Pictures of Prometheus and the IGVC competition

Pictures have been added of the team, Prometheus, and other robots. These pictures were taken over the past two days.

http://picasaweb.google.com/107537254206068337248

Now the team is anxiously awaiting the announcement of the design competition winners. By noon, we should know! And if we move on, we will be presenting again later today!

Prometheus @ IGVC 2010

After working through the morning we have given our design presentation and it went very well. The judges loved our design and commented on how the vehicle is a fantastic platform for a first year team. With a half hour of pool time we are now currently working on some internal navigation programming issues and are hoping to not only qualify for tomorrow, but also be picked for the second round of design presentations.

Team hard at work on the morning of the second day. Almost ready to qualify!

Prometheus in action!

Outdoor Testing

Recently, we took Prometheus outside to do some path following testing.  During this testing, Prometheus was able to successfully navigate through an obstacle course with a switchback.  This course was built using construction cones and barrels.  We also added a camera box to protect our stereo-vision cameras and a GPS for navigation purposes.

Prometheus Presented to the WPI Public

On April 22nd, Team Prometheus presented the current progress of their vehicle to the WPI public on the senior project presentation day. Below are a couple of images from the event. Spectators gathered around the vehicle inquiring about everything, as excited about the project as the team!


Added Hardware and Skins

The vehicle now has a new power distribution board located in the back behind the motors. It also has the electronics and sensors mounted. The top and sides have been covered with a thin sheet of polycarbonate to protect against rain water.

Prometheus Is Moving!

Today was the first time running the vehicle under manual control outside of the lab. During the test, we decided to try and move up a steep incline. The link below will open the video file.

Video: prometheus_vs_hill

Also, here are a few pictures of the robot with the top cover in place.

Chassis Base Ready for Testing

The Chassis base is now functional and ready to do test drives.At the rear, two sets of custom sprockets was CNC machined in house and mounted on each drive motor and rear wheel. The rear wheel assembly was modified to accommodate the added sprockets. Optical encoders were attached to the drive motors at the rear end of the motor shaft.At the front, the two supporting plates at the top were CNC machined and bolted onto the chassis. The turning shaft is supported by two ball bearings and a thrust bearing plate. A set of timing belt & pulley was used for turning the wheel and the angle feedback is recorded by the potentiometer mounted at the top of the shaft.It is ready now to mount the battery and control electronics to do some testings!

Functional Chassis Base

Disparity Map

We have successful created a disparity map from our two Stereo images.  An initial estimate of the disparity between the left and right images was attained using a sum squared difference algorithm.  This algorithm attempts to match 5×5 blocks of pixels in the left image to the right image.  If a good enough match is not found a disparity of -1 is recorded.  After the initial disparity map is created we use the segmented image to preform a segmented based average on the disparities.  This serves to eliminate some of the outliers in the image and give us more consistent data.  The average is taken over a 11×11 pixel radius and pixels that are located outside the center pixels segment do not count heavily towards the average.  This allowing us to maintain differences between objects in the image while still averaging within them.  The whole process takes about 80msec in the GPU and the results of one run are shown below.  The picture of the disparity map shown below was colored to show depth, red is closest and blue is furthest away.

Left Rectified Image

Right Rectified Image

Segmented Image

Disparity Map

Software Team Update

These past few weeks the software development team has been preparing for the project presentation day. The following requirements have to be met in order to reach our goal of having a qualifying robot for the IGVC.

  • Making sure the Control Center (CC) and joystick work on the laptop which will be used during the competition. (done)
  • Adding the capability to enter a series of way-points through the CC  for the Navigation Challenge.  (done)
  • Implementing the ability to control the state of the vehicle through CC. Vehicle state includes paused, running, and shut-down. (done)
  • Implementing the ability to switch between the different challenge modes including Navigation, Autonomous and JAUS. (done)
  • Adding the ability to update the CC with the current usage information of the main-board computer. This includes RAM, SWAP space and system up-time. (done)
  • Implementing path finding based on the waypoints. (in progress)

Besides the latter changes, a major re-factor for the whole code-base was preformed in order to make the system architecture more robust. As well as additional functionality was added to the CC in order to ease the development and testing of the vehicle.

Functioning Chassis Wheels

The steering front wheel is completely constructed (it works!) and the back wheels are attached. The only thing left to do is attach the motor encoders to the motors and we are ready to do some drive testing.

Here’s a picture of the team testing the front steering because we were to eager to see it working before attaching the motor to a battery!