Event-based PID controller fully realized in neuromorphic hardware: a one DoF study

Sie sind hier: Homepage > Suche

Event-based PID controller fully realized in neuromorphic hardware: a one DoF study

Freier Zugriff

Stagsted, R K / Vitale, A / Renner, A / Larsen, L B / Christensen, A L / Sandamirskaya, Yulia

Spiking Neuronal Networks (SNNs) realized inneuromorphic hardware lead to low-power and low-latency neuronal computing architectures. Neuromorphic computing systems are most efficient when all of perception, decision making, and motor control are seamlessly integrated into a single neuronal architecture that can be realized on the neuromorphic hardware. Many neuronal network architectures address the perception tasks, while work on neuronal motor controllers is scarce. Here, we present an improved implementation of a neuromorphic PID controller. The controller was realized on Intel’s neuromorphic research chip Loihi and its performance tested on a drone, constrained to rotate on a single axis. The SNN controller is built using neuronal populations, in which a single spike carries information about sensed and control signals. Neuronal arrays perform computation on such sparse representations to calculate the proportional, derivative, and integral terms. The SNN PID controller is compared to a PID controller, implemented in software, and achieves a comparable performance, paving the way to a fully neuromorphic systemin which perception, planning, and control are realized in a non-chip SNN.

Zugriff

Download

Exportieren, teilen und zitieren

Dokumentinformationen

Titel :

Event-based PID controller fully realized in neuromorphic hardware: a one DoF study

Beteiligte:

Stagsted, R K (Autor:in) / Vitale, A (Autor:in) / Renner, A (Autor:in) / Larsen, L B (Autor:in) / Christensen, A L (Autor:in) / Sandamirskaya, Yulia (Autor:in)

Erscheinungsdatum :

2020-10-29

Anmerkungen:

Stagsted, R K; Vitale, A; Renner, A; Larsen, L B; Christensen, A L; Sandamirskaya, Yulia (2020). Event-based PID controller fully realized in neuromorphic hardware: a one DoF study. In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, 25 October 2020 - 29 October 2020, IEEE.

DOI :

https://doi.org/10.5167/uzh-200414 , https://doi.org/10.1109/IROS45743.2020.9340861

Medientyp :

Aufsatz (Konferenz)

Format :

Elektronische Ressource

Sprache :

Englisch

Schlagwörter :

Institute of Neuroinformatics , 570 Life sciences , biology

Klassifikation :

DDC: