Computer Engineering Commons^™

Sabr: Development Of A Neuromorphic Balancing Robot, Alec Yen, Yaw Mensah, Mark Dean

EURēCA: Exhibition of Undergraduate Research and Creative Achievement

We discuss the development of a self-adjusted balancing robot (SABR) using a neuromorphic computing framework for control. Implementations of two-wheeled balancing robots have been achieved using traditional algorithms, often in the form of proportional-integral-derivative (PID) control. We aim to achieve the same task using a neuromorphic architecture, which offers potential for higher power efficiency than conventional processing techniques. We utilize evolutionary optimization (EO) and the second iteration of Dynamic Adaptive Neural Network Arrays (DANNA2) developed by the Laboratory of Tennesseans Exploring Neural Networks (TENNLab). For the purpose of comparison, a traditional balancing robot was first designed using PID control; the …

Identification Of Emergent Collaborative Behaviors In Multi-Agent Systems, Bryson Howell

EURēCA: Exhibition of Undergraduate Research and Creative Achievement

Identification of Emergent Collaborative Behaviors in Multi-Agent Systems

Bryson Howell

Multi-Agent Reinforcement Learning (MARL) has been used to allow groups of autonomous agents to perform complex cooperative tasks. When MARL methods such as the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm [1] are used to train teams of agents in cooperative tasks, it has been observed that the actions of individual agents are significantly influenced by the actions of their teammates [2]. Additionally, prior work has shown that teams of agents trained independently of one another under identical conditions display a variety of behaviors [3]. Since these teams have been …

The Comparison Of Verbalized Feedback In Human To Computer Interfacing Versus Human To Human Interaction, Kea Francis

EURēCA: Exhibition of Undergraduate Research and Creative Achievement

The project evaluates response to social robots for purposeful tasks. The study uses a social robot, Rapiro, along with a smartphone that serves as a visual interface for the robot system. My role was to design a program on a Raspberry Pi that allows simultaneous control of Rapiro’s actions and a response from a phone application. The phone app is downloaded to an Android phone and designed using MIT App Inventor software. This allows pre-programmed and real-time control of the robot. The user inputs what they want the robot to say through the terminal of the Raspberry Pi. Through serial …