December 27th, 2013

Robots: Teams and Tasks

In today’s episode, Per Sjöborg speaks with Lynne Parker from the University of Tennessee about her work with robot teams. Her lab is developing techniques to get robots to team up to complete tasks that they individually could not. The robots share data from sensors to extend their perception or share capabilities to perform particular tasks. This approach is essential to increase the efficiency, potential and reliability of multi-robot systems.

The Distributed Intelligence Laboratory robots

The Distributed Intelligence Laboratory robots

Ideally, multi-robot systems should be able to cope with different types of robots joining or leaving the team, and tasks changing over time. While most approaches would require a roboticist to manually predefine how the robot team accomplishes its task, Parker automates this process using smart algorithms and software architectures. This makes the design of multi-robot systems more manageable in the long run since one framework can be used in different situations.

Dr. Parker also works on integrating humans in the robot teams. This allows implicit communication between the robot and the human coworker to reduce the workload on the human and make the interaction more efficient.

In the long term, she hopes her research in multi-robot systems will enable applications in security, surveillance, and reconnaissance; planetary exploration; search and rescue; cleanup of hazardous waste; mining; construction; automated manufacturing; industrial/household maintenance; and nuclear power plant decommissioning.

 
Lynne Parker
Lynne E. Parker is Professor and Associate Head in the Department of Electrical Engineering and Computer Science at The University of Tennessee-Knoxville (UTK). At UTK, she is the founder and director of the Distributed Intelligence Laboratory, which performs research in multi-robot systems, sensor networks, machine learning, and human-robot interaction.

Parker is a leading international researcher in the field of distributed multi-robot systems. She has published over 135 articles in the areas of mobile robot cooperation, human-robot cooperation, sensor networks, robotic learning, intelligent agent architectures, and robot navigation. These publications include five edited books on the topic of distributed robotics.

She is the Editor-in-Chief of the IEEE Robotics Automation Society’s Conference Editorial Board, Senior Editor of IEEE Transactions on Robotics, Associate Editor of IEEE Intelligent Systems Magazine and an Associate Editor of the Swarm Intelligence journal. She serves on numerous international conference program committees. She is also an elected member of the Administrative Committee of the IEEE Robotics and Automation Society.

Links:

| More

December 13th, 2013

Robots: The DARPA Robotics Challenge

In this episode, Sabine Hauert interviews Paul Oh, the Director of the Drexel Autonomous Systems Lab at Drexel University. His team, spanning 10 universities, is competing in the DARPA Robotics Challenge (DRC) with the HUBO humanoid made by KAIST in South Korea. The goal of the challenge is to design robots capable of assisting humans in responding to natural and man-made disasters. Trials will take place next week in Florida from December 20-21 and will require robots to drive a vehicle, walk over rough terrain, clear debris, open doors, use a hand tool to break through a wall, climb a ladder, turn a valve, and finally drag a hose and connect it to pipes. The 7 HUBO robots on Oh’s team will be competing against sixteen other teams from around the world to determine which teams continues on to the DRC Finals in 2014 with continued DARPA funding. Competing in the 2014 Finals will lead to one team winning a $2 million prize.

The video below shows Oh’s vision for robot-enabled disaster response in 2020. You can find more videos of the HUBO working on tasks for the trials here.

Paul Oh
Paul Oh is a Full Professor at Drexel’s Mechanical Engineering Department, Affiliated Faculty in the ECE Department, and Director of the Drexel Autonomous Systems Lab (DASL). He received mechanical engineering degrees from McGill (B.Eng 1989), Seoul National (M.Sc 1992), and Columbia (PhD 1999). Honors include faculty fellowships at NASA Jet Propulsion Lab (2002), Naval Research Lab (2003), the NSF CAREER award (2004), the SAE Ralph Teetor Award for Engineering Education Excellence (2005) and being named a Boeing Welliver Fellow (2006). He is also the Founding Chair of the IEEE Technical Committee on Aerial Robotics and UAVs. From 2008-2010, he served at the National Science Foundation (NSF) as the Program Director managing the robotics research portfolio. Paul Oh was named ASME Fellow in 2011.
Links:

| More

Related episodes:

November 29th, 2013

Robots: Working with EOD Personnel

In this episode, AJung Moon talks to Julie Carpenter, a recent graduate of the University of Washington who interviewed 23 U.S. Military Explosive Ordnance Disposal personnel to find out how they interact with everyday field robots. Julie is currently writing a book on the topic that is scheduled to be published next year.

Julie Carpenter

Julie Carpenter has received her doctoral degree in Education at the University of Washington with her dissertation titled The Quiet Professional: An investigation of U.S. Military Explosive Ordnance Disposal personnel interactions with everyday field robots. She primarily studies emotional attachment issues in human-robot interaction, and how it affects user decision-making in collaborative, sometimes stressful, situations.

Find out more about Julie and her work on her website.

Holiday Robots
Like last year, we ask you to submit videos or audio related to robotics and the holidays! Content can be fictional, scientific or business oriented. We’ll be posting the material on our dedicated YouTube channel. To submit material, simply go to www.robotspodcast.com/christmas or send us your material by email to christmas@robotspodcast.com. To get in the spirit, check out the videos from previous years via the link above or on our YouTube channel. Some of these videos gathered millions of views!

Links:

| More

Related episodes:

November 15th, 2013

Robots: From the Greenhouse to the Fields

In this episode, Ron Vanderkley speaks with David Dorhout from Iowa State University about his Agricultural Robots that include Prospero the robot farmer and Aquarius the greenhouse watering robot.

Today’s agricultural equipment has been designed around a single farmer sitting on large machinery. This method has its drawbacks since farming decisions have to be made at the level of the field. Nature instead is chaotic and dynamic, soil nutrients and moisture change from foot to foot. A swarm of small robots like Prospero would have the ability to farm inch by inch, examining the soil before planting each seed and choosing the best variety for that spot. Ideally, this would maximize the productivity of each acre, allow less land to be converted to farm land, and ultimately feed more people.

Prospero is the working prototype of an Autonomous Micro Planter (AMP) that uses a combination of swarm and game theory to plant seeds at safe distances from one another.

Dorhout’s second agricultural robot Aquarius is a greenhouse robot that autonomously waters plants using its 30 gallon tank. The robot is programed using taping on the ground of the greenhouse.

David Dorhout
David Dorhout is a graduate of Iowa State University. He has always been interested in robotics and has 14 years of experience in the agriculture and biotech industry doing field and greenhouse discovery work. He is the founder of Dorhout R&D LLC which is a research and development business designing and building novel robotic systems and interactive consumer electronic devices.

Links:

| More

Related episodes:

November 1st, 2013

Robots: Blue River Technology

In this episode Sabine Hauert speaks with Jorge Heraud, CEO of California-based startup Blue River Technology which brings together computer vision and robotics to automate agriculture. Their first robot LettuceBot targets the state’s #1 vegetable crop. Its task is to thin rows of lettuce in fields. This involves selectively removing some of the plants by spraying excess fertilizer on them, thereby avoiding overcrowding while fertilizing nearby plants. The tractor-mounted robot is already being rented out to farms across the state.

Heraud tells us about the challenges in robot vision and the rapid growth of Blue River Technology. He shares his hopes to apply their technology to other agriculture tasks and crops with different vision challenges. Finally he explains how this technology will transform the classical workforce on farms.

Jorge Heraud
Jorge Heraud is CEO of Blue River Technology. Before co-founding the company with Lee Redden, a fellow graduate student at Stanford University, Heraud worked in precision agriculture as Director of Business Development at Trimble Navigation. At Stanford he completed an MBA at the Graduate School of Business.

Links:

| More

Related episodes: