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

We address the important problem of generalizing robotic rearrangement toclutter without any explicit object models. We first generate over 650Kcluttered scenes - orders of magnitude more than prior work - in diverseeveryday environments, such as cabinets and shelves. We render syntheticpartial point clouds from this data and use it to train our CabiNet modelarchitecture. CabiNet is a collision model that accepts object and scene pointclouds, captured from a single-view depth observation, and predicts collisionsfor SE(3) object poses in the scene. Our representation has a fast inferencespeed of 7 microseconds per query with nearly 20% higher performance thanbaseline approaches in challenging environments. We use this collision model inconjunction with a Model Predictive Path Integral (MPPI) planner to generatecollision-free trajectories for picking and placing in clutter. CabiNet alsopredicts waypoints, computed from the scene's signed distance field (SDF), thatallows the robot to navigate tight spaces during rearrangement. This improvesrearrangement performance by nearly 35% compared to baselines. Wesystematically evaluate our approach, procedurally generate simulatedexperiments, and demonstrate that our approach directly transfers to the realworld, despite training exclusively in simulation. Robot experiment demos incompletely unknown scenes and objects can be found at this httphttps://cabinet-object-rearrangement.github.io

CabiNet: Scaling Neural Collision Detection for Object Rearrangement with Procedural Scene Generation