Safe and efficient path planning under uncertainty via deep collision probability fields
Herrmann, Felix ; Zach, Sebastian ; Banfi, Jacopo ; Peters, Jan ; Chalvatzaki, Georgia and Tateo, Davide LU
(2024)
In IEEE Robotics and Automation Letters
9(11).
p.9327-9334
- Abstract
Estimating collision probabilities between robots and environmental obstacles or other moving agents is crucial to ensure safety during path planning. This is an important building block of modern planning algorithms in many application scenarios such as autonomous driving, where noisy sensors perceive obstacles. While many approaches exist, they either provide too conservative estimates of the collision probabilities or are computationally intensive due to their sampling-based nature. To deal with these issues, we introduce Deep Collision Probability Fields, a neural-based approach for computing collision probabilities of arbitrary objects with arbitrary unimodal uncertainty distributions. Our approach relegates the computationally... (More)
Estimating collision probabilities between robots and environmental obstacles or other moving agents is crucial to ensure safety during path planning. This is an important building block of modern planning algorithms in many application scenarios such as autonomous driving, where noisy sensors perceive obstacles. While many approaches exist, they either provide too conservative estimates of the collision probabilities or are computationally intensive due to their sampling-based nature. To deal with these issues, we introduce Deep Collision Probability Fields, a neural-based approach for computing collision probabilities of arbitrary objects with arbitrary unimodal uncertainty distributions. Our approach relegates the computationally intensive estimation of collision probabilities via sampling at the training step, allowing for fast neural network inference of the constraints during planning. In extensive experiments, we show that Deep Collision Probability Fields can produce reasonably accurate collision probabilities (up to 10^-3) for planning and that our approach can be easily plugged into standard path planning approaches to plan safe paths on 2-D maps containing uncertain static and dynamic obstacles.
(Less)
- author
- Herrmann, Felix
; Zach, Sebastian
; Banfi, Jacopo
; Peters, Jan
; Chalvatzaki, Georgia
and Tateo, Davide
LU
- publishing date
- 2024
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Collision avoidance, Deep learning methods, Planning under uncertainty, Robot safety
- in
- IEEE Robotics and Automation Letters
- volume
- 9
- issue
- 11
- pages
- 8 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- external identifiers
-
- scopus:85204200977
- ISSN
- 2377-3766
- DOI
- 10.1109/LRA.2024.3457208
- language
- English
- LU publication?
- no
- id
- c1c15100-61ba-415b-8cb0-6e6e77905b9c
- date added to LUP
- 2025-10-16 14:04:31
- date last changed
- 2025-11-03 16:17:54
@article{c1c15100-61ba-415b-8cb0-6e6e77905b9c,
abstract = {{<p>Estimating collision probabilities between robots and environmental obstacles or other moving agents is crucial to ensure safety during path planning. This is an important building block of modern planning algorithms in many application scenarios such as autonomous driving, where noisy sensors perceive obstacles. While many approaches exist, they either provide too conservative estimates of the collision probabilities or are computationally intensive due to their sampling-based nature. To deal with these issues, we introduce Deep Collision Probability Fields, a neural-based approach for computing collision probabilities of arbitrary objects with arbitrary unimodal uncertainty distributions. Our approach relegates the computationally intensive estimation of collision probabilities via sampling at the training step, allowing for fast neural network inference of the constraints during planning. In extensive experiments, we show that Deep Collision Probability Fields can produce reasonably accurate collision probabilities (up to 10^-3) for planning and that our approach can be easily plugged into standard path planning approaches to plan safe paths on 2-D maps containing uncertain static and dynamic obstacles.</p>}},
author = {{Herrmann, Felix and Zach, Sebastian and Banfi, Jacopo and Peters, Jan and Chalvatzaki, Georgia and Tateo, Davide}},
issn = {{2377-3766}},
keywords = {{Collision avoidance; Deep learning methods; Planning under uncertainty; Robot safety}},
language = {{eng}},
number = {{11}},
pages = {{9327--9334}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
series = {{IEEE Robotics and Automation Letters}},
title = {{Safe and efficient path planning under uncertainty via deep collision probability fields}},
url = {{http://dx.doi.org/10.1109/LRA.2024.3457208}},
doi = {{10.1109/LRA.2024.3457208}},
volume = {{9}},
year = {{2024}},
}