Skip to content



Growers of high-value agriculture require information about the current state of the crop to efficiently manage production. We are designing methods to collect crop information automatically with accuracy, efficiency, precision. There are three main themes to our work:

Generative Visual Estimation

A visual estimation framework applicable across different commodities (strawberry, grape, apple, mushroom, peaches etc.) measuring desired crop characteristics from images with minimal human burden

Active Sampling

Adaptive statistical sampling by human-robot teams to develop optimal strategies with respect to;

  • Number of samples
  • Location of samples
  • Cost of sampling
  • Accuracy of crop estimates

Active Perception

Physical actuation to improve the measurements collected by the robots, by estimating occluded area on plant and move sensor head or actuator to reveal hidden crop.

Leave a Comment

Leave a Reply

Please log in using one of these methods to post your comment: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s