RoboBrain contains knowledge from different sources stored as a graph . With our API , one can push and retrieve this knowledge. With our query language RaQueL , one can enable several robotics applications.

Play with RaQueL online

Robotic Applications


A Crowdsourcing Approach for Learning to Plan Paths from Large

PlanIt uses RoboBrain to fetch trajectory parameters from different attributes computed from user preferences. You can try the example below.

Please wait while we query the roboBrain and obtain the heatmap.

Select files

Choose Multiple Files

Upload queue(Max items:2)

Queue length: 0

Name Size Progress Status
Queue progress:


Console Messages

RaQueL query

trajectories = fetch("({handle:'egg_carton'})-[e:`IS_TRAJECTORY_OF`]-()")


Anticipating Human Activities for Reactive Robotic Responses

The assistive robots working with humans should be able to understand human activities and also anticipate the future actions that the human can perform. In order to anticipate, the robot should reason over the action possibilities in the environment, i.e., object affordances, and how the actions can be performed, i.e., trajectories.

RaQueL query

trajectories = fetch("({handle:'standing_human'})-[e]-({handle:'refrigerator'})")
anticipated_trajectory = SortBy(trajectories, 'Belief')

Partner Projects


Intelligent car cabin sensing


Manipulating novel objects using learning based on transfer of object parts