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

In target tracking with mobile multi-sensor systems, sensor deploymentimpacts the observation capabilities and the resulting state estimationquality. Based on a partially observable Markov decision process (POMDP)formulation comprised of the observable sensor dynamics, unobservable targetstates, and accompanying observation laws, we present a distributedinformation-driven solution approach to the multi-agent target trackingproblem, namely, sequential multi-agent nominal belief-state optimization(SMA-NBO). SMA-NBO seeks to minimize the expected tracking error via recedinghorizon control including a heuristic expected cost-to-go (HECTG). SMA-NBOincorporates a computationally efficient approximation of the targetbelief-state over the horizon. The agent-by-agent decision-making is capable ofleveraging on-board (edge) compute for selecting (sub-optimal) target-trackingmaneuvers exhibiting non-myopic cooperative fleet behavior. The optimizationproblem explicitly incorporates semantic information defining target occlusionsfrom a world model. To illustrate the efficacy of our approach, a randomocclusion forest environment is simulated. SMA-NBO is compared to otherbaseline approaches. The simulation results show SMA-NBO 1) maintains trackingperformance and reduces the computational cost by replacing the calculation ofthe expected target trajectory with a single sample trajectory based on maximuma posteriori estimation; 2) generates cooperative fleet decision bysequentially optimizing single-agent policy with efficient usage of otheragents' policy of intent; 3) aptly incorporates the multiple weighted tracepenalty (MWTP) HECTG, which improves tracking performance with acomputationally efficient heuristic.

SMA-NBO: A Sequential Multi-Agent Planning with Nominal Belief-State Optimization in Target Tracking