Artificial Intelligence Depot
Visiting guest. Why not sign in?
News, knowledge and discussion for the AI enthusiast.
FEATURES COMMUNITY KNOWLEDGE SEARCH  
The Age of Spiritual Machines
This is a book for computer enthusiasts, science fiction writers in search of cutting-edge themes, and anyone who wonders where human technology is going next.
More information at Amazon US UK

Reply to Message

Not registered yet?

The AI Depot has a focused community of friendly users. Rather than let anyone abuse the site at the brink of promiscuity, we prefer to let only those with an active interest participate... this simply requires registering.

Why not sign up!

Joining the site's community is completely free. You can then post messages freely, and customise your personal profile at will. Specific privileges will also be granted to you, like being able to access printer-friendly articles without restrictions. So, why not register?

Username:
Password:
Subject:
Email me when someone replies.
Body:

Parent Message

Car parking...

This is solvable using an A* search, so long as the car can generate a search space representing its surroundings.

I've done it in simulation, the hard part is generating the real world map to do the work in. And it sounds like they've done most of that already...

8 posts.
Thursday 29 November, 11:27
Reply
Obstacle-Avoidance rather than Path-Planning

I think they basically let the driver find the parking spot, and use the distance sensors to do the manoevering. I'd be very amazed if it was any more than that!

A* is over-rated ;)

935 posts.
Friday 30 November, 10:36
Reply
Parallel Park

Well I was assuming they where doing something more complex than just automatically backing the a car into a space - that's just a question of not hitting things.

Think of the component movements involved in getting into or out of a parallel park position, or performing a three point turn.

It can be useful to think of this as a route finding problem, in the same way as solving a rubix cube, or docking a spaceship can be thought of as "route finding" problems.

I wasn't talking about "finding a space to park", rather how to park in a tight space using several small movements.

8 posts.
Monday 03 December, 07:19
Reply
Indeed

Yeah, I was disapointed too... but hey, one step at a time!

Indeed, route finding problem would be much harder. To some extent, it's already been done at a high-level, with GPS-based guiding systems. But this does not apply to lower-level details.

I guess a blend of the two approaches sounds like the way forward. Hmmm, sounds a lot like the research I'm doing ;)

935 posts.
Tuesday 04 December, 07:07
Reply

Back to the Artificial Intelligence Depot.