# Unsupervised Memory-Enhanced Video Transformers: Obstacle Detection for Autonomous Agricultural Rover

arXiv: https://arxiv.org/abs/2606.26151 · HTML: https://mlsanity.com/paper/2606.26151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [SimpleNet: A Simple Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2303.15140/) (2023)
- [VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2104.10036/) (2021)
- [Video Transformers: A Survey](https://mlsanity.com/paper/2201.05991/) (2022)
- [Safe Robot Navigation via Multi-Modal Anomaly Detection](https://mlsanity.com/paper/2001.07934/) (2020)
- [ADTR: Anomaly Detection Transformer with Feature Reconstruction](https://mlsanity.com/paper/2209.01816/) (2022)
- [AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decoder](https://mlsanity.com/paper/2203.10808/) (2022)
- [GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features](https://mlsanity.com/paper/2407.12427/) (2024)
- [Self-Supervised Drivable Area and Road Anomaly Segmentation using RGB-D Data for Robotic Wheelchairs](https://mlsanity.com/paper/2007.05950/) (2020)
- [Wild Visual Navigation: Fast Traversability Learning via Pre-Trained Models and Online Self-Supervision](https://mlsanity.com/paper/2404.07110/) (2024)
- [Anomaly Detection in Aerial Videos with Transformers](https://mlsanity.com/paper/2209.13363/) (2022)
- [Foundation Models and Transformers for Anomaly Detection: A Survey](https://mlsanity.com/paper/2507.15905/) (2025)

## Abstract (arXiv)

While autonomous rovers have become indispensable to precision farming, achieving consistent operational safety remains a critical challenge. Conventional safety sensors, such as LiDAR, fail to detect obstacles positioned below the plant canopy, posing a significant risk. While camera-based supervised learning methods can detect common objects, they perform poorly when faced with obstacles that were not present in their training data. Actual unsupervised anomaly detection offers a solution by learning the normal visual patterns of an environment, but often fails for the dynamic scenes captured by a moving rover. This paper introduces Video Memory Transformers for Anomaly Detection (VMTAD), a fully unsupervised method designed for real-time obstacle detection in dynamic agricultural scenes. VMTAD utilizes a transformer-driven architecture augmented with a dedicated memory module. This memory module leverages temporal context by processing encoded representations of preceding frames. This approach enables the system to effectively address the dynamic context caused by the robot's movement. The model is trained using only images that represent normal operation, requiring no data labels. VMTAD was rigorously evaluated on the 'Grillion' agricultural rover. On a challenging rapeseed dataset, VMTAD achieved state-of-the-art performance, reaching a 0.973 detection and 0.997 segmentation Area Under the Receiver Operating Characteristic curve. A lightweight variant provides an optimal balance of high accuracy and real-time inference (14 ms), which is critical for safety, as confirmed by our analysis of the rover's total stopping distance.