Problem Space Transformations for Generalisation in Behavioural Cloning

The behavioural cloning (BC) paradigm has been the foundation of recent advances in robotic manipulation [1, 2]. BC is particularly promising for robot manipulation, as humans are very proficient in general manipulation, and can quickly learn to collect demonstrations when given a well-designed interface [3]. An important benefit of using this data to train a robot policy is that it can be collected on the real system, thus avoiding the sim-to-real gap. However, as a supervised learning method, BC requires the collected data to cover the workspace with relatively high density [4, 5, 6]. Neural networks trained with BC, and more generally functions estimated through supervised learning, hardly generalise outside the support of the training data, i.e. "out-of-distribution" (OOD) [7, 8].