Vision-based Autonomous Driving for Unstructured Environments Using Imitation Learning

TL;DR

This paper presents a vision-based imitation learning approach for autonomous driving in unstructured environments, enabling vehicles to reactively avoid obstacles using only occupancy grid maps, thus handling complex and noisy situations effectively.

Contribution

The study introduces a novel imitation learning method that trains a neural network to drive using vision-based occupancy grids, bypassing the need for path planning and precise localization in unstructured environments.

Findings

The proposed method effectively handles complex, noisy driving scenarios.

Experiments show improved obstacle avoidance compared to model-based methods.

The approach demonstrates successful real-world parking lot navigation.

Abstract

Unstructured environments are difficult for autonomous driving. This is because various unknown obstacles are lied in drivable space without lanes, and its width and curvature change widely. In such complex environments, searching for a path in real-time is difficult. Also, inaccurate localization data reduce the path tracking accuracy, increasing the risk of collision. Instead of searching and tracking the path, an alternative approach has been proposed that reactively avoids obstacles in real-time. Some methods are available for tracking global path while avoiding obstacles using the candidate paths and the artificial potential field. However, these methods require heuristics to find specific parameters for handling various complex environments. In addition, it is difficult to track the global path accurately in practice because of inaccurate localization data. If the drivable space is not accurately recognized (i.e., noisy state), the vehicle may not smoothly drive or may collide with obstacles. In this study, a method in which the vehicle drives toward drivable space only using a vision-based occupancy grid map is proposed. The proposed method uses imitation learning, where a deep neural network is trained with expert driving data. The network can learn driving patterns suited for various complex and noisy situations because these situations are contained in the training data. Experiments with a vehicle in actual parking lots demonstrated the limitations of general model-based methods and the effectiveness of the proposed imitation learning method.