IROS 2020 — 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Going Cognitive: A Demonstration of the Utility of Task-General Cognitive Architectures for Adaptive Robotic Task Performance

Tyler Frasca* (Tufts), Zhao Han*, Jordan Allspaw, Holly Yanco, and Matthias Scheutz (Tufts)

* Equal contribution; 47% Acceptance rate
After teaching using cognitive architecture, Fetch is asked to describe how to assemble a caddy
After teaching using cognitive architecture, Fetch is asked to describe how to assemble a caddy
News
  • Jun 30, 2020

    Our paper is accepted to the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), a top robotics conference in robotics! This is a collaboration project with Tufts University, the Human-Robot Interaction laboratory.

Abstract

It has been claimed that a main advantage of cognitive architectures (compared to other types of specialized robotic architectures) is that they are task-general and can thus learn to perform any task as long as they have the right perceptual and action primitives.

In this paper, we provide empirical evidence for this claim by directly comparing a high-performing custom robotic architecture developed for the standardized robotic “FetchIt!” challenge task to a hybrid cognitive robotic architecture that allows for online one-shot task learning and task modifications through natural language instructions.

The results show that there is no disadvantage of running the hybrid architecture (i.e., no significant difference in overall performance or computational overhead compared to the custom architecture) while adding the flexibility of online one-shot task instruction and modification not available in the custom architecture.

Figures

iros20 digest
Digest slide

Video

Accompanying video

Video presentation

Video presentation by Tyler Frasca

Leave a comment

Your email address will not be published.