Learning Vehicle Dynamics from Cropped Image Patches for Robot Navigation in Unpaved Outdoor Terrains

TL;DR

This paper introduces Crop-LSTM, a method that uses cropped image patches to improve local feature extraction for predicting robot trajectories, enabling safer navigation in unpaved outdoor terrains.

Contribution

The paper presents Crop-LSTM, a novel approach that iteratively focuses on local image patches for better trajectory prediction in outdoor robot navigation.

Findings

Crop-LSTM improves trajectory prediction accuracy.

The method enables safe navigation in challenging terrains.

Successful demonstration on a wheeled robot platform.

Abstract

In the realm of autonomous mobile robots, safe navigation through unpaved outdoor environments remains a challenging task. Due to the high-dimensional nature of sensor data, extracting relevant information becomes a complex problem, which hinders adequate perception and path planning. Previous works have shown promising performances in extracting global features from full-sized images. However, they often face challenges in capturing essential local information. In this paper, we propose Crop-LSTM, which iteratively takes cropped image patches around the current robot's position and predicts the future position, orientation, and bumpiness. Our method performs local feature extraction by paying attention to corresponding image patches along the predicted robot trajectory in the 2D image plane. This enables more accurate predictions of the robot's future trajectory. With our wheeled mobile robot platform Raicart, we demonstrated the effectiveness of Crop-LSTM for point-goal navigation in an unpaved outdoor environment. Our method enabled safe and robust navigation using RGBD images in challenging unpaved outdoor terrains. The summary video is available at https://youtu.be/iIGNZ8ignk0.