ロボットの模倣学習における長系列タスクへのTransformer-XLの応用
Transformer-XL for Long Sequence Tasks in Robotic Learning from Demonstration
RGB-D・LiDAR・触覚などのマルチモーダル入力をTransformer-XLで統合し、長期的依存を含む模倣学習タスクの成功率と効率を改善した。
著者: Gao Tianci
分類: cs.RO
原文アブストラクト
This paper presents an innovative application of Transformer-XL for long sequence tasks in robotic learning from demonstrations (LfD). The proposed framework effectively integrates multi-modal sensor inputs, including RGB-D images, LiDAR, and tactile sensors, to construct a comprehensive feature vector. By leveraging the advanced capabilities of Transformer-XL, particularly its attention mechanism and position encoding, our approach can handle the inherent complexities and long-term dependencies of multi-modal sensory data. The results of an extensive empirical evaluation demonstrate significant improvements in task success rates, accuracy, and computational efficiency compared to conventional methods such as Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs). The findings indicate that the Transformer-XL-based framework not only enhances the robot's perception and decision-making abilities but also provides a robust foundation for future advancements in robotic learning from demonstrations.