Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception

TL;DR

This paper presents a framework for autonomous vehicle navigation in unstructured environments that minimizes control and perception uncertainties, combining learning-based models and meta-learning for improved safety and reliability.

Contribution

It introduces a novel uncertainty-aware navigation framework using a dynamics model and traversability estimation with meta-learning, enhancing safety in unstructured terrains.

Findings

Reduces prediction uncertainty in navigation tasks

Improves stability and safety in unstructured environments

Enables online adaptation to diverse terrains

Abstract

Uncertainty in control and perception poses challenges for autonomous vehicle navigation in unstructured environments, leading to navigation failures and potential vehicle damage. This paper introduces a framework that minimizes control and perception uncertainty to ensure safe and reliable navigation. The framework consists of two uncertainty-aware models: a learning-based vehicle dynamics model and a self-supervised traversability estimation model. We train a vehicle dynamics model that can quantify the epistemic uncertainty of the model to perform active exploration, resulting in the efficient collection of training data and effective avoidance of uncertain state-action spaces. In addition, we employ meta-learning to train a traversability cost prediction network. The model can be trained with driving data from a variety of types of terrain, and it can online-adapt based on interaction experiences to reduce the aleatoric uncertainty. Integrating the dynamics model and traversability cost prediction model with a sampling-based model predictive controller allows for optimizing trajectories that avoid uncertain terrains and state-action spaces. Experimental results demonstrate that the proposed method reduces uncertainty in prediction and improves stability in autonomous vehicle navigation in unstructured environments.