This paper investigates spiking neural networks (SNN) for novel robotic controllers with the aim of improving accuracy in trajectory tracking. By emulating the operation of the human brain through the incorporation of temporal coding mechanisms, SNN offer greater adaptability and efficiency in information processing, providing significant advantages in the representation of temporal information in robotic arm control compared to conventional neural networks. Exploring specific implementations of SNN in robot control, this study analyzes neuron models and learning mechanisms inherent to SNN. Based on the principles of the Neural Engineering Framework (NEF), a novel spiking PID controller is designed and simulated for a 3-DoF robotic arm using Nengo and MATLAB R2022b. The controller demonstrated good accuracy and efficiency in following designated trajectories, showing minimal deviations, overshoots, or oscillations. A thorough quantitative assessment, utilizing performance metrics like root mean square error (RMSE) and the integral of the absolute value of the time-weighted error (ITAE), provides additional validation for the efficacy of the SNN-based controller. Competitive performance was observed, surpassing a fuzzy controller by 5% in terms of the ITAE index and a conventional PID controller by 6% in the ITAE index and 30% in RMSE performance. This work highlights the utility of NEF and SNN in developing effective robotic controllers, laying the groundwork for future research focused on SNN adaptability in dynamic environments and advanced robotic applications. 1660 sensors Sensors (Basel, Switzerland) Sensors (Basel) Multidisciplinary Digital Publishing Institute (MDPI) PMC10819625 10819625 10819625 38257584 10.3390/s24020491 A Novel Robotic Controller Using Neural Engineering Framework-Based Spiking Neural Networks Marrero Dailin Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization 1 Kern John Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Supervision, Project administration, Funding acquisition 1 * Urrea Claudio Conceptualization, Supervision, Project administration, Funding acquisition 1 Galan Daniel Academic Editor 1 Suarez Fernandez Ramon A Academic Editor 1 Badesa Francisco Javier Academic Editor 1 1 Electrical Engineering Department, Faculty of Engineering, University of Santiago of Chile (USACH), Av. By emulating the operation of the human brain through the incorporation of temporal coding mechanisms, SNN offer greater adaptability and efficiency in information processing, providing significant advantages in the representation of temporal information in robotic arm control compared to conventional neural networks. Exploring specific implementations of SNN in robot control, this study analyzes neuron models and learning mechanisms inherent to SNN. Based on the principles of the Neural Engineering Framework (NEF), a novel spiking PID controller is designed and simulated for a 3-DoF robotic arm using Nengo and MATLAB R2022b. SNN Fundamentals In neural connections, each neuron connects with around 10,000 others, processes information continuously, and consumes minimal energy in comparison to the millions of existing neurons. It self-organizes and reconfigures over time. Replicating this behavior in an artificial system presents a highly complex endeavor. This complexity persists even when employing simplifications that only capture a fraction of the biological richness. Over time, models and algorithms have been developed to, in some way, attempt to mimic this neuronal behavior. These developments have evolved in conjunction with advancements in computing resources and neuroscience discoveries. The generated spike travels through the axon to other neurons. Figure 1 Biological neurons and synapses. ( a ) Structure and components of neurons. ( b ) Schematic diagram of a synapse [ 34 ]. Action potentials arriving at axon terminals initiate the release of neurotransmitters into the synaptic cleft, binding to receptors on the postsynaptic neuron’s membrane and altering its potential. Neurotransmitters can have excitatory or inhibitory effects, facilitating information transmission. This neuronal connection, known as a synapse, is a fundamental and intricate element of neural function. This phenomenon is illustrated in Figure 1 b. Neural Engineering Framework The Neural Engineering Framework (NEF) is a comprehensive methodology for developing large-scale, biologically plausible cognitive models [ 50 ]. It ensures a globally optimal approximation of dynamic equations, balancing high-level abstraction with preservation of fundamental behavioral aspects. Unlike frameworks for learning from input–output data, the NEF constructs a spiking neural network with a known transform through an optimization procedure [ 51 ]. The NEF translates neural activity into a vector space representation, implementing ordinary differential equations (ODE) [ 52 ]. The principle of representation outlines how the NEF represents information using patterns of neuronal The ANFIS, being an adaptive neuro-fuzzy inference system, proves to be more adept at modeling and adapting to the specific nonlinearities of the system. 6. Conclusions Spiking neural networks (SNN) play a significant role in advancing robotics, particularly in systems with higher degrees of freedom and industrial applications, showcasing a high potential to enhance autonomy and adaptability in dynamic environments. The utilization of the Neural Engineering Framework (NEF) and Nengo provides a powerful, robust, and adaptable approach for SNN-based controllers, as demonstrated by the implementation of a novel spiking Proportional–Integral–Derivative (PID) controller for a robotic arm.