Capture and synthesis of insect motion
Proceedings of the 2005 ACM SIGGRAPH/Eurographics symposium on Computer animation
A system for the capture and synthesis of insect motion
Graphical Models
Spatiotemporal correspondence as a metric for human-like robot motion
Proceedings of the 6th international conference on Human-robot interaction
Generating human-like motion for robots
International Journal of Robotics Research
Hi-index | 0.00 |
We present a novel approach to motion synthesis. It isshown that by splitting sequences into segments new sequencescan be created with a similar look and feel to theoriginal. Copying segments of the original data generatesa sequence which maintains detailed characteristics. Bymodelling each segment using an autoregressive process wecan introduce new segments and therefore unseen motions.These statistical models allow a potentially infinite numberof new segments to be generated. We show that this systemcan model complicated nonstationary sequences whicha single ARP is unable to do.