Detrive: Imitation Learning with Transformer Detection for End-to-End Autonomous Driving

TL;DR

Detrive introduces a transformer-based end-to-end autonomous driving model that enhances perception and obstacle avoidance by integrating detection, feature fusion, and imitation learning, demonstrating superior performance in simulation benchmarks.

Contribution

The paper presents a novel transformer-based perception module and an imitation learning framework for end-to-end autonomous driving, improving obstacle detection and dynamic obstacle avoidance.

Findings

Transformer detector improves obstacle detection accuracy.

Model outperforms traditional models in dynamic obstacle avoidance.

Reinforcement learning enhances training data quality.

Abstract

This Paper proposes a novel Transformer-based end-to-end autonomous driving model named Detrive. This model solves the problem that the past end-to-end models cannot detect the position and size of traffic participants. Detrive uses an end-to-end transformer based detection model as its perception module; a multi-layer perceptron as its feature fusion network; a recurrent neural network with gate recurrent unit for path planning; and two controllers for the vehicle's forward speed and turning angle. The model is trained with an on-line imitation learning method. In order to obtain a better training set, a reinforcement learning agent that can directly obtain a ground truth bird's-eye view map from the Carla simulator as a perceptual output, is used as teacher for the imitation learning. The trained model is tested on the Carla's autonomous driving benchmark. The results show that the Transformer detector based end-to-end model has obvious advantages in dynamic obstacle avoidance compared with the traditional classifier based end-to-end model.