PERCH: Perception via Search for Multi-Object Recognition and Localization

TL;DR

PERCH introduces a generative, search-based approach for multi-object recognition and localization that guarantees optimal scene explanation and performs well under occlusion, surpassing traditional discriminative methods.

Contribution

The paper presents a novel optimization framework for multi-object recognition, formulating it as a combinatorial search on a Monotone Scene Generation Tree, with guarantees of optimality.

Findings

Successfully localizes objects under heavy occlusion.

Outperforms state-of-the-art methods in challenging scenarios.

Guarantees the best scene explanation under the defined cost function.

Abstract

In many robotic domains such as flexible automated manufacturing or personal assistance, a fundamental perception task is that of identifying and localizing objects whose 3D models are known. Canonical approaches to this problem include discriminative methods that find correspondences between feature descriptors computed over the model and observed data. While these methods have been employed successfully, they can be unreliable when the feature descriptors fail to capture variations in observed data; a classic cause being occlusion. As a step towards deliberative reasoning, we present PERCH: PErception via SeaRCH, an algorithm that seeks to find the best explanation of the observed sensor data by hypothesizing possible scenes in a generative fashion. Our contributions are: i) formulating the multi-object recognition and localization task as an optimization problem over the space of hypothesized scenes, ii) exploiting structure in the optimization to cast it as a combinatorial search problem on what we call the Monotone Scene Generation Tree, and iii) leveraging parallelization and recent advances in multi-heuristic search in making combinatorial search tractable. We prove that our system can guaranteedly produce the best explanation of the scene under the chosen cost function, and validate our claims on real world RGB-D test data. Our experimental results show that we can identify and localize objects under heavy occlusion--cases where state-of-the-art methods struggle.