TY - GEN
T1 - An Attentional Recurrent Neural Network for Occlusion-Aware Proactive Anomaly Detection in Field Robot Navigation
AU - Schreiber, Andre
AU - Ji, Tianchen
AU - McPherson, D. Livingston
AU - Driggs-Campbell, Katherine
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85182526218&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85182526218&partnerID=8YFLogxK
U2 - 10.1109/IROS55552.2023.10341852
DO - 10.1109/IROS55552.2023.10341852
M3 - Conference contribution
AN - SCOPUS:85182526218
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 8038
EP - 8045
BT - 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
Y2 - 1 October 2023 through 5 October 2023
ER -