Development of Occupancy Prediction Algorithm for Underground Parking Lots

TL;DR

This paper presents a novel occupancy prediction algorithm for underground parking lots using a Transformer-based neural network within a simulated environment, aiming to improve autonomous vehicle perception in challenging basement conditions.

Contribution

It introduces a Transformer-based occupancy network trained on a new underground parking dataset, enhancing perception accuracy in dimly lit, adverse environments.

Findings

High accuracy in occupancy prediction in basement scenarios

Effective use of simulated data for training and validation

Improved perception performance in underground parking environments

Abstract

The core objective of this study is to address the perception challenges faced by autonomous driving in adverse environments like basements. Initially, this paper commences with data collection in an underground garage. A simulated underground garage model is established within the CARLA simulation environment, and SemanticKITTI format occupancy ground truth data is collected in this simulated setting. Subsequently, the study integrates a Transformer-based Occupancy Network model to complete the occupancy grid prediction task within this scenario. A comprehensive BEV perception framework is designed to enhance the accuracy of neural network models in dimly lit, challenging autonomous driving environments. Finally, experiments validate the accuracy of the proposed solution's perception performance in basement scenarios. The proposed solution is tested on our self-constructed underground garage dataset, SUSTech-COE-ParkingLot, yielding satisfactory results.