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

We consider the problem of optimal unsignalized intersection management forcontinual streams of randomly arriving robots. This problem involves repeatedlysolving different instances of a mixed integer program, for which thecomputation time using a naive optimization algorithm scales exponentially withthe number of robots and lanes. Hence, such an approach is not suitable forreal-time implementation. In this paper, we propose a solution framework thatcombines learning and sequential optimization. In particular, we propose analgorithm for learning a shared policy that given the traffic stateinformation, determines the crossing order of the robots. Then, we optimize thetrajectories of the robots sequentially according to that crossing order. Thisapproach inherently guarantees safety at all times. We validate the performanceof this approach using extensive simulations. Our approach, on average,significantly outperforms the heuristics from the literature. We also showthrough simulations that the computation time for our approach scales linearlywith the number of robots. We further implement the learnt policies on physicalrobots with a few modifications to the solution framework to address real-worldchallenges and establish its real-time implementability.

Reinforcement Learning Aided Sequential Optimization for Unsignalized Intersection Management of Robot Traffic