An Attentional Recurrent Neural Network for Occlusion-Aware Proactive Anomaly Detection in Field Robot Navigation

TL;DR

This paper introduces an attention-based recurrent neural network that explicitly models sensor occlusions to improve proactive anomaly detection in field robot navigation, especially under sensor occlusion conditions.

Contribution

It presents a novel neural network architecture that fuses sensory inputs, control actions, and occlusion modeling for enhanced anomaly detection in unstructured environments.

Findings

Improved detection accuracy during sensor occlusion scenarios

Increased resilience to false positives in navigation failure prediction

Effective handling of brief complete sensor occlusions

Abstract

The use of mobile robots in unstructured environments like the agricultural field is becoming increasingly common. The ability for such field robots to proactively identify and avoid failures is thus crucial for ensuring efficiency and avoiding damage. However, the cluttered field environment introduces various sources of noise (such as sensor occlusions) that make proactive anomaly detection difficult. Existing approaches can show poor performance in sensor occlusion scenarios as they typically do not explicitly model occlusions and only leverage current sensory inputs. In this work, we present an attention-based recurrent neural network architecture for proactive anomaly detection that fuses current sensory inputs and planned control actions with a latent representation of prior robot state. We enhance our model with an explicitly-learned model of sensor occlusion that is used to modulate the use of our latent representation of prior robot state. Our method shows improved anomaly detection performance and enables mobile field robots to display increased resilience to predicting false positives regarding navigation failure during periods of sensor occlusion, particularly in cases where all sensors are briefly occluded. Our code is available at: https://github.com/andreschreiber/roar