Worcester Polytechnic Institute - RAIL
Loading the player ...
- Offer Profile
- The Robot Autonomy and
Interactive Learning research group at Worcester Polytechnic Institute (WPI)
focuses on the development of interactive robotic and software systems. Our
work aims to provide everyday people with the ability to customize the
functionality of autonomous devices. Our research spans the fields of robot
learning, adjustable autonomy, crowdsourcing, multi-robot teaming and
- The development of robots that work cooperatively with
people is of critical importance for furthering advancements in
manufacturing, medicine, healthcare, military, and consumer applications.
Critical to this goal is the development of technologies that are adaptable
to changing task and user needs.
The Robot Autonomy and Interactive Learning research group at
Worcester Polytechnic Institute (WPI) focuses on the development of
interactive robotic and software systems. Our work aims to provide everyday
people with the ability to customize the functionality of autonomous
devices. Our research spans the fields of robot learning, adjustable
autonomy, crowdsourcing, multi-robot teaming and human-robot interaction.
Robot Learning from Demonstration
- Robot learning from demonstration (LfD) research focuses
on algorithms that enable a robot to learn new task policies from
demonstrations performed by a human teacher. See the Survey of Robot
Learning from Demonstration for more information on this research area. Our
current work includes the first comparative evaluation of leading algorithms
in this area and the development of new multi-strategy learning algorithms:
- Halit Bener Suay and Sonia Chernova. A Comparison of Two Algorithms for
Robot Learning from Demonstration. In the IEEE International Conference on
Systems, Man, and Cybernetics, 2011.
- Halit Bener Suay and Sonia Chernova. Effect of the Human Guidance and
State Space Size on Interactive Reinforcement Learning. In the IEEE
International Symposium on Robot and Human Interactive Communication
RoboCup Autonomous Robot Soccer
- RoboCup is an international competition that aims to
promote AI and robotics research through the development of autonomous
soccer playing robots. WPI competes in the Standard Platform League, which
requires all teams to use the Aldebaran Nao robots. The robots are not
remote controlled in any way; they observe the world through two
head-mounted cameras and use this information to recognize objects in the
environment and their own location on the field. Robots communicate with
each other using the wireless network and use on-board processing to decide
which actions to take. Here is an article describing the event and WPI
Open Source Kinect Interface for Humanoid Robot Contro
- The ROS Nao-OpenNI package provides gesture-based control
for humanoid robots using the Microsoft Kinect sensor. The video shows the
code being used to control an Aldebaran Nao.
The video on top shows the code being used to control an Aldebaran Nao.
- Human-Agent Transfer (HAT) is a policy learning technique
that combines transfer learning, learning from demonstration and
reinforcement learning to achieve rapid learning and high performance in
complex domains. Using this technique we can effectively transfer knowledge
from a human to an agent, even when they have different perceptions of
- Matthew Taylor, Halit Bener Suay and Sonia Chernova. Integrating
Reinforcement Learning with Human Demonstrations of Varying Ability. In the
International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS),
Taipei, Taiwan, 2011.
- Matthew E. Taylor, Halit Bener Suay and Sonia Chernova. Using Human
Demonstrations to Improve Reinforcement Learning. In the AAAI 2011 Spring
Symposium: Help Me Help You: Bridging the Gaps in Human-Agent Collaboration,
Palo Alto, CA, 2011.
Cloud Primer: Leveraging Common Sense Computing for
Early Childhood Literacy
- Providing young children with opportunities to develop
early literacy skills is important to their success in school, their success
in learning to read, and their success in life. This project focuses on the
creation of a new interactive reading primer technology on tablet computers
that will foster early literacy skills and shared parent-child reading
through the use of a targeted discussion-topic suggestion system aimed at
the adult participant. The Cloud Primer will crowdsource the interactions
and discussions of parent-child dyads across a community of readers. It will
then leverage this information in combination with a common sense knowledge
base to develop computational models of the interactions. These models will
then be used to provide context-sensitive discussion topic suggestions to
parents during the shared reading activity with young children.