Affordance Learning in Simulation

The affordance framework provides an easily-understandable way for robots to represent and reason about their environment. This project investigates whether or not we can use data collected in a simulator to train robot affordance models, and how humans can interact with those models to give robots manipulation commands.


Affordance Discovery using Simulated Exploration
Adam Allevato, Andrea Thomaz, Mitch Pryor
Extended Abstract, to appear, 2018 International Conference on Autonomous Agents and Multiagent Systems (AAMAS)

Choosing Observation Points for a Camera Robot

We developed an algorithm to select a viewpoint from which to observe a task. This can be useful in a two-robot scenario where one robot is the “cameraman” and the other is the “worker” or “actor.” The camera viewpoint is chosen so as to stay out of the actor’s way, while still providing a good view of the task region.


Getting the Shot: Socially-Aware Viewpoints for Autonomously Observing Tasks
Adam Allevato, Andrew Sharp, Mitch Pryor
Conference Paper, 2017 IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO)
site | PDFbibtex | slides | code

Glovebox Workcell Manufacturing and Integration

In this three-year project, our team at the Nuclear and Applied Robotics Group have deployed robots in various configurations inside nuclear gloveboxes. Developed in conjunction with Los Alamos National Laboratory, we have investigated visual recognition, mixed-waste sorting, and manufacturing tasks such as automated hole drilling with a highly customized robotic system.

This project has resulted in a number of publicly-available ROS packages, many of which are available on our lab’s GitHub pages, which I help run.


Demonstrating Autonomous and Robust Sorting in a Glovebox Environment
Adam Allevato, Matthew Horn, Mitch Pryor
Conference Paper, 2016 American Nuclear Society Decommissioning and Remote Systems (D&RS)

Characterizing Glovebox Automation Tasks using Partially Observable Markov Decision Processes
Adam Allevato, Mitch Pryor
Conference Paper, 2016 American Nuclear Society Decommissioning and Remote Systems (D&RS)

Using a Depth Camera for Object Classification in Nuclear Gloveboxes
Adam Allevato, Thomas Lu, Mitch Pryor
Podium Presentation/Technical Session, 2015 American Nuclear Society Student Conference

3D Computer Vision for Robotics

Using Point Cloud Library and OpenCV, I developed a 3D pose estimation library based on Robot Operating System (ROS). I showed that the library was effective for use in robotic sorting, remote inspection, and small part picking. The library has not (yet) been made public, but only due to lack of demand. If you’re interested, shoot me an email.


An Object Recognition and Pose Estimation Library for Intelligent Industrial Automation
Adam Allevato
Masters’ Thesis, published Spring 2016

Hough Transform Calculator

View site

The Hough Transform is a basic computer vision technique for searching for structure (like lines or circles) in an image.