Neuromorphic Spiking Ring Attractor for Proprioceptive Joint-State Estimation
Federica Ferrari, Flavia Davidhi, Bernard Maacaron, Alberto Motta, Luuk van Keeken + 4 more
TLDR
This paper presents a neuromorphic spiking ring-attractor network for stable proprioceptive joint-state estimation in robots.
Key contributions
- Introduces a spiking ring-attractor network for stable robot joint angle estimation.
- Employs local excitation, broad inhibition, and velocity-modulated asymmetries for bump translation.
- Demonstrates smooth trajectory tracking, stability near joint limits, and reduced drift.
- Compact, hardware-compatible design with multi-second stability and accurate velocity control.
Why it matters
This paper addresses the challenge of stable proprioceptive estimation in neuromorphic systems under resource constraints. It offers a compact, hardware-compatible spiking ring-attractor network that provides stable and accurate joint-state estimation. This work is crucial for developing more efficient and robust bio-inspired robotic control.
Original Abstract
Maintaining stable internal representations of continuous variables is fundamental for effective robotic control. Continuous attractor networks provide a biologically inspired mechanism for encoding such variables, yet neuromorphic realizations have rarely addressed proprioceptive estimation under resource constraints. This work introduces a spiking ring-attractor network representing a robot joint angle through self-sustaining population activity. Local excitation and broad inhibition support a stable activity bump, while velocity-modulated asymmetries drive its translation and boundary conditions confine motion within mechanical limits. The network reproduces smooth trajectory tracking and remains stable near joint limits, showing reduced drift and improved accuracy compared to unbounded models. Such compact hardware-compatible implementation preserves multi-second stability demonstrating a near-linear relationship between bump velocity and synaptic modulation.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.