View
222
Download
6
Category
Preview:
Citation preview
Vision-based Motion Planning for an Autonomous Motorcycle on Ill-Structured
Road
Reporter:鄒嘉恆Date: 08/31/09
Introduction
• Design a vision-based motion planning system for desert terrain.
• The motion planning is based on a vision vector space(V2-space).
• Motivated by the DARPA Grand Challenge.
Outline
• V2-space• Algorithm– V2-Space construction– Motion planning in V2-space
• Experimental results• Conclusion
V2-space
• Pin-hole model:• Video frame F is a matrix of RGB values:
•
Algorithm:V2-space construction
Algorithm:V2-space construction
• Color correction:
Algorithm:V2-space construction
• Surface verification:
• Obstacles detection:
Algorithm:V2-space construction
• Direction extraction:
Algorithm:Motion planning in V2-
space• A point robot with no time delay:
Algorithm:Motion planning in V2-
space• Choose the velocity profile vp(t)• The motorcycle cannot run too fast for a given
trajectory radius R.
Algorithm:Motion planning in V2-space
• Incorporating GPS information:
Algorithm:Vehicle size and processing delay• Vehicle size
Algorithm:Vehicle size and processing
delay• Image processing delay:
Algorithm overview
Experimental results
• From video clip:
Experimental results
• From video clip:
Experimental results
• From video clip:
Experimental results
• Filed tests:
Conclusions
• Propose V2-space, a new framework that represent road feature and allows fast construction and motion planning.
• In the future, they will consider incorporating V2-space in a stereo vision system.
Recommended