SlipNet: Enhancing Slip Cost Mapping for Autonomous Navigation on Heterogeneous and Deformable Terrains

TL;DR

SlipNet is a novel deep learning approach that predicts wheel slip in diverse terrains, improving autonomous rover navigation without prior terrain classification, validated through high-fidelity simulations.

Contribution

Introduces SlipNet, a new slip prediction model using dynamic segmentation and slip assignment, trained on synthetic data for better navigation in uncertain terrains.

Findings

SlipNet outperforms TerrainNet in MAE across five terrains.

Synthetic datasets effectively train slip prediction models.

Dynamic segmentation enhances slip prediction accuracy.

Abstract

Autonomous space rovers face significant challenges when navigating deformable and heterogeneous terrains due to variability in soil properties, which can lead to severe wheel slip, compromising navigation efficiency and increasing the risk of entrapment. To address this problem, we introduce SlipNet, a novel approach for predicting wheel slip in segmented regions of diverse terrain surfaces without relying on prior terrain classification. SlipNet employs dynamic terrain segmentation and slip assignment techniques on previously unseen data, enhancing rover navigation capabilities in uncertain environments. We developed a synthetic data generation framework using the high-fidelity Vortex Studio simulator to create realistic datasets that replicate a wide range of deformable terrain conditions for training and evaluation. Extensive simulation results demonstrate that our model, combining DeepLab v3+ with SlipNet, significantly outperforms the state-of-the-art TerrainNet method, achieving lower mean absolute error (MAE) across five distinct terrain samples. These findings highlight the effectiveness of SlipNet in improving rover navigation in challenging terrains.