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

Model-based control is a popular paradigm for robot navigation because it canleverage a known dynamics model to efficiently plan robust robot trajectories.However, it is challenging to use model-based methods in settings where theenvironment is a priori unknown and can only be observed partially throughon-board sensors on the robot. In this work, we address this short-coming bycoupling model-based control with learning-based perception. The learning-basedperception module produces a series of waypoints that guide the robot to thegoal via a collision-free path. These waypoints are used by a model-basedplanner to generate a smooth and dynamically feasible trajectory that isexecuted on the physical system using feedback control. Our experiments insimulated real-world cluttered environments and on an actual ground vehicledemonstrate that the proposed approach can reach goal locations more reliablyand efficiently in novel environments as compared to purely geometricmapping-based or end-to-end learning-based alternatives. Our approach does notrely on detailed explicit 3D maps of the environment, works well with low framerates, and generalizes well from simulation to the real world. Videosdescribing our approach and experiments are available on the project website.

Combining Optimal Control and Learning for Visual Navigation in Novel Environments