Endeavour Drive - Drivability analysis |
Endeavour Drive - Drivability analysis |
Sep 18 2008, 11:05 AM
Post
#1
|
|
Founder Group: Chairman Posts: 14434 Joined: 8-February 04 Member No.: 1 |
http://www.sciencefriday.com/program/archives/200809191
You can listen via NPR, or via one of the web feeds that are listed on the site, but make sure you do listen if you can. |
|
|
Oct 14 2008, 03:54 AM
Post
#2
|
|
Member Group: Members Posts: 399 Joined: 28-August 07 From: San Francisco Member No.: 3511 |
I'm beginning to make sense of this process through the extraordinary efforts posted here...
Astounding... Thank you. -------------------- 'She drove until the wheels fell off...'
|
|
|
Oct 14 2008, 08:02 AM
Post
#3
|
|
Member Group: Members Posts: 257 Joined: 18-December 04 Member No.: 123 |
Interesting problem.
If I had time I'd love to try and implement this. At first look here would be my suggestion for an algorithm. CODE Start by overlaying a grid over the image, with each grid location being 5 pixels square (arbitrary right now). Each grid would be assigned a score. (Take a pixel colour of RED to be a score of 1, and a pixel colour of green to be a score of 0 and intervening colours having a 0.xx value as suggested by stevesliva) The score for a grid location would be the average score of the pixels it contains. (obviously the smaller the grid size in pixels the more accurate the score) The cost of traveling from one grid position to another would be the difference in the neighbouring grid location's scores. There would be 7 possible directions to travel from a given grid location (excluding the path you just took) You could perhaps limit this again by only using ones that take you southwards or weighting the southward direction steps higher With a grid of 5 pixels over the HIRISE image, recursion would be good. Using the grid makes it arbitrary to change the algorithm for more fine grained route planning. You could start with a large grid size to get the algorithm going. Not sure what languages people are using here, if a collaborative effort was going to start it would be worth getting a sourceforge or google code thing setup. I'll be watching with interest! -------------------- Turn the middle side topwise....TOPWISE!!
|
|
|
Oct 14 2008, 08:43 AM
Post
#4
|
|
Senior Member Group: Moderator Posts: 4279 Joined: 19-April 05 From: .br at .es Member No.: 253 |
Now, have a look to this very interesting paper "The Mars Exploration Rover Surface Mobility Flight Software: Driving Ambition" in section 5. Autonomous Driving:
"In Terrain Assessment (or Predictive Hazard Detection) mode, one or more stereo pairs of images are processed into a traversability or goodness map, ... If path selection is also enabled, candidate motion paths are projected into this map (see Figure 3), and a weighted evaluation of the constituent cells is assigned to each path. This results in a set of Obstacle path evaluations; low values indicate a less traversable path, high values indicate a more traversable path." Similar algorithm as yours is already used by the rovers, obviously on a much smaller scale. |
|
|
Lo-Fi Version | Time is now: 23rd September 2024 - 04:42 AM |
RULES AND GUIDELINES Please read the Forum Rules and Guidelines before posting. IMAGE COPYRIGHT |
OPINIONS AND MODERATION Opinions expressed on UnmannedSpaceflight.com are those of the individual posters and do not necessarily reflect the opinions of UnmannedSpaceflight.com or The Planetary Society. The all-volunteer UnmannedSpaceflight.com moderation team is wholly independent of The Planetary Society. The Planetary Society has no influence over decisions made by the UnmannedSpaceflight.com moderators. |
SUPPORT THE FORUM Unmannedspaceflight.com is funded by the Planetary Society. Please consider supporting our work and many other projects by donating to the Society or becoming a member. |