Grasp Synthesis for Novel Objects Using Heuristic-based and Data-driven Active Vision Methods

TL;DR

This paper introduces heuristic-based and data-driven active vision strategies to optimize viewpoint selection for robotic grasping, supported by a simulation benchmark and real-world experiments, demonstrating their effectiveness and robustness.

Contribution

It presents a comprehensive benchmarking platform and evaluates novel active vision methods for grasp synthesis, highlighting their versatility and robustness over existing strategies.

Findings

Heuristic methods effectively prioritize exploration types.

Strategies show robustness to novel objects and simulation-to-real transfer.

Identified challenging scenarios for current methods.

Abstract

In this work, we present several heuristic-based and data-driven active vision strategies for viewpoint optimization of an arm-mounted depth camera for the purpose of aiding robotic grasping. These strategies aim to efficiently collect data to boost the performance of an underlying grasp synthesis algorithm. We created an open-source benchmarking platform in simulation (https://github.com/galenbr/2021ActiveVision), and provide an extensive study for assessing the performance of the proposed methods as well as comparing them against various baseline strategies. We also provide an experimental study with a real-world setup by utilizing an existing grasping planning benchmark in the literature. With these analyses, we were able to quantitatively demonstrate the versatility of heuristic methods that prioritize certain types of exploration, and qualitatively show their robustness to both novel objects and the transition from simulation to the real world. We identified scenarios in which our methods did not perform well and scenarios that are objectively difficult, and present a discussion on which avenues for future research show promise.