BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163648Z
LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T133000
DTEND;TZID=Australia/Melbourne:20231215T134500
UID:siggraphasia_SIGGRAPH Asia 2023_sess157_papers_419@linklings.com
SUMMARY:Neural Packing: from Visual Sensing to Reinforcement Learning
DESCRIPTION:Juzhan Xu (Shenzhen University), Minglun Gong (University of G
 uelph), Hao Zhang (Simon Fraser University), and Hui Huang and Ruizhen Hu 
 (Shenzhen University)\n\nWe present a novel learning framework to solve th
 e transport-and-packing (TAP) problem in 3D. It constitutes a full solutio
 n pipeline from partial observations of input objects via RGBD sensing and
  recognition to final box placement, via robotic motion planning, to arriv
 e at a compact packing in a target container. The technical core of our me
 thod is a neural network for TAP, trained via reinforcement learning (RL),
  to solve the NP-hard combinatorial optimization problem. Our network simu
 ltaneously selects an object to pack and determines the final packing loca
 tion, based on a judicious encoding of the continuously evolving states of
  partially observed source objects and available spaces in the target cont
 ainer, using separate encoders both enabled with attention mechanisms. The
  encoded feature vectors are employed to compute the matching scores and f
 easibility masks of different pairings of box selection and available spac
 e configuration for packing strategy optimization. Extensive experiments, 
 including ablation studies and physical packing execution by a real robot 
 (Universal Robot UR5e), are conducted to evaluate our method in terms of i
 ts design choices, scalability, generalizability, and comparisons to basel
 ines, including the most recent RL-based TAP solution. We also contribute 
 the first benchmark for TAP which covers a variety of input settings and d
 ifficulty levels.\n\nRegistration Category: Full Access\n\nSession Chair: 
 Chi Wing Fu (The Chinese University of Hong Kong)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_419&sess=sess157
END:VEVENT
END:VCALENDAR