Guangzhi Tang

PhD Candidate

I’m Guangzhi Tang, a PhD candidate in computer science at Rutgers University and a member of the Computational Brain Lab (ComBra). My main research interests are neuromorphic computing and robotics. I have developed Spiking Neural Networks (SNN) solving a wide spectrum of robotic problems on neuromorphic processor with robustness, efficiency, and adaptivity.

We think the most crucial task for neuromorphic computing is to build the bridge between robotics and brain. Robotics can provide real-world interactions and intelligent applications as testbeds for brain modeling, and the brain can inspire robust and efficient solutions for robotic problems. By using SNN, we believe questions of both areas can be answered simultaneously.

Research

Spiking DDPG for robot navigation

Spiking-DDPG trains an SNN for energy-efficient mapless navigation on Intel’s Loihi neuromorphic processor.

Neuromorphic 1D SLAM

Brain-inspired SNN solves the 1D SLAM problem of mobile robot using Intel’s Loihi neuromorphic processor.

Publications

G Tang, N Kumar, R Yoo, KP Michmizos. Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control. In CoRL, 2020.

PDF Code

G Tang, N Kumar, KP Michmizos. Reinforcement co-Learning of Deep and Spiking Neural Networks for Energy-Efficient Mapless Navigation with Neuromorphic Hardware. In IROS, 2020.

PDF Code Project

I Polykretis, G Tang, KP Michmizos. An Astrocyte-Modulated Neuromorphic Central Pattern Generator for Hexapod Robot Locomotion on Intel’s Loihi. In ICONS, 2020.

PDF

G Tang, KP Michmizos. Real-time Mapping on a Neuromorphic Processor. In NICE, 2020.

PDF

G Tang, A Shah, KP Michmizos. Spiking Neural Network on Neuromorphic Hardware for Energy-Efficient Unidimensional SLAM. In IROS, 2019.

PDF Project

G Tang, IE Polykretis, VA Ivanov, A Shah, KP Michmizos. Introducing Astrocytes on a Neuromorphic Processor: Synchronization, Local Plasticity and Edge of Chaos. In NICE, 2019.

PDF Code Video

G Tang, KP Michmizos. Gridbot: An autonomous robot controlling by a spiking neural network mimicking the brain's navigational system. In ICONS, 2018.

PDF Poster

G Tang, KP Michmizos. Gridbot: A Spiking Neural Network Model of the Brain’s Navigation System for Autonomous Robots. In NICE, 2018.

PDF Poster Video

G Tang, KP Michmizos. NeuRobotics: A Spiking Neural Network Model of the Brain’s Spatial Navigation System for Autonomous Robots. In CCN, 2017.

PDF Poster

G Tang, KP Michmizos. Gridbot: Spike-Based Head Direction Cells Employing Bayesian Inference. In NICE, 2017.

PDF Poster