English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Uncertainty in control and perception poses challenges for autonomous vehiclenavigation in unstructured environments, leading to navigation failures andpotential vehicle damage. This paper introduces a framework that minimizescontrol and perception uncertainty to ensure safe and reliable navigation. Theframework consists of two uncertainty-aware models: a learning-based vehicledynamics model and a self-supervised traversability estimation model. We traina vehicle dynamics model that can quantify the epistemic uncertainty of themodel to perform active exploration, resulting in the efficient collection oftraining data and effective avoidance of uncertain state-action spaces. Inaddition, we employ meta-learning to train a traversability cost predictionnetwork. The model can be trained with driving data from a variety of types ofterrain, and it can online-adapt based on interaction experiences to reduce thealeatoric uncertainty. Integrating the dynamics model and traversability costprediction model with a sampling-based model predictive controller allows foroptimizing trajectories that avoid uncertain terrains and state-action spaces.Experimental results demonstrate that the proposed method reduces uncertaintyin prediction and improves stability in autonomous vehicle navigation inunstructured environments.

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