amr-logo-p3icon-wide-blue-cropped
October 8, 2014
divider.gif
Adept MobileRobots Wraps Up IROS 2014
divider2.gif
Adept MobileRobots Booth at IROS 2014Pioneer LX
Hope you had a chance to visit our booth at IROS 2014

Last month in Chicago Adept MobileRobots (AMR) had the opportunity to attend and exhibit at the 2014 International Conference on Intelligent Robots and Systems (IROS).  We hope we saw you there but for those we didn’t here is a short summary on our exhibition and demos. 


We had a few interesting things to see in our booth this year.  We had the Seekur Jr. (datasheet here) present to show off our outdoor platforms.  We also had our tried and true DX (datasheet here) indoor platform performing an “autonomous pick and place” demonstration with help from Energid’s new R3 manipulator arm (available later this year, Energid’s website here).  However, the most interesting product we brought to the show didn’t spend much time in our booth.  In fact, it was hardly there at all.  Of course we’re talking about our newest autonomous mobile platform, the Pioneer LX.  The Pioneer LX spent most of its time autonomously navigating the show floor, spreading product literature, visiting other booths, and posing for selfies with conference attendees.  The LX has a runtime of 13 hours, automatic docking / charging, and a payload of 60 kg.  The hardware’s features in combination with our proprietary ARNL navigation software provided an impressive show demo that drove a lot of traffic back to our booth.  We were grateful that the LX broke the ice with many attendees and other exhibitors at the show.  For the LX datasheet click here.

spacer.gif
divider2.gif
Adept MobileRobots and Microsoft Team Up to Sponsor the Kinect Challenge at IROS 2014

At the 2014 International Conference on Intelligent Robots and Systems (IROS) in Chicago, IL, USA, six teams from around the world took up the challenge of navigating an Adept MobileRobots Pioneer 3-DX mobile robot in a difficult, novel environment using only a Kinect for Windows RGB-D camera as a sensor, in combination with the mobile robot’s own motion sensing and position estimate. This contest was organized and sponsored by the robotics group from Microsoft Research, and Adept MobileRobots (http://www.mobilerobots.com).

 

Nine qualifying teams were chosen for the contest, and began working on their navigation implementations 13 weeks before the contest. In this short time, the teams had only general information about the environment in which the robot would have to navigate.  

 

Six teams were present at IROS: “Maxed Out” (SV-ROS, USA), “SCARAB” (Seoul National University, Korea), ONERA (France), MetroRobotics (USA), “Kordis” (Korea Advanced Institute of Science and Technology, Korea), “Blackberry” (Virginia State University, USA).

 

Contestants’ software had to use the Kinect to sense the objects in front of the robot, as visual images and/or distance measurements; communicate with the Pioneer 3-DX robot to drive it and receive measurements of  its movement as sensed by its internal motion controller and wheel encoder sensors; create a representation or understanding of the environment including specific goal locations within it; and communicate with the external benchmark system used to determine whether the robot had reached the desired goal locations. 

 

This contest provided many challenges in robot navigation and software engineering, and pressed the participants skills in autonomous robot mapping, navigation and localization as well as some practical constraints seen in real applications of robotics.  Contestants noted that the Kinect presents limitations in field of view and stability of data when compared to other, more expensive sensors such as scanning laser (LIDAR) sensors.  They also noted the time pressure to perform tests and reconfiguration and debugging when finally on-site just days and hours before the start of the contest.   Teams had to be agile in adjusting their software for specific details of the environment such as the appearance of the carpet, walls and furniture.   Some features in particular were especially challenging, including very narrow furniture, and a long narrow hallway that provided few unique localization features.  An important aspect of the challenge was the presence of people during navigation trials that were not present during the earlier mapping and preparation stages.  Most teams worked late into the night before the contest.

 

All teams used existing ROS (http://www.ros.org) as a foundation for their systems.  ROS is a large open-source project for robotics software, and provides a system of reusable components that provide standardized interfaces to hardware such as the Kinect sensor and the Pioneer 3 DX robot, components for performing mapping, localization, and planning and navigation of the robot through a mapped 2D space, as well as visualization and other development tools.  Teams customized and added to this foundation of existing code to implement their unique approaches to the challenge.

 

The first place winning team, “Maxed Out”, representing the Silicon Valley ROS users group,  used ROS to incorporate Mathiew Labbe’s Rtabmap mapping and localization algorithm, which used both the Kinect’s distance measurement capability and its visual camera to sense obstacles as well as match features previously recorded in the map during the mapping and preparation phase of the contest.   Team members present at the contest collaborated with each other and remote members of the team to test, debug and improve their total system, and their work resulted in the highest score with 3 waypoints successfully visited in the fastest amount of time of 80.4 seconds.   More details on this entry are available from the team at http://www.meetup.com/SV-ROS-users/pages/Winning_the_IROS2014_Microsoft_Connect_Challenge/ and https://code.google.com/p/rtabmap/wiki/IROS2014KinectChallenge

 

Second place was claimed by Charles Lesire for the French National Aerospace Research Laboratory (ONERA), also successfully reaching 3 waypoints, in a time of 157.6 seconds.

 

The third place finisher, David Lu of Metro Robotics, using his modified ROS navigation stack, reached 2 waypoints in a time of 33.9 seconds, followed by Kordis (2 waypoints, 82 secs.), SCARAB (2 waypoints, 97 secs.) and Blackberry (1 goal, 32 secs).

 

The members of the winning team split a grand prize of $5,000 USD.  All runner up competitors also received a prize of a new second-generation Kinect One for Windows Developer Kit.


(Photo Credit to George Maxwell)

Kinect Challenge Environment
All Kinect Challenge TeamsWinning Team - Maxed Out
spacer.gif
divider2.gif
IROS Topic Summary
Industry Trends and Hot Topics at IROS 2014

One of the biggest benefits (in my opinion) of industry events is that they serve as a bellwether for trends in the industries that they are associated with.  No matter how you participate in the industry; whether you represent a business or university, whether you are a student or an employee; there is immense value in identifying and understanding these trends.

 

One way I’ve found to identify and understand these trends is to review the topics presented at the event.  For IROS this can be particularly challenging.  With 750 papers submitted and presented over the course of the conference it can be a daunting task to take away any meaningful, actionable intelligence.  However, it can be done. 


The included graphic is an estimate of some umbrella topics’ popularity based on how often they showed up in presentations and papers.  Obviously, as a mobile robotics company, we’ve honed in on and summarized most exhaustively the topics that are most relevant to trends in the mobile community.  We were very happy to find that of all the 750 papers submitted for the conference that 28% of them are dealing, in some way, with mobile robotics.  Whether the submissions were for autonomous navigation, solving localization challenges, or advancing mobile technology…a large portion of the topics presented dealt with robots that were mobile. 


You’ll see in the graphic that we summarized the subtopics under mobile as well.  Mobile aerial robots win the popularity contest within mobile (next to general topics).  With the popularity of UAVs in the media today it isn’t surprising that both corporate and academic settings are seeking to involve themselves in such a visible segment.  I’ll also add that some of the topics concentrating on overcoming the challenges of air and water autonomy were among the subjects I found most fascinating.  One last focus topic that I’d like to mention is efficient, autonomous navigation around humans.  I found it interesting that there are parties in the industry that are no longer looking at humans as just an obstacle and navigating around them as if they are a crate or a desk.  Many (roughly 7% of all mobile topics) presentations dealt with the advancement of how to treat a human as human, how to determine their intended path (not just their location), and how to best navigate around us given that determined intent.  Given the implications of success I wouldn’t be surprised if this continues to be an area of great focus.


Lastly, I’ve already admitted to you that we’ve selfishly focused on reviewing and summarizing the topics most relevant to our company.  However, being the generally curious type of folks that we are, we also kept track of other topics that seemed to have higher frequencies of recurrence.  Those other hot topics that we’ve identified are:


+ Multiple Robot Cooperative Navigating and Task Completion (Swarm)

+ Autonomous Terrain Identification

+ Mapping Dynamic Environments

+ Assisted Surgical Applications

+ Tactile Object Recognition

+ “Snake-like” Robots

+ Printable Robots

+ Wearable Robots

+ Legged Robots

+ Soft Robots


Thanks for reading our newsletter.  We hope the information about Adept MobileRobots at IROS as well as the event as a whole has been helpful to you.  If you have any questions please feel free to reach out to Sales@mobilerobots.com or Chad.LaCroix@adept.com for additional detail.

spacer.gif




Adept MobileRobots
10 Columbia Dr.
Amherst, New Hampshire 03031
US