Archive for the ‘Podcast’ Category

January 28th, 2011

Robots: Odor Source Localization

In this episode we revisit robot olfaction and take a closer look at the problem of odor source localization. Our first guest, Hiroshi Ishida from the Tokyo University of Agriculture and Technology is an expert in the field, whose sniffing robots range from blimps to ground and underwater robots. Our second guest, Thomas Lochmatter from EPFL talks about tradeoffs between biologically inspired and probabilistic approaches to navigate a gas plume.

Hiroshi Ishida

Hiroshi Ishida is Associate Professor in the Department of Mechanical Systems Engineering, Tokyo University of Agriculture and Technology, Japan.
The focus of his research group is to develop robots that can find sources of airborne gas plumes or underwater chemical plumes. To this end, they developed the Active Stereo Nose (see figure below), a differential gas sampling system inspired by the dog’s nose, and the Crayfish robot that mimics the mechanism used by crayfish in nature to create unidirectional water currents.

Thomas Lochmatter

image credit: SNF

During his PhD at the Distributed Intelligent Systems and Algorithms Lab at EPFL in Switzerland, Thomas Lochmatter developed a modular odor system for the Khepera III robot. His research focused on the pros and cons of biologically-inspired and probabilistic algorithms for odor localization, while dealing with both single and multi-robot systems.


| More

Related episodes:

November 5th, 2010

Robots: Autonomous Vehicles

In today’s episode we take a deeper look at what’s behind the hype over autonomous vehicles, and talk to two experts in the field, Alberto Broggi, leader of the Vislab Intercontinental Vehicle Challenge, and Raul Rojas, leader of the Made in Germany autonomous vehicle project.

Alberto Broggi

Alberto BroggiAlberto Broggi is the Director of the Artificial Vision and Intelligent Systems Lab at the University of Parma.

His main milestones are the ARGO Project (a 2000+ km test done on Italian highways back in 1998 in which the ARGO vehicle drove itself autonomously) and the setup of the Terramax vehicle who reached the finish line of the DARPA Grand Challenge 2005. The Vislab Intercontinental Vehicle Challenge was accomplished when the vehicle expedition recently reached Shanghai on October 28th after crossing two continents in a journey more than 3 months long.

Raúl Rojas

Raúl Rojas is a professor of Computer Science and Mathematics at the Free University of Berlin and a renowned specialist in artificial neural networks.

The FU-Fighters, football-playing robots he helped build, were world champions in 2004 and 2005. He formerly lead an autonomous car project called Spirit of Berlin and is now leading the development of the Made in Germany car, a spin-off project of the AutoNOMOS Project. Although most of his current research and teaching revolves around artificial intelligence and its applications, he holds academic degrees in mathematics and economics.


Latest News:
For more information on this week’s news, including pictures and videos of the two new robotic grippers, have a look at the Robots Forum.

| More

Related episodes:

September 24th, 2010

Robots: Olfaction

In this episode we look at how robots can use smell to navigate and map their environment or detect hazards. Our first guest, Achim Lilienthal from Örebro University in Sweden focuses on mapping gas clouds and localizing their source. Our second guest, Lino Forte Marques from the University of Coimbra in Portugal tells us about applications and sensors.

Achim Lilienthal

Achim Lilienthal is Associate Professor at the AASS Research Centre, Dept. of Technology, Örebro University in Sweden where he leads the Learning Systems Lab.

One of his main research goals is to use mobile robots equipped with gas sensors to map chemical clouds or localize their source. This requires making models of how gas diffuses in different environments based on many factors including wind. More unexpected however, is the use of smell for localization. For this purpose, Lilienthal who is also an expert in Self-Localization and Mapping techniques (SLAM) suggests that robots could figure out where they are by recognizing an odor previously encountered… say the smell of bacon frying in the kitchen. Finally, he discusses differences in natural and artificial smell and possibilities for 3D gas mapping.

Lino Forte Marques

Lino Forte Marques is an Assistant Professor in the Electrical Engineering Department of the University of Coimbra, Portugal, and Head of Research of the Embedded Systems Lab within the Institute of Systems and Robotics.

His research group wants to use teams of smell-endowed robots to research techniques that could be used for real-world applications like humanitarian demining, search and rescue operations, detecting fire hazards and counter-terrorism.
In order to achieve this, they have developed a cheap, small and modular odor sensing system called the kheNose for the popular Khepera III robot. An attractive feature of this system is that it is capable of odor discrimination, an ability often overlooked with other research modules that focus on detecting one particular substance in an otherwise odor clean environment. This makes it more suitable for realistic scenarios for which a clean environment is not necessarily a given.


Latest News:
More info on this week’s news, in particular on UC Berkeley’s new type of artificial skin and UC Berkeley’s laser mapping backpack, can be found at the Robots Forum.

| More

Related episodes:

January 15th, 2010

Robots: Deep-Sea Exploration

In today’s show we focus on the great depths of our ocean and robotic vehicles capable of taking us deeper than we ever imagined. Alberto Collasius Jr. tells us about his institute’s highly-advanced remotely operated vehicle, or ROV, capable of bringing high-definition video from over 5km underwater. We then announce the winner of our Christmas contest and proud owner of two Didel SA robot kits.

Alberto Collasius Jr.

Alberto Collasius Jr., or Tito to those who know him, is part of the Applied Ocean Physics and Engineering Department at the Woods Hole Oceanographic Institution in Massachusetts in the US. Collasius spends much of his time at sea as expedition leader with the JASON ROV which is used throughout the world’s oceans to search for old shipwrecks, underwater volcanoes or deep-sea natural environments that are inaccessible to human-operated vehicles. He tells us about the particular difficulties involved in operating at depths beyond 5000m and the sophisticated sensors and control systems present on their advanced ROV and base station.

Click to see a video of the underwater volcanic eruption

(photo courtesy of Woods Hole Oceanographic Institution)


Before Christmas, we asked you “who made the giant six legged robot?” for a chance to win the two robot kits offered by Didel SA. Turns out there were actually two answers to this question any of which qualified our many participants for the lottery. The first possible answer was Julie Townsend from the NASA and her Athlete robot for Lunar missions which was featured on a recent episode. The second giant six legged robot was actually called “the giant six legged robot” by its creator Jaimie Mantzel who was featured in April of last year.

The lucky winner of our competition is Will Preston who will be receiving his prize shortly.


Latest News:

For more information on this episode’s news, including some first robotics milestones for 2010, videos of ROV Justin’s close encounter with an underwater volcano and this year’s robot novelties at the CES 2010, visit the Robots forum!

View and post comments on this episode in the forum

| More

Related episodes:

December 4th, 2009

Robots: Planetary Exploration

Take the 5-minute survey to help us improve ROBOTS!

Today’s show is a special episode on space robots. We start by speaking with Julie Townsend from the Jet Propulsion Laboratory at the California Institute of Technology and her work with NASA‘s Mars Exploration Rovers and the lunar ATHLETE robot. We then speak with Sebastian Gautsch from the SAMLAB in Neuchatel, Switzerland, who tells us about his Atomic Force Microscope that was sent to Mars aboard the Pheonix lander in the Spring of 2008.

Julie Townsend

Julie Townsend completed her Bachelor in Aeronautics and Astronautics at MIT and then went on to Stanford for her Master’s degree. She’s now continuing a PhD there while working for the Jet Propulsion Laboratory (JPL) which she joined in 2001. The JPL exists as a NASA laboratory and has been involved in missions relating to the exploration of Earth and space with plans to send robots and humans to explore the moon, Mars and beyond.

As a robotics engineer at the JLP, Townsend has been working on the Mars Exploration Rovers Spirit and Opportunity. After touching on the development, integration, and testing of the rovers earlier in her career, she then became a Rover Planner, creating command sequences to drive the robots and move their arms on Mars. Townsend tells us what it is like to be the one behind the wheel of a robot on another planet, with all the mind boggling details that make space robots seem so improbable. She also gives us her insider’s view on efforts to get Spirit out of its sand trap on Mars.

In the second part of the interview, Townsend presents the prototype of the All-Terrain Hex-Legged Extra-Terrestrial Explorer (ATHLETE) robot which will be used as part of the Human Lunar Return campaign to help load, transport, manipulate, and deposit payloads to any desired site of interest. In particular, she speaks about its six legs capable of rolling or walking over extremely rough or steep terrain. After some redesigns, the ATHLETE is now onto its second prototype, getting ready for its mission to the moon.

Sebastian Gautsch

Sebastian Gautsch recently completed his PhD at the SAMLAB, part of the Institute of Microtechnology in Neuchatel, Switzerland, the goal of which was to design an miniature Atomic Force Microscope (AFM) destined to analyze dust particles on the martian surface. It is hoped that by analyzing the surface of the red planet in minute detail we can gain some insight into the geologic history and potential for biology on the planet.

Gautsch tells us about the difficulties in creating sensors for space, especially the limited payload and autonomy constraints of such a system. He then describes the impressive results they achieved with their sensor which was sent to Mars on the Phoenix lander mission in the spring of 2008, where they took the first ever atomic force microscope image on another planet (see below)!

An AFM calibration image taken on Mars


Latest News:

For more information on the robots demonstrated at Japan’s IREX, retiree robot Charlie and the Mobile Manipulation Challenge visit the Robots forum!

View and post comments on this episode in the forum

| More

Related episodes: