GraspingExperiment

Prev: The Discrimination Experiment	Up: Home	Next: Collective Behaviour and Swarm Robotics

Table of contents

• Reaching and grasping on an iCub robot

Reaching and grasping on an iCub robot

The GraspExperiment plugin enables a simulated iCub robot to acquire integrated reaching and grasping capabilities that enable it to reach a ball located in varying positions over a table, grasp it, handle it, and elevate it (Massera et al, 2014). Beside the difficulties concerning the need to control an articulated robot with many DOFs, this represents a rather challenging task since it requires interaction with physical objects (including a sphere that can easily roll away from the robot’s peripersonal space) and integration of three interdependent behaviours (reaching, grasping, and lifting). This indeed represents one of the most complex tasks that have been successfully mastered in evolutionary robotics and more generally in adaptive methods. The results obtained in simulation have not been validated in hardware. However, a video described the behaviour of a similar experiment in which the evolved controller have been successfully ported on the physical robot is available from this page.

The ReachExperiment plugin, instead, enables to replicate a simpler experiment in which the robot is evolved simply for the ability to reach variable target point in the robot peri-personal space.

The source code of these plugins can eventually be modified to replicated other related experiments involving the iCub platform, such the experiments on active categorization described in (Tuci et al, 2010), language and action described in (Massera et al., 2010), and language comprehension described in (Tuci et al., 2011).

References

Massera G., Ferrauto T., Gigliotta O., Nolfi S. (2014). Designing adaptive humanoid robots through the FARSA open-source framework. Adaptive Behavior, 1-11.
Massera G., Tuci E., Ferrauto T., Nolfi S. (2010). The facilitatory role of linguistic instructions on developing manipulation skills, IEEE Computational Intelligence Magazine, (5) 3: 33-42.
Tuci E., Ferrauto T., Zeschel A., Massera G., Nolfi S. (2011). An Experiment on behaviour generalisation and the emergence of linguistic compositionality in evolving robots, IEEE Transactions on Autonomous Mental Development, (3) 2: 176-189
Tuci E., Massera G., Nolfi S. (2010). Active categorical perception of object shapes in a simulated anthropomorphic robotic arm, Transaction on Evolutionary Computation Journal, (14) 6: 885-899.