Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems

Moritz B. Milde; Alexander Dietmuller; Hermann Blum; Giacomo Indiveri; Yulia Sandamirskaya

Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems

Moritz B. Milde, Alexander Dietmuller, Hermann Blum, Giacomo Indiveri, Yulia Sandamirskaya

Western Sydney University

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

9 Citations (Scopus)

Abstract

Event based sensors and neural processing architectures represent a promising technology for implementing low power and low latency robotic control systems. However, the implementation of robust and reliable control architectures using neuromorphic devices is challenging, due to their limited precision and variable nature of their underlying computing elements. In this paper we demonstrate robust obstacle avoidance and target acquisition behaviors in a compact mobile platform controlled by a neuromorphic sensory-processing system and validate its performance in a number of robotic experiments.

Original language	English
Title of host publication	From Dreams to Innovation: Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS 2017), 28-31 May 2017, Baltimore, Maryland, USA
Publisher	IEEE
Number of pages	4
ISBN (Print)	9781467368520
Publication status	Published - 2017
Event	IEEE International Symposium on Circuits and Systems - Duration: 28 May 2017 → …

Conference

Conference	IEEE International Symposium on Circuits and Systems
Period	28/05/17 → …

Keywords

robotics
target acquisition
neural networks (computer science)
obstacle avoidance

Cite this

@inproceedings{3de5353bdc334b99ab740fae8fd1163e,

title = "Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems",

abstract = "Event based sensors and neural processing architectures represent a promising technology for implementing low power and low latency robotic control systems. However, the implementation of robust and reliable control architectures using neuromorphic devices is challenging, due to their limited precision and variable nature of their underlying computing elements. In this paper we demonstrate robust obstacle avoidance and target acquisition behaviors in a compact mobile platform controlled by a neuromorphic sensory-processing system and validate its performance in a number of robotic experiments.",

keywords = "robotics, target acquisition, neural networks (computer science), obstacle avoidance",

author = "Milde, {Moritz B.} and Alexander Dietmuller and Hermann Blum and Giacomo Indiveri and Yulia Sandamirskaya",

year = "2017",

language = "English",

isbn = "9781467368520",

booktitle = "From Dreams to Innovation: Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS 2017), 28-31 May 2017, Baltimore, Maryland, USA",

publisher = "IEEE",

note = "IEEE International Symposium on Circuits and Systems ; Conference date: 28-05-2017",

}

Milde, MB, Dietmuller, A, Blum, H, Indiveri, G & Sandamirskaya, Y 2017, Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems. in From Dreams to Innovation: Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS 2017), 28-31 May 2017, Baltimore, Maryland, USA. IEEE, IEEE International Symposium on Circuits and Systems, 28/05/17.

Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems. / Milde, Moritz B.; Dietmuller, Alexander; Blum, Hermann et al.
From Dreams to Innovation: Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS 2017), 28-31 May 2017, Baltimore, Maryland, USA. IEEE, 2017.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems

AU - Milde, Moritz B.

AU - Dietmuller, Alexander

AU - Blum, Hermann

AU - Indiveri, Giacomo

AU - Sandamirskaya, Yulia

PY - 2017

Y1 - 2017

N2 - Event based sensors and neural processing architectures represent a promising technology for implementing low power and low latency robotic control systems. However, the implementation of robust and reliable control architectures using neuromorphic devices is challenging, due to their limited precision and variable nature of their underlying computing elements. In this paper we demonstrate robust obstacle avoidance and target acquisition behaviors in a compact mobile platform controlled by a neuromorphic sensory-processing system and validate its performance in a number of robotic experiments.

AB - Event based sensors and neural processing architectures represent a promising technology for implementing low power and low latency robotic control systems. However, the implementation of robust and reliable control architectures using neuromorphic devices is challenging, due to their limited precision and variable nature of their underlying computing elements. In this paper we demonstrate robust obstacle avoidance and target acquisition behaviors in a compact mobile platform controlled by a neuromorphic sensory-processing system and validate its performance in a number of robotic experiments.

KW - robotics

KW - target acquisition

KW - neural networks (computer science)

KW - obstacle avoidance

UR - https://hdl.handle.net/1959.7/uws:53028

UR - https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8050984

M3 - Conference Paper

SN - 9781467368520

BT - From Dreams to Innovation: Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS 2017), 28-31 May 2017, Baltimore, Maryland, USA

PB - IEEE

T2 - IEEE International Symposium on Circuits and Systems

Y2 - 28 May 2017

ER -

Obstacle avoidance and target acquisition in mobile robots equipped with neuromorphic sensory-processing systems

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this