Planit
Home
About
TeachIt
SeeIt
Research
Planit

Robots just like babies, do not know much about the world around them. They need to learn crowd preferences if they wish to move around, without annoying or harming people. This is a difficult problem because the criterion that defines a good trajectory can vary with tasks and environments.

PlanIt is a crowdsourcing system to collect large amount of preference data by showing videos to non-expert users. PlanIt learns a cost function from the preference data and uses it to generate desirable robot trajectories. Since the users are not experts, the feedback is weak and noisy but our extensive experiments show that this feedback helps generate preferred trajectories. We also visualize the learned cost functions as heatmaps and confirm that the preferences learned make intuitive sense.

In popular press:

Bbc Discovery Ieee Acm Dailymail Techcrunch Fox Kurzweil Cbs news Cnet Nbc Huffpost Gizmodo Popsci Slashdot



Ashesh small

Ashesh Jain
Project Lead

Deedy

Debarghya Das

Jkg

Jayesh K. Gupta

Thorsten

Thorsten Joachims

Ashu

Ashutosh Saxena


Also special thanks to

  • Daniel Liu
  • Julie Behr
  • Vaibhav Aggarwal

for their help in setting up and testing the system.



For technical details, contact
Ashutosh Saxena: asaxena@cs.cornell.edu
Ashesh Jain: ashesh@cs.cornell.edu
For web page issues: planit.webmaster@gmail.com