Enhanced Behavioral Cloning Based self-driving Car Using Transfer Learning

TL;DR

This paper proposes a transfer learning approach using VGG16 architecture for behavioral cloning in self-driving cars, demonstrating improved performance and faster convergence compared to NVIDIA-based models.

Contribution

It introduces a novel transfer learning method with VGG16 architecture for behavioral cloning, outperforming existing NVIDIA models in self-driving car applications.

Findings

VGG16 with transfer learning outperforms NVIDIA architectures.

The proposed model converges faster during training.

Pruned models reduce parameters with minimal performance loss.

Abstract

With the growing phase of artificial intelligence and autonomous learning, the self-driving car is one of the promising area of research and emerging as a center of focus for automobile industries. Behavioral cloning is the process of replicating human behavior via visuomotor policies by means of machine learning algorithms. In recent years, several deep learning-based behavioral cloning approaches have been developed in the context of self-driving cars specifically based on the concept of transfer learning. Concerning the same, the present paper proposes a transfer learning approach using VGG16 architecture, which is fine tuned by retraining the last block while keeping other blocks as non-trainable. The performance of proposed architecture is further compared with existing NVIDIA architecture and its pruned variants (pruned by 22.2% and 33.85% using 1x1 filter to decrease the total number of parameters). Experimental results show that the VGG16 with transfer learning architecture has outperformed other discussed approaches with faster convergence.