Underdog Nearly Victorious

http://geekmo.de/urban-challenge-2007/underdog-nearly-victorious/

Little Ben Secrets

Watch some the secrets behind Little Ben on this excellent video:

http://www.tgdaily.com/content/view/34685/113/

Little Ben making history

This is a historic day not only for robotics but also for Penn Engineering.
Little Ben has just completed a total of 19 complex driving missions in 6
hours while obeying all California driving laws. Congratulations to Dan Lee
and all members of the Little Ben team for this historic achievement! They
have all made us all so proud.

In addition to Little Ben, Stanford, CMU, and Virginia Tech have completed
the race, while MIT and Cornell are about to finish soon. Noone expected
six teams to complete the race, clearly indicating of how much robotics has
evolved over the past decade. The remaining five finalists dropped during
the first two hours of the competition.

There is a complex scoring formula that will be used in ranking the teams.
But regardless of scoring and ranking, completing the mission is the
greatest accomplishment, and, in our opinion, all teams are winners. You
can watch the official award ceremony tomorrow, Sunday from the DARPA
website at: www.grandchallenge.org . The (current) schedule is as follows:

Sunday, November 4
11:00AM EST Recognition of finalists
13:00PM EST Awards ceremony, press briefing to follow

Check the above website for potential schedule changes but also for great
highlights from today's race. There were some scary moments, even for
Little Ben. But in the end, everything worked.

We will be organizing a party for the return of the team, as well as a broad
seminar with Little Ben videos from the competition. More info on this
soon.

Congratulations Little Ben! What a fantastic day!

George J. Pappas
Professor, GRASP Director
Department of Electrical and Systems Engineering
University of Pennsylvania

Urban Challenge Finals - Time update

Opening ceremony will begin at 10:30 AM ET, and vehicles will begin to launch at 11:00 AM ET.

NQE Highlights [video,pic]

Ben Franklin racing team is one of only 11 teams which will compete in the final event on Saturday Nov 3rd 9:30am ET.

Watch a video of highlights from the NQE here:
http://www.darpa.mil/grandchallenge/video/DARPA_NQE_preview_high.wmv

!!! :) Ben qualified for the race :) !!!

Ben qualified for the Urban Challenge Final event!!!

The Ben Franklin Racing team is one of only 6 teams, out of 35 teams that arrived to the National Qualifying Event, that were qualified early for the Urban Challenge race.

Great Work ....

Watch the final event in a live webcast from Victorville, CA on Nov. 3rd 2007 starting 6:20 PT.

In a message from the trenches:

Dear All,

We have just heard that we are unofficially through to the final, in
addition to CMU & Stanford.  The competition has been really tough
this year but Ben has performed really well. Next up - taking Tony
Tether's money  :) 

-Ben Franklin Racing Team

Ben is leaving for the NQE

The team is about to leave to Victorville, CA. For the National Qualification Event (NQE) which will be held between October 26 - November 1.

35 teams and their vehicles will compete in a qualification round for a chance to compete in the finals. The finalists will be announced on November 1.

On Saturday November 3rd there will be a live webcast of the final Urban Challenge event.

A short video on Ben

This little car can drive itself home
Allentown Morning Call - Allentown,PA,USA
... of grounds for the driverless vehicle developed by engineers from Lehigh, the University of Pennsylvania and the defense contractor Lockheed Martin. ...

New Storage Container

We're continuing testing. In the mean time we've rented a shipping container for secure storage of Ben.

Qualifications for the Semi-Finals

I'm proud to announce that we are one of the 36 teams selected for the semi-final event starting October 26th.

The Darpa Press Release is here http://www.darpa.mil/grandchallenge/docs/PR_UC_Semifinalist_Announcement.pdf

Congrats to all the other teams!

Video Highlights from the Site Visit

Here's a video of our performance at the site visit.

Short Clip of the Site Visit

Site Visit Completed

Sorry for the long delay in posting. We've been working hard on the vehicle and have made good progress.

Today we completed our official site visit. We successfully completed all 4 missions in approximately two hours and had time for a few extra demonstrations.

Photos are below. And hopefully we'll have a video to post soon as well.

Thank you to all our fans who came out to support us on this hot Sunday.

New Photos Posted

There are new photos of the latest generation of sensor roof rack as well as new photos of the EMC system and computing rack.

Testing Update,

We made it up to Lehigh by midday and had a good afternoon of testing.

• We successfully logged performance data for trajfollower.
  
• We also drove the site visit course again now with OmniStar DGPS coverage.
• I successfully tested the distributed logging on the RT3K module, however the combination of Xforwarding, rendering, and NFS caused problems with the velodyne logging in this manner. So we logged in the old format as we drove with other vehicles around the site visit route.
• Dan demonstrated successful following using the matlab controller up to 17 mph forward and 15 mph in reverse in a relatively tight course.The vehicle was programmed to automatically slow for corners.
• And we were able to successfully navigate the site visit course with dense waypoints, with the problem that the tracks would drift off the road due to GPS offset.

Tully

DARPA Site Visit

"The Ben Franklin Racing Team has been selected to receive a site visit by DARPA officials in June 2007 ... "

Dr. Tony Tether, Director of the Advanced Research Projects Agency.

Intersection Navigation Demonstrated

Good news,
We successfully demonstrated intersection navigation to the level required for the site visit today. Drew videotaped our driving through an intersection after waiting for a car to clear a few times.

Also John and his students have laid down the centerline marking tape around the whole course and have made good looking stop lines for the intersection.

We have driven around the course 3 times with Little Ben to get out best estimate of it's position. This will be used to finalize our RNDF to submit this week.

Also of note we have new photos of the team up from last week.

Video Submission Completed

We've spent the last few weeks working to produce our video for submission to Darpa. It's done so here it is,

Getting the Velodyne to work

We spent the day working on demonstrating intersection navigation including vehicle avoidance. We were able to demonstrate intersection navigation with empty obstacle maps. However we ran into technical difficulties when trying to translate the maps generated by the velodyne to the
planner.

Paul has helped me out and the Velodyne can render beautiful point clouds in real time. Now that we have the correct calibration for our unit we can watch people walk down the sidewalk from 20m away, and see 5+ cars around a busy intersection. Hopefully we can post some of the recorded data into videos soon.

Tully

Video Demo - Proof of concept test

Today we took Ben out to the car-park to test the LADAR
integration with the video-demonstration code - in short, after
debugging/fixing we were able to reliably transform the LADAR data
into a usable map, evaluate our plan through the map and correctly
identify Tully's car as an obstacle in our path, stop in front of it
and then transition to the other available lane and then transition
back to the first lane after passing Tully's car - this was all at
about 5mph.

We were also able to demonstrate that trajFollower could drive the
video-demo course that Jim laid out at park and we took the
reporter who came out with us around the course a couple of times and
she seemed suitably impressed. Heeten was also able to make
significant progress on testing the RNDF generator that uses the
google-map-esque interface.

There are still some issues that we need to resolve, primarily
concerned with the quality of the LADAR maps when driving at higher
speeds and making reasonably sharp bends, both of which frequently
lead to significant obstacles being painted into the map, although
these are rarely sufficiently high to be viewed as obstacles to plan
around by the video-demo code, the performance should be better than
it is now.

Alex

Autonomous Trails

A video of autonomous trails by little ben, the ben franklin racing team's car.
Following a marked course, avoiding an unexpected pedestrian crossing the road and following a leading car.

Ice Accident

Hi there,

I've got some bad news. Ben will be out of service for a little while. While we were getting Ben setup in front of the Levine loading dock, a large bunch of ice fell off the roof of Fisher Bennett and smashed our windshield, hood, and right mirror. The ladar's were on the roof and one took enough of a hit to knock it cockeyed on it's mount, but it tested ok in the lab afterwards.

The only major problem with Ben is the windshield, it's pretty opaque and obviously compromised. The mirror needs to be replaced. And the hood is cosmetic, but probably a good thing to fix so we don't look like we got into an accident. All other systems are fine.

In the good news. None of us were hurt. As the first smaller stuff came down we moved away. Also, we now successfully have tested LADAR producing elevation maps feeding directly into matlab and then feeding a map to the planner. We were on our way out to record some data to try planning through when the ice fell.

Here are some pictures:

Tully

(Great) Testing Results Featured in the Philadelphia Inquirer

We had a really fantastic testing day today - the steering control is now really good and very smooth (no jerking steering wheel etc - it actually looks like a human is driving). We did have a reasonably persistent problem with the GPS jumping near the poles in the car park which is why we have some discrete jumps in the route traces - but this is something that we are investigating several different avenues to solve (new pose system, pose filter changes etc). Hence we got a lot of recorded data using benracer.dangerous (keyboard arrow control of the vehicle controls - great fun) of human driving and throttle/brake characterisation data so we should be able to build a good map of the throttle-brake characteristics to use in a new longitudinal controller.

The Philadelphia Inquirer reporter and photographer met us took photos of Ben and we took the reporter for a spin in the driving seat (with Ben driving) which he seemed to enjoy - read more about it and watch a video of the car here:
http://www.philly.com/mld/inquirer/16709897.htm

However - we also had a minor problem:

We smelt burning plastic in the car and stopped immediately - when we looked in the boot (trunk) we found that we had melted (the casing) *and* fried the wires connecting the 400V inverter to the 12V power supplied from the vehicle.

Alex

Another Day in The Field

On Sunday we tested a new trajectory follower which is based on a value-function. The pose estimator was tested integrating all sensors including GPS, IMU, and car odametery.
The video production team is working on a promotion video of little ben performing an autonomous run which will display our GUI to the brains of the car.

Driving by the RNDF

Jim, Alex K., Heeten and I went to the Boeing lot with the Prius for
the first time on Sunday. Our objective was mainly to get acquainted
with the site, but we also took the opportunity to do some more
testing of the trajectory-following code and a simple RNDF. We
enabled the
trajectory follower's throttle control for the first time, since we weren't
willing to risk it in the smaller lot. Everything was pretty successful,
though the controller gains still need a lot of tuning. We were able
to follow some pretty interesting trajectories, including one based on
an RNDF we also built for the site.