Spiking neural control aligns robot joints with circular motion geometry
A Spiking Ring-Attractor Architecture for Representation and Control of Revolute Robot Joints
RoboticsNeural and Evolutionary Computing
Summary
Robot joints that rotate like wheels move in circles, but most control systems treat these movements like straight lines, which can be less natural and efficient. The authors propose a new way to control joints using spiking neural networks that represent joint positions as activity patterns on a ring, matching the joints' circular nature. This method allows the robot to better track and control its joint angles by naturally moving an activity bump around the ring, similar to how a dial rotates. They tested this approach in simulations and on a real robot arm, showing it can accurately generate joint movements that respect the circular geometry.
What this means in practice
- •For robotics engineers: Design control systems for robot joints that exploit their circular motion for smoother and more accurate movement.
- •For embedded systems developers: Create neuromorphic controllers that use spiking neural networks for energy-efficient real-time joint control in robots.
Authors
Aung Htet, Alejandro Rodriguez Jimenez, Ruidong Ma, Alessandro Di Nuovo
Abstract
Robotic systems with revolute joints evolve on circular state spaces, yet most control architectures represent these states using Euclidean variables that ignore this underlying geometry. We propose a fully spiking neural control architecture in which ring attractors encode joint states, enforcing representations consistent with the topology of revolute systems. Homeostatic regulation computes goal-state mismatch directly over these distributed representations, and opponent gain-modulated populations convert this mismatch into controlled phase shifts of the activity bump, implementing set-point regulation as motion on the ring. We show that the bump dynamics follow an SO(2) geometry, and that gain asymmetries induce a signed phase velocity on the ring. To interface distributed activity with scalar regulation signals, we derive an analytic Fourier phase decoder and implement its signed components using push-pull spiking populations. For multi-joint systems, we demonstrate that local ring-based Fourier features compose into product representations that linearly decode SO(3) orientations through forward kinematics. Experiments in NEST validate the full SO(2) regulation mechanism and the spiking product-feature decoder for lift, pitch, and yaw. Robot experiments on a Tiago arm show that decoded ring dynamics generate joint velocity commands, producing directed motion with joint-dependent accuracy. Together, these results establish a neuromorphic control framework in which representation, regulation, and action are unified within a ring-attractor substrate aligned with the geometry of revolute systems.