# Embedded out-of-distribution detection on an autonomous robot platform

arXiv: https://arxiv.org/abs/2106.15965 · HTML: https://mlsanity.com/paper/2106.15965/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2021.

## Built on by (most cited first, 6 of 6)

- [Out-of-distribution detection algorithms for robust insect classification](https://mlsanity.com/paper/2305.01823/) (2023)
- [Design Methodology for Deep Out-of-Distribution Detectors in Real-Time Cyber-Physical Systems](https://mlsanity.com/paper/2207.14694/) (2022)
- [Demo Abstract: Real-Time Out-of-Distribution Detection on a Mobile Robot](https://mlsanity.com/paper/2211.11520/) (2022)
- [Out-of-Distribution Detection for Adaptive Computer Vision](https://mlsanity.com/paper/2305.09293/) (2023)
- [Making the Flow Glow -- Robot Perception under Severe Lighting Conditions using Normalizing Flow Gradients](https://mlsanity.com/paper/2412.07565/) (2024)
- [A Low-Cost Lane-Following Algorithm for Cyber-Physical Robots](https://mlsanity.com/paper/2208.10765/) (2022)

## Abstract (arXiv)

Machine learning (ML) is actively finding its way into modern cyber-physical systems (CPS), many of which are safety-critical real-time systems. It is well known that ML outputs are not reliable when testing data are novel with regards to model training and validation data, i.e., out-of-distribution (OOD) test data. We implement an unsupervised deep neural network-based OOD detector on a real-time embedded autonomous Duckiebot and evaluate detection performance. Our OOD detector produces a success rate of 87.5% for emergency stopping a Duckiebot on a braking test bed we designed. We also provide case analysis on computing resource challenges specific to the Robot Operating System (ROS) middleware on the Duckiebot.