Data Efficient Human Intention Prediction: Leveraging Neural Network Verification and Expert Guidance
This work addresses the problem of data scarcity and noise in human motion data for intention prediction, which is critical for safe and efficient human-robot collaboration, but it appears incremental as it builds on existing training methods with a novel augmentation approach.
The paper tackles the challenge of building data-driven models for human intention prediction in human-robot collaboration by proposing an iterative adversarial data augmentation framework that leverages neural network verification and expert guidance to learn from insufficient training data, achieving more robust and accurate prediction performance compared to existing methods.
Predicting human intention is critical to facilitating safe and efficient human-robot collaboration (HRC). However, it is challenging to build data-driven models for human intention prediction. One major challenge is due to the diversity and noise in human motion data. It is expensive to collect a massive motion dataset that comprehensively covers all possible scenarios, which leads to the scarcity of human motion data in certain scenarios, and therefore, causes difficulties in constructing robust and reliable intention predictors. To address the challenge, this paper proposes an iterative adversarial data augmentation (IADA) framework to learn neural network models from an insufficient amount of training data. The method uses neural network verification to identify the most "confusing" input samples and leverages expert guidance to safely and iteratively augment the training data with these samples. The proposed framework is applied to collected human datasets. The experiments demonstrate that our method can achieve more robust and accurate prediction performance compared to existing training methods.