ris

%0 Conference Paper
%A Lanz, Alessandra Maria
%A Ou, Matias
%A Nicolella, Mattia
%A Mancuso, Renato
%T Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware
%B Industrial Session of the 38th Euromicro Conference on Real-Time Systems (ECRTS 2026)
%D 2026
%C Lund, Sweden
%R 10.4230/LIPIcs.CVIT.2016.23
%U https://doi.org/10.4230/LIPIcs.CVIT.2016.23
%X We present a user-space feedback controller for protecting the tracking accuracy of OV 2 SLAM, the visual SLAM component of the Arm AR HUD Industrial Challenge, when it runs alongside competing workloads. The controller monitors the SLAM pipeline at five function-entry checkpoints using Linux uprobes, measures per-frame progress against a pre-calibrated solo-run baseline, and pauses the interfering workload via SIGSTOP/SIGCONT when progress falls below a threshold. We implement and evaluate the controller on a Xilinx ZCU102 development board (quad-core ARM Cortex-A53, 1 MB shared L2 cache) running Ubuntu 22.04 and ROS2 Humble, using a synthetic memory-bandwidth aggressor as the interfering workload. Under uncontrolled interference, mean trajectory RMSE rises to 1.03 m with 3 out of 5 trials diverging. With the controller active, mean RMSE drops to 0.095 m with no trials diverging. All tools are written in C and run entirely in user space, requiring no kernel modifications and no recompilation of the SLAM binary.

Download .enw

[
    {
        "id": "UPROG_ecrts-ic-26",
        "type": "paper-conference",
        "title": "Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware",
        "author": [
            {
                "family": "Lanz",
                "given": "Alessandra Maria"
            },
            {
                "family": "Ou",
                "given": "Matias"
            },
            {
                "family": "Nicolella",
                "given": "Mattia"
            },
            {
                "family": "Mancuso",
                "given": "Renato"
            }
        ],
        "container-title": "Industrial Session of the 38th Euromicro Conference on Real-Time Systems (ECRTS 2026)",
        "issued": {
            "date-parts": [
                [
                    2026,
                    7
                ]
            ]
        },
        "publisher-place": "Lund, Sweden",
        "DOI": "10.4230/LIPIcs.CVIT.2016.23",
        "abstract": "We present a user-space feedback controller for protecting the tracking accuracy of OV 2 SLAM, the visual SLAM component of the Arm AR HUD Industrial Challenge, when it runs alongside competing workloads. The controller monitors the SLAM pipeline at five function-entry checkpoints using Linux uprobes, measures per-frame progress against a pre-calibrated solo-run baseline, and pauses the interfering workload via SIGSTOP/SIGCONT when progress falls below a threshold. We implement and evaluate the controller on a Xilinx ZCU102 development board (quad-core ARM Cortex-A53, 1 MB shared L2 cache) running Ubuntu 22.04 and ROS2 Humble, using a synthetic memory-bandwidth aggressor as the interfering workload. Under uncontrolled interference, mean trajectory RMSE rises to 1.03 m with 3 out of 5 trials diverging. With the controller active, mean RMSE drops to 0.095 m with no trials diverging. All tools are written in C and run entirely in user space, requiring no kernel modifications and no recompilation of the SLAM binary."
    }
]

Download .json

A. M. Lanz, M. Ou, M. Nicolella, and R. Mancuso, “Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware,” in Industrial Session of the 38th Euromicro Conference on Real-Time Systems (ECRTS 2026), Jul. 2026, doi: 10.4230/LIPIcs.CVIT.2016.23.

Download .txt

Lanz, A. M., Ou, M., Nicolella, M., & Mancuso, R. (2026). Under Pressure: Adaptive Isolation for Visual SLAM Perception Workloads on Contended ARM Hardware. In Industrial Session of the 38th Euromicro Conference on Real-Time Systems (ECRTS 2026). https://doi.org/10.4230/LIPIcs.CVIT.2016.23

Download .txt