Neuromorphic Electronic Artist for Robotic Painting Advances Robotics Capabilities

Researchers at the University of Zurich, in collaboration with the Swiss Federal Institute of Technology Zurich, have made a significant breakthrough in robotics with the development of a neuromorphic electronic artist for robotic painting. This innovative system uses neuromorphic cameras and mixed-signal neuromorphic processors to capture dynamic brushstrokes and produce diverse physical brushstrokes. The system's ability to adapt to real-time feedback and adjust its trajectory on the fly marks a significant step towards a fully spiking robotic controller with ultra-low latency responsiveness.

Key Takeaways:

• The neuromorphic electronic artist for robotic painting system uses neuromorphic cameras and mixed-signal neuromorphic processors to capture dynamic brushstrokes and produce diverse physical brushstrokes.
• The system's ability to adapt to real-time feedback and adjust its trajectory on the fly is a significant step towards a fully spiking robotic controller with ultra-low latency responsiveness.
• The system's performance was tested in a real-world setting, with successful generation of diverse physical brushstrokes.
• The researchers used a 6-DOF robotic arm, event-based input from a Dynamic Vision Sensor (DVS) camera, and a neuromorphic processor to produce dynamic brushstrokes and tactile feedback from a force-torque sensor to compensate for brush deformation.
• The system receives DVS events representing the desired brushstroke trajectory and maps these events onto the processor's neurons to compute joint velocities in close-loop.
• The variability in the input's noisy event streams and the processor's analog circuits reproduces the heterogeneity of human brushstrokes.
• The system's neural network is a first step towards a fully spiking robotic controller with ultra-low latency responsiveness, applicable to any robotic task requiring real-time closed-loop adaptive control.

Statistics:

• 6-DOF robotic arm used in the system
• Dynamic Vision Sensor (DVS) camera used to capture event-based input
• Neuromorphic processor used to produce dynamic brushstrokes
• Force-torque sensor used to compensate for brush deformation
• 15(1):19561 as the article number in Scientific Reports
• 1 real-world setting tested for system performance
• 101,000+ articles published in Scientific Reports (as of 2025)
• 52,000+ articles published in Nature (as of 2025)

Sources:

• A neuromorphic electronic artist for robotic painting ( Scientific Reports, 2025;15(1):19561 )
• NewsRx. University of Zurich Reports Findings in Robotics (A neuromorphic electronic artist for robotic painting). Journal of Engineering. June 16, 2025; p 4016.