Incremental Learning with Memory Regressors for Motion Prediction in Autonomous Racing

• DOI: 10.1145/3576841.3589627
• Publication Date: 2023-05-04T16:18:19Z
• Authors: Yahan Yang; Souradeep Dutta; Kuk Jin Jang; Oleg Sokolsky; Insup Lee
• Keywords: Component (thermodynamics)

Cyber-physical systems (CPS) with learning-enabled components suffer from reduced performance under distribution shift. In this paper, we consider the problem of motion prediction within an autonomous racing setting. such a setting, ability to predict adversaries' behavior is essential for safe and efficient planning. We propose method using memories detect anomalous input incrementally learn model online, quickly adapt unseen behaviors. our experiments, demonstrate effectiveness approach in adapting various data collected F1Tenth-Gym environment, simulator racing. Our experiments show promising results, achieve improvement 14% mean squared error compared without adaptation. future would like extend more extensive evaluation core component act online