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 tackle the Online 3D Bin Packing Problem, a challenging yet practicallyuseful variant of the classical Bin Packing Problem. In this problem, the itemsare delivered to the agent without informing the full sequence information.Agent must directly pack these items into the target bin stably withoutchanging their arrival order, and no further adjustment is permitted. Online3D-BPP can be naturally formulated as Markov Decision Process (MDP). We adoptdeep reinforcement learning, in particular, the on-policy actor-criticframework, to solve this MDP with constrained action space. To learn apractically feasible packing policy, we propose three critical designs. First,we propose an online analysis of packing stability based on a novel stackingtree. It attains a high analysis accuracy while reducing the computationalcomplexity from $O(N^2)$ to $O(N \log N)$, making it especially suited for RLtraining. Second, we propose a decoupled packing policy learning for differentdimensions of placement which enables high-resolution spatial discretizationand hence high packing precision. Third, we introduce a reward function thatdictates the robot to place items in a far-to-near order and thereforesimplifies the collision avoidance in movement planning of the robotic arm.Furthermore, we provide a comprehensive discussion on several key implementalissues. The extensive evaluation demonstrates that our learned policyoutperforms the state-of-the-art methods significantly and is practicallyusable for real-world applications.

Learning Practically Feasible Policies for Online 3D Bin Packing