Learning Relative Interactions through Imitation
This is an incremental improvement for robotics in handling object-relative interactions, addressing sensor ambiguities from symmetries.
The paper tackled the problem of training a neural network via imitation learning to move a robot to a fixed pose relative to an object, achieving very good performance with little training data, but found more work needed for arbitrary poses.
In this project we trained a neural network to perform specific interactions between a robot and objects in the environment, through imitation learning. In particular, we tackle the task of moving the robot to a fixed pose with respect to a certain object and later extend our method to handle any arbitrary pose around this object. We show that a simple network, with relatively little training data, is able to reach very good performance on the fixed-pose task, while more work is needed to perform the arbitrary-pose task satisfactorily. We also explore the effect of ambiguities in the sensor readings, in particular caused by symmetries in the target object, on the behaviour of the learned controller.