2D LiDAR Map Prediction via Estimating Motion Flow with GRU

TL;DR

This paper introduces LiDAR-FlowNet, a recurrent neural network that estimates motion flow from 2D LiDAR maps to predict future maps, aiding robotics navigation without requiring manual annotations.

Contribution

The paper presents a novel deep neural network architecture, LiDAR-FlowNet, and a self-supervised training strategy for predicting future LiDAR maps using motion flow estimation.

Findings

LiDAR-FlowNet effectively estimates motion flow between LiDAR maps.

The self-supervised training strategy eliminates the need for manual annotations.

Predicted LiDAR maps demonstrate improved accuracy over baseline methods.

Abstract

It is a significant problem to predict the 2D LiDAR map at next moment for robotics navigation and path-planning. To tackle this problem, we resort to the motion flow between adjacent maps, as motion flow is a powerful tool to process and analyze the dynamic data, which is named optical flow in video processing. However, unlike video, which contains abundant visual features in each frame, a 2D LiDAR map lacks distinctive local features. To alleviate this challenge, we propose to estimate the motion flow based on deep neural networks inspired by its powerful representation learning ability in estimating the optical flow of the video. To this end, we design a recurrent neural network based on gated recurrent unit, which is named LiDAR-FlowNet. As a recurrent neural network can encode the temporal dynamic information, our LiDAR-FlowNet can estimate motion flow between the current map and the unknown next map only from the current frame and previous frames. A self-supervised strategy is further designed to train the LiDAR-FlowNet model effectively, while no training data need to be manually annotated. With the estimated motion flow, it is straightforward to predict the 2D LiDAR map at the next moment. Experimental results verify the effectiveness of our LiDAR-FlowNet as well as the proposed training strategy. The results of the predicted LiDAR map also show the advantages of our motion flow based method.