Regularized deep signed distance fields for reactive motion generation
Liu, Puze ; Zhang, Kuo ; Tateo, Davide LU
; Jauhri, Snehal
; Peters, Jan
and Chalvatzaki, Georgia
(2022)
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
In IEEE International Conference on Intelligent Robots and Systems
2022-October.
p.6673-6680
- Abstract
Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces. A key component for allowing robots to leave structured lab and manufacturing settings is their ability to evaluate online and real-time collisions with the world around them. Distance-based constraints are fundamental for enabling robots to plan their actions and act safely, protecting both humans and their hardware. However, different applications require different distance resolutions, leading to various heuristic approaches for measuring distance fields w.r.t. obstacles, which are computationally expensive and hinder their application in dynamic obstacle avoidance use-cases. We propose Regularized Deep Signed Distance... (More)
Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces. A key component for allowing robots to leave structured lab and manufacturing settings is their ability to evaluate online and real-time collisions with the world around them. Distance-based constraints are fundamental for enabling robots to plan their actions and act safely, protecting both humans and their hardware. However, different applications require different distance resolutions, leading to various heuristic approaches for measuring distance fields w.r.t. obstacles, which are computationally expensive and hinder their application in dynamic obstacle avoidance use-cases. We propose Regularized Deep Signed Distance Fields (ReDSDF), a single neural implicit function that can compute smooth distance fields at any scale, with fine-grained resolution over high-dimensional manifolds and articulated bodies like humans, thanks to our effective data generation and a simple inductive bias during training. We demonstrate the effectiveness of our approach in representative simulated tasks for whole-body control (WBC) and safe Human- Robot Interaction (HRI) in shared workspaces. Finally, we provide proof of concept of a real-world application in a HRI handover task with a mobile manipulator robot.
(Less)
- author
- Liu, Puze
; Zhang, Kuo
; Tateo, Davide
LU
; Jauhri, Snehal
; Peters, Jan
and Chalvatzaki, Georgia
- publishing date
- 2022
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
- series title
- IEEE International Conference on Intelligent Robots and Systems
- volume
- 2022-October
- pages
- 8 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022
- conference location
- Kyoto, Japan
- conference dates
- 2022-10-23 - 2022-10-27
- external identifiers
-
- scopus:85138308312
- ISSN
- 2153-0866
- 2153-0858
- ISBN
- 9781665479271
- DOI
- 10.1109/IROS47612.2022.9981456
- language
- English
- LU publication?
- no
- id
- 062656f8-23b0-492a-96b3-14e5bd3b79d0
- date added to LUP
- 2025-10-16 14:33:11
- date last changed
- 2025-12-12 09:01:01
@inproceedings{062656f8-23b0-492a-96b3-14e5bd3b79d0,
abstract = {{<p>Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces. A key component for allowing robots to leave structured lab and manufacturing settings is their ability to evaluate online and real-time collisions with the world around them. Distance-based constraints are fundamental for enabling robots to plan their actions and act safely, protecting both humans and their hardware. However, different applications require different distance resolutions, leading to various heuristic approaches for measuring distance fields w.r.t. obstacles, which are computationally expensive and hinder their application in dynamic obstacle avoidance use-cases. We propose Regularized Deep Signed Distance Fields (ReDSDF), a single neural implicit function that can compute smooth distance fields at any scale, with fine-grained resolution over high-dimensional manifolds and articulated bodies like humans, thanks to our effective data generation and a simple inductive bias during training. We demonstrate the effectiveness of our approach in representative simulated tasks for whole-body control (WBC) and safe Human- Robot Interaction (HRI) in shared workspaces. Finally, we provide proof of concept of a real-world application in a HRI handover task with a mobile manipulator robot.</p>}},
author = {{Liu, Puze and Zhang, Kuo and Tateo, Davide and Jauhri, Snehal and Peters, Jan and Chalvatzaki, Georgia}},
booktitle = {{2022 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022}},
isbn = {{9781665479271}},
issn = {{2153-0866}},
language = {{eng}},
pages = {{6673--6680}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE International Conference on Intelligent Robots and Systems}},
title = {{Regularized deep signed distance fields for reactive motion generation}},
url = {{http://dx.doi.org/10.1109/IROS47612.2022.9981456}},
doi = {{10.1109/IROS47612.2022.9981456}},
volume = {{2022-October}},
year = {{2022}},
}