news    views    podcast    learn    |    about    contribute     republish    

Low-latency event-based visual odometry | ETHZ via Phys.org


curated by | May 29, 2014

One of the reasons we don’t yet have self-driving cars and mini-helicopters delivering online purchases is that autonomous vehicles tend not to perform well under pressure. A system that can flawlessly parallel park at 5 mph may have trouble avoiding obstacles at 35 mph.

John Payne‘s insight:

From http://rpg.ifi.uzh.ch/docs/ICRA14_Censi.pdf

“The achievable agility of a robotic platform depends on the speed of its processing pipeline (the series of data acquisition plus data processing); more precisely, it is important that the pipeline offers high sampling rate as well as low latency. At the state of the art, the latency of a CMOS-based pipeline is at a minimum in the order of 50- 250 ms and the sampling rate is in the order of 15-30 Hz. To obtain more agile robots, we need to switch to faster sensors.”

See on phys.org

-->


comments powered by Disqus


Presented work at IROS 2018 (Part 1 of 3)
November 12, 2018

Are you planning to crowdfund your robot startup?

Need help spreading the word?

Join the Robohub crowdfunding page and increase the visibility of your campaign