Efficient and Robust LiDAR-Based End-to-End Navigation

TL;DR

This paper introduces an efficient LiDAR-based end-to-end navigation system that leverages sparse convolution and uncertainty estimation to improve robustness and performance in autonomous driving.

Contribution

It presents Fast-LiDARNet with optimized sparse convolutions and Hybrid Evidential Fusion for uncertainty-aware control, advancing LiDAR-based autonomous navigation.

Findings

Improved robustness during sensor failures

Reduced need for multiple sampling in uncertainty estimation

Enhanced lane stability and navigation in real-world tests

Abstract

Deep learning has been used to demonstrate end-to-end neural network learning for autonomous vehicle control from raw sensory input. While LiDAR sensors provide reliably accurate information, existing end-to-end driving solutions are mainly based on cameras since processing 3D data requires a large memory footprint and computation cost. On the other hand, increasing the robustness of these systems is also critical; however, even estimating the model's uncertainty is very challenging due to the cost of sampling-based methods. In this paper, we present an efficient and robust LiDAR-based end-to-end navigation framework. We first introduce Fast-LiDARNet that is based on sparse convolution kernel optimization and hardware-aware model design. We then propose Hybrid Evidential Fusion that directly estimates the uncertainty of the prediction from only a single forward pass and then fuses the control predictions intelligently. We evaluate our system on a full-scale vehicle and demonstrate lane-stable as well as navigation capabilities. In the presence of out-of-distribution events (e.g., sensor failures), our system significantly improves robustness and reduces the number of takeovers in the real world.