neurorobotics

The Spiking Reservoir (Liquid State Machine - LSM) Simulator

A neurorobot is a robot controlled by a computer simulation of a biological brain. At Backyard Brains we use neurorobots to teach neuroscience in schools.

Dynamic Time Warping in Python / C (using ctypes)

Neuro-Cybernetic Protocol: versioned canonical-JSON contract connecting neural simulators and neuromorphic controllers to robots, UAVs and analysis clients over Zenoh. Rust reference, independent TypeScript validator, Python/C/C++ bindings. v0.8.0 is the latest release; HEAD is a release-blocked 1.0 candidate.

Processing chain in ROS-Neuro to determine when the logarithmic bandpower of the EEG signal crosses a given threshold.

Analysis of data collected during a 3-day Motor Imagery (MI) Brain-Computer Interface (BCI) experiment involving 8 healthy participants.

Positioning control on a collaborative robot by sensor fusion with liquid state machines

Deep reinforcement learning for controlling Myorobotics muscles in the Neurorobotics Platform

Evaluation and Generalization of Capsule Networks in Neurorobotics

Evaluates the robustness of capsule networks in regard to novel viewpoints, occlusion and more

Visual Navigation with Plexus Robots

Testing different Reinforcement Learning strategies inspired by hippocampal replay for robotic navigation

PushBot experiments in the Neurorobotics Platform

An Experiment for the Neurorobotics Platform that can be used to create sensor data for training in object recognition.

Sepehr Mahmoudian — AI/ML engineer in Berlin. Agentic systems, continual learning, knowledge graphs & RAG; roots in computational neuroscience, information theory, neurorobotics & 3D vision. Rust + Python.