• Sorted by Date • Classified by Publication Type • Classified by Topic • Sorted by First Author Last Name •
Sai Kiran Narayanaswami, Mauricio Tec, Ishan Durugkar, Siddharth Desai, Bharath Masetty, Sanmit Narvekar, and Peter Stone. Towards a Real-Time, Low-Resource, End-to-end Object Detection Pipeline for Robot Soccer. In Amy Eguchi, Nuno Lau, Maike Paetzel-Prussman, and Thanapat Wanichanon, editors, RoboCup 2022: Robot World Cup XXV, pp. 62–74, Springer International Publishing, 2023.
The book
This work presents a study for building a Deep Vision pipeline suitable for the Robocup Standard Platform League, a humanoid robot soccer tournament. Specifically, we focus on end-to-end trainable object detection for effective perception using Aldebaran NAO v6 robots. The implementation of such a detector poses two major challenges, those of speed, and resource-effectiveness with respect to memory and computational power. We benchmark architectures using the YOLO and SSD detection paradigms, and identify variants that are able to achieve good detection performance for ball detection, while being able to perform rapid inference. To add to the training data for these networks, we also create a dataset from logs collected by the UT Austin Villa team during previous competitions, and set up an annotation pipeline for training. We utilize the above results and training pipeline to realize a practical, multi-class object detector that enables the robot's vision system to run at 35 Hz while maintaining good detection performance.
@InCollection{RoboCup2022-nskiran,
author = {Sai Kiran Narayanaswami and Mauricio Tec and Ishan Durugkar and Siddharth Desai and Bharath Masetty and Sanmit Narvekar and Peter Stone},
title = {Towards a Real-Time, Low-Resource, End-to-end Object Detection Pipeline for Robot Soccer},
editor="Amy Eguchi and Nuno Lau and Maike Paetzel-Prussman and Thanapat Wanichanon",
booktitle="{R}obo{C}up 2022: Robot World Cup {XXV}",
year="2023",
publisher="Springer International Publishing",
pages="62--74",
abstract = {This work presents a study for building a Deep Vision pipeline
suitable for the Robocup Standard Platform League, a humanoid robot
soccer tournament. Specifically, we focus on end-to-end trainable
object detection for effective perception using Aldebaran NAO v6 robots.
The implementation of such a detector poses two major challenges,
those of speed, and resource-effectiveness with respect to memory and computational power. We benchmark architectures
using the YOLO and SSD detection paradigms, and identify variants
that are able to achieve good detection performance for ball
detection, while being able to perform rapid inference. To add to
the training data for these networks, we also create a dataset from
logs collected by the UT Austin Villa team during previous competitions,
and set up an annotation pipeline for training.
We utilize the above results and training pipeline to realize a
practical, multi-class object detector that enables the robot's vision system to
run at 35 Hz while maintaining good detection performance.
},
wwwnote={<a href="https://link.springer.com/book/10.1007/978-3-031-28469-4">The book</a>},
}
Generated by bib2html.pl (written by Patrick Riley ) on Sun Nov 24, 2024 20:30:02