News

Check out my recent videos: 

 

ICRA 2013: we are organizing a workshop on: Interactive Perception. More soon...

IEEE/RAS: I was a guest editor of the Robotics and Automation Magazine special issue on mobile manipulation. Check it out!

 

 

 

Semi-Autonomous Manipulation of Natural Objects

 

Scene of natural disasters Effective deployment of robots in search and rescue missions will enable faster and safer removal of debris and other hazardous material. As a result, additional lives will be saved, the number and severity of injuries will decrease, and significant damage to infrastructure will be avoided.

Already today robots are an integral part of many search and rescue units. These robots typically serve as either mobile cameras (autonomy in navigation, but no manipulation capabilities) or as tools controlled by a human operator (no autonomy, but capable of interacting with the environment).

I developed perceptual and manipulation capabilities that enable a robot to share a role with a human operator: the robot provides the operator with processed visual information and a set of possible actions, and the human operator chooses the strategy of interacting with the environment.

  • The robot's perceptual capabilities include a novel scene segmentation algorithm based on 3D data, and tools to analyze the segments to determine possible interactions with objects
  • The robot's manipulation and grasping capabilities are based on a library of compliant controllers
  • The human-robot interaction is achieved with a graphical user interface
Graphical User Interface The graphical user interface enabling role-sharing between the robot and a human operator.

Top
Left
Live video. The operator can choose when to take a snapshot of the scene using a context menu.
Top Right The captured snapshot. It is updated when a new snapshot is requested. The interface can show either the current or previous snapshot.
Bottom Left The computed segmentation. The operator can choose from a list of available action by right-clicking on each segment.
Bottom Right A live 3D display.