A Spiking Neural Architecture for Coordinating Arm and Locomotor Control

2026-06-09

AI Summary

This work addresses the common limitation in existing spiking neural network (SNN)-based approaches to humanoid robot control, which typically treat bipedal locomotion and arm movements in isolation, lacking integrated coordination. The authors propose a unified SNN control architecture that combines the Neural Engineering Framework (NEF) with the Semantic Pointer Architecture (SPA), augmented by a biologically plausible basal ganglia model to enable high-level action selection and behavioral switching. For the first time, this system integrates full-body bipedal walking with force-based arm control on a full-scale humanoid platform. Validated through co-simulation using Nengo and Isaac Sim, the approach successfully demonstrates goal-directed grasping, continuous digit drawing, path following, and flexible transitions between tasks, confirming its efficacy and deployability in complex, real-world scenarios.

Abstract

Spiking Neural Networks (SNNs) coupled with neuromorphic hardware offer energy-efficient solutions for humanoid robot control. However, existing SNN-based motor control systems address bipedal locomotion and arm control in isolation, leaving integrated control of both unaddressed. We present a spiking architecture that coordinates force-based arm control and bipedal locomotion in a simulated humanoid, using the Neural Engineering Framework (NEF) and Semantic Pointer Architecture (SPA). High-level action selection between locomotor and arm control is mediated by a biologically grounded spiking basal ganglia model. We validate the system through co-simulation of Nengo, for the neural control, and Isaac Sim, demonstrating successful target reaching, continuous digit drawing, path-following locomotion, and finally, switching between walking and arm control via basal ganglia disinhibition. To our knowledge, this is the first integrated spiking controller to combine bipedal locomotion and arm control on a full-scale humanoid platform. The full spike-based implementation enables future deployment on low-power neuromorphic hardware.

Problem

• Spiking Neural Networks
• bipedal locomotion
• arm control
• integrated motor control
• humanoid robot

Innovation

• Spiking Neural Networks
• Neuromorphic Control
• Integrated Motor Control
• Basal Ganglia Model
• Humanoid Robotics