# VIO drifting when using TFlite Server

Source: https://forum.modalai.com/topic/4744/vio-drifting-when-using-tflite-server
Category: Autonomy: VIO, Mapping and Navigation (https://forum.modalai.com/category/19/autonomy-vio-mapping-and-navigation)
Tags: vio
Posted: 2025-09-15 23:03:56 UTC by Ege Yüceel
Replies: 2 · Views: 2449

## Ege Yüceel · 2025-09-15 23:03:56 UTC

Hi ModalAI team

I’m working with a Starling 2 drone running SDK 1.4.0. In a recent project, I integrated a TFLite server to command the drone in certain directions using VIO (qvio).

Here’s the situation:

In Position mode, VIO works fine. It can handle mild to moderately agile maneuvers with good stability. However, once I start using the TFLite server to command the drone (via MAVSDK Python Docker, listening to TFLite outputs from a mounted pipe), VIO becomes unstable. The issues I observe: During slightly rapid motions, I get errors like “accelerometer fail” or “height estimate error”. Over time, VIO itself fails completely and I have to restart.

I am presuming this can happen because of overheating. When the neural network runs, the VOXL2 temperature often reaches 80–85°C, sometimes even above 90°C when I dont start the propellers quickly. This could:

-Directly harm the VOXL2 hardware.

-Disrupt IMU calibration at high temperatures.

I’m thinking about adding a cooling fan or redoing the IMU calibration (hot calibration in particular).

What would be your suggestions or other potential reasons for this case?

Thanks!

## Reply by Moderator (ModalAI staff) · 2025-09-17 14:37:42 UTC

@Ege-Yüceel Hi Ege, the most likely scenario is that the tflite-server is starving the open-vins process causing backups and missed data. Can you increase the "skip frames" parameter in tflite-server or reduce the number of cores it is using?

## Reply by Ege Yüceel · 2025-09-18 21:59:27 UTC (in reply to Moderator)

@Moderator thank you for the recommendation. I will try out this.