Pose-aware object recognition on a mobile platform via learned geometric representations

Mobile robot operations are becoming increasingly sophisticated in terms of robust environment perception and levels of automation. However, exploiting the great representational power of data-hungry learned representations is not straightforward, as robotic tasks typically target diverse scenarios with different sets of objects. Learning specific attributes of frequently occurring object categories such as pedestrians and vehicles, is feasible since labeled data-sets are plenty. On the other hand, less common object categories call for the need of use-case-specific data acquisition and labelling campaigns, resulting in efforts which are not sustainable with a growing number of scenarios. In this paper we propose a structure-aware learning scheme, which represents geometric cues of specific functional objects (airport loading ramp) in a highly invariant manner, permitting learning solely from synthetic data, and also leading to a great degree of generalization in real scenarios. In our experiments we employ monocular depth estimation for generating depth and surface normal data and in order to express geometric traits instead of appearance. Using the surface normals, we explore two different representations to learn structural elements of the ramp object and decode its 3D pose: as a set of key-points and as a set of 3D bounding boxes. Results are demonstrated and validated in a series of robotic transportation tasks, where the different representations are compared in terms of recognition and metric space accuracy. Te proposed learning scheme can be also easily applied to recognize arbitrary manmade functional objects (e.g. containers, tools) with and without known dimensions.