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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Recent advances in computational perception have significantly improved theability of autonomous robots to perform state estimation with low entropy. Suchadvances motivate a reconsideration of robot decision-making under uncertainty.Current approaches to solving sequential decision-making problems model statesas inhabiting the extremes of the perceptual entropy spectrum. As such, thesemethods are either incapable of overcoming perceptual errors or asymptoticallyinefficient in solving problems with low perceptual entropy. With low entropyperception in mind, we aim to explore a happier medium that balancescomputational efficiency with the forms of uncertainty we now observe frommodern robot perception. We propose an approach for efficient task planning forgoal-directed robot reasoning. Our approach combines belief spacerepresentation with the fast, goal-directed features of classical planning toefficiently plan for low entropy goal-directed reasoning tasks. We compare ourapproach with current classical planning and belief space planning approachesby solving low entropy goal-directed grocery packing tasks in simulation. Ourapproach outperforms these approaches in planning time, execution time, andtask success rate in our simulation experiments. We also demonstrate ourapproach on a real world grocery packing task with physical robot.

Elephants Don’t Pack Groceries: Robot Task Planning for Low Entropy Belief States