少ないほど良い：自動運転の軌道予測のための効率的な脳に着想を得た学習
Less is More: Efficient Brain-Inspired Learning for Autonomous Driving Trajectory Prediction
人間の認知プロセスを模倣した教師-生徒知識蒸留フレームワークとフーリエ適応スパイクニューラルネットワーク（FA-SNN）を導入し、自動運転の軌道予測精度を向上させつつパラメータ数を削減した研究。
著者: Haicheng Liao, Yongkang Li, Zhenning Li, Chengyue Wang, Chunlin Tian, Yuming Huang, Zilin Bian, Kaiqun Zhu, Guofa Li, Ziyuan Pu, Jia Hu, Zhiyong Cui, Chengzhong Xu
分類: cs.AI, cs.RO
原文アブストラクト
Accurately and safely predicting the trajectories of surrounding vehicles is essential for fully realizing autonomous driving (AD). This paper presents the Human-Like Trajectory Prediction model (HLTP++), which emulates human cognitive processes to improve trajectory prediction in AD. HLTP++ incorporates a novel teacher-student knowledge distillation framework. The "teacher" model equipped with an adaptive visual sector, mimics the dynamic allocation of attention human drivers exhibit based on factors like spatial orientation, proximity, and driving speed. On the other hand, the "student" model focuses on real-time interaction and human decision-making, drawing parallels to the human memory storage mechanism. Furthermore, we improve the model's efficiency by introducing a new Fourier Adaptive Spike Neural Network (FA-SNN), allowing for faster and more precise predictions with fewer parameters. Evaluated using the NGSIM, HighD, and MoCAD benchmarks, HLTP++ demonstrates superior performance compared to existing models, which reduces the predicted trajectory error with over 11% on the NGSIM dataset and 25% on the HighD datasets. Moreover, HLTP++ demonstrates strong adaptability in challenging environments with incomplete input data. This marks a significant stride in the journey towards fully AD systems.
