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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In our previous work, we designed a systematic policy to prioritize samplinglocations to lead significant accuracy improvement in spatial interpolation byusing the prediction uncertainty of Gaussian Process Regression (GPR) as"attraction force" to deployed robots in path planning. Although theintegration with Traveling Salesman Problem (TSP) solvers was also shown toproduce relatively short travel distance, we here hypothesise several factorsthat could decrease the overall prediction precision as well becausesub-optimal locations may eventually be included in their paths. To addressthis issue, in this paper, we first explore "local planning" approachesadopting various spatial ranges within which next sampling locations areprioritized to investigate their effects on the prediction performance as wellas incurred travel distance. Also, Reinforcement Learning (RL)-based high-levelcontrollers are trained to adaptively produce blended plans from a particularset of local planners to inherit unique strengths from that selection dependingon latest prediction states. Our experiments on use cases of temperaturemonitoring robots demonstrate that the dynamic mixtures of planners can notonly generate sophisticated, informative plans that a single planner could notcreate alone but also ensure significantly reduced travel distances at no costof prediction reliability without any assist of additional modules for shortestpath calculation.

Adaptive Selection of Informative Path Planning Strategies via Reinforcement Learning