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

The process of designing costmaps for off-road driving tasks is often achallenging and engineering-intensive task. Recent work in costmap design foroff-road driving focuses on training deep neural networks to predict costmapsfrom sensory observations using corpora of expert driving data. However, suchapproaches are generally subject to over-confident mispredictions and arerarely evaluated in-the-loop on physical hardware. We present an inversereinforcement learning-based method of efficiently training deep cost functionsthat are uncertainty-aware. We do so by leveraging recent advances in highlyparallel model-predictive control and robotic risk estimation. In addition todemonstrating improvement at reproducing expert trajectories, we also evaluatethe efficacy of these methods in challenging off-road navigation scenarios. Weobserve that our method significantly outperforms a geometric baseline,resulting in 44% improvement in expert path reconstruction and 57% fewerinterventions in practice. We also observe that varying the risk tolerance ofthe vehicle results in qualitatively different navigation behaviors, especiallywith respect to higher-risk scenarios such as slopes and tall grass.

Learning Risk-Aware Costmaps via Inverse Reinforcement Learning for Off-Road Navigation