Motion Prediction Based on Multiple Futures for Dynamic Obstacle Avoidance of Mobile Robots
(2021) 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE) p.475-481- Abstract
- The ability to decide and adjust actions according to motion prediction of dynamic obstacles offers a flexible planning scheme and ampler reaction time to avoid potential impact. Prediction-based collision avoidance implies a two-stage decision-making process from motion prediction to action planning. One of the challenges in motion prediction is the movements of objects are usually non-deterministic and governed by multimodal models. Many studies have been made on motion prediction of dynamic obstacles and action planning for mobile robots separately. The objective of this work is to explore their coherence in terms of multiple future predictions by combining a data-driven motion prediction approach with a model-based control strategy.... (More)
- The ability to decide and adjust actions according to motion prediction of dynamic obstacles offers a flexible planning scheme and ampler reaction time to avoid potential impact. Prediction-based collision avoidance implies a two-stage decision-making process from motion prediction to action planning. One of the challenges in motion prediction is the movements of objects are usually non-deterministic and governed by multimodal models. Many studies have been made on motion prediction of dynamic obstacles and action planning for mobile robots separately. The objective of this work is to explore their coherence in terms of multiple future predictions by combining a data-driven motion prediction approach with a model-based control strategy. More specifically, we integrate motion prediction from deep learning models, Mixture Density Networks (MDNs) with a Non-linear Model Predictive Control (NMPC) framework. The deep learning models produce the multimodal probability distribution of future positions of dynamic obstacles, which is utilized by the MPC controller as a constraint. We show via simulation that the selected model provides valid predictions of motion in a dynamic environment. The prediction result endows the controller with the capability to avoid dynamic obstacles in advance. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/ef63c269-89ec-4388-8480-88d8491cea7c
- author
- Zhang, Ze ; Dean-Leon, Emmanuel ; Karayiannidis, Yiannis LU and Åkesson, Knut
- publishing date
- 2021
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2021 17th IEEE International Conference on Automation Science and Engineering (CASE)
- pages
- 7 pages
- conference name
- 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)
- conference location
- Lyon, France
- conference dates
- 2021-08-23 - 2021-08-27
- external identifiers
-
- scopus:85116962888
- DOI
- 10.1109/CASE49439.2021.9551463
- language
- English
- LU publication?
- no
- id
- ef63c269-89ec-4388-8480-88d8491cea7c
- date added to LUP
- 2022-12-14 15:07:02
- date last changed
- 2024-01-29 22:55:23
@inproceedings{ef63c269-89ec-4388-8480-88d8491cea7c, abstract = {{The ability to decide and adjust actions according to motion prediction of dynamic obstacles offers a flexible planning scheme and ampler reaction time to avoid potential impact. Prediction-based collision avoidance implies a two-stage decision-making process from motion prediction to action planning. One of the challenges in motion prediction is the movements of objects are usually non-deterministic and governed by multimodal models. Many studies have been made on motion prediction of dynamic obstacles and action planning for mobile robots separately. The objective of this work is to explore their coherence in terms of multiple future predictions by combining a data-driven motion prediction approach with a model-based control strategy. More specifically, we integrate motion prediction from deep learning models, Mixture Density Networks (MDNs) with a Non-linear Model Predictive Control (NMPC) framework. The deep learning models produce the multimodal probability distribution of future positions of dynamic obstacles, which is utilized by the MPC controller as a constraint. We show via simulation that the selected model provides valid predictions of motion in a dynamic environment. The prediction result endows the controller with the capability to avoid dynamic obstacles in advance.}}, author = {{Zhang, Ze and Dean-Leon, Emmanuel and Karayiannidis, Yiannis and Åkesson, Knut}}, booktitle = {{2021 17th IEEE International Conference on Automation Science and Engineering (CASE)}}, language = {{eng}}, pages = {{475--481}}, title = {{Motion Prediction Based on Multiple Futures for Dynamic Obstacle Avoidance of Mobile Robots}}, url = {{http://dx.doi.org/10.1109/CASE49439.2021.9551463}}, doi = {{10.1109/CASE49439.2021.9551463}}, year = {{2021}}, }