Learning Visual Affordances with Target-Orientated Deep Q-Network to Grasp Objects by Harnessing Environmental Fixtures

TL;DR

This paper presents a self-supervised deep reinforcement learning approach for robotic grasping that leverages environmental fixtures, using a novel Target-Oriented Deep Q-Network to learn visual affordances for complex object grasping tasks.

Contribution

It introduces a new visual affordance learning method with TO-DQN, enabling robots to grasp objects using environmental fixtures without prior knowledge.

Findings

TO-DQN outperforms standard DQN in training efficiency and robustness.

The learned policy achieves human-comparable performance in simulation and real-world tests.

The approach effectively generalizes across different environment settings.

Abstract

This paper introduces a challenging object grasping task and proposes a self-supervised learning approach. The goal of the task is to grasp an object which is not feasible with a single parallel gripper, but only with harnessing environment fixtures (e.g., walls, furniture, heavy objects). This Slide-to-Wall grasping task assumes no prior knowledge except the partial observation of a target object. Hence the robot should learn an effective policy given a scene observation that may include the target object, environmental fixtures, and any other disturbing objects. We formulate the problem as visual affordances learning for which Target-Oriented Deep Q-Network (TO-DQN) is proposed to efficiently learn visual affordance maps (i.e., Q-maps) to guide robot actions. Since the training necessitates robot's exploration and collision with the fixtures, TO-DQN is first trained safely with a simulated robot manipulator and then applied to a real robot. We empirically show that TO-DQN can learn to solve the task in different environment settings in simulation and outperforms a standard and a variant of Deep Q-Network (DQN) in terms of training efficiency and robustness. The testing performance in both simulation and real-robot experiments shows that the policy trained by TO-DQN achieves comparable performance to humans.