BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171530Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241204T145600
DTEND;TZID=Asia/Tokyo:20241204T150800
UID:siggraphasia_SIGGRAPH Asia 2024_sess120_papers_739@linklings.com
SUMMARY:PC-Planner: Physics-Constrained Self-Supervised Learning for Robus
 t Neural Motion Planning with Shape-Aware Distance Function
DESCRIPTION:Xujie Shen, Haocheng Peng, and Zesong Yang (State Key Laborato
 ry of CAD&CG, Zhejiang University); Juzhan Xu (Shenzhen University (SZU));
  Hujun Bao (State Key Laboratory of CAD&CG, Zhejiang University); Ruizhen 
 Hu (Shenzhen University (SZU)); and Zhaopeng Cui (State Key Laboratory of 
 CAD&CG, Zhejiang University)\n\nMotion Planning (MP) is a critical challen
 ge in robotics, especially pertinent with the burgeoning interest in embod
 ied artificial intelligence. Traditional MP methods often struggle with hi
 gh-dimensional complexities. Recently neural motion planners, particularly
  physics-informed neural planners based on the Eikonal equation, have been
  proposed to overcome the curse of dimensionality. However, these methods 
 perform poorly in complex scenarios with shaped robots due to multiple sol
 utions inherent in the Eikonal equation. %local minima of their solutions.
  To address these issues, this paper presents \pcplanner, a novel physics-
 constrained self-supervised learning framework for robot motion planning w
 ith various shapes in complex environments. To this end, we propose severa
 l physical constraints, including monotonic and optimal constraints, to st
 abilize the training process of the neural network with the Eikonal equati
 on. Additionally, we introduce a novel shape-aware distance field that con
 siders the robot's shape for efficient collision checking and Ground Truth
  (GT) speed computation. This field reduces the computational intensity, a
 nd facilitates adaptive motion planning at test time. Experiments in diver
 se scenarios with different robots demonstrate the superiority of the prop
 osed method in efficiency and robustness for robot motion planning, partic
 ularly in complex environments.\n\nRegistration Category: Full Access, Ful
 l Access Supporter\n\nLanguage Format: English Language\n\nSession Chair: 
 Hao (Richard) Zhang (Simon Fraser University, Augmenta)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_739&sess=sess120
END:VEVENT
END:VCALENDAR