Visual Spatial Attention and Proprioceptive Data-Driven Reinforcement Learning for Robust Peg-in-Hole Task Under Variable Conditions
This work addresses the problem of robust robotic automation in construction environments with variable conditions, representing an incremental improvement over existing methods.
The authors tackled the automation of anchor-bolt insertion in construction, a peg-in-hole task under variable lighting and surface conditions, by developing a vision and proprioceptive data-driven robot control model that achieved higher success rates and shorter completion times than baselines in evaluations with 12 unknown holes and 16 initial positions.
Anchor-bolt insertion is a peg-in-hole task performed in the construction field for holes in concrete. Efforts have been made to automate this task, but the variable lighting and hole surface conditions, as well as the requirements for short setup and task execution time make the automation challenging. In this study, we introduce a vision and proprioceptive data-driven robot control model for this task that is robust to challenging lighting and hole surface conditions. This model consists of a spatial attention point network (SAP) and a deep reinforcement learning (DRL) policy that are trained jointly end-to-end to control the robot. The model is trained in an offline manner, with a sample-efficient framework designed to reduce training time and minimize the reality gap when transferring the model to the physical world. Through evaluations with an industrial robot performing the task in 12 unknown holes, starting from 16 different initial positions, and under three different lighting conditions (two with misleading shadows), we demonstrate that SAP can generate relevant attention points of the image even in challenging lighting conditions. We also show that the proposed model enables task execution with higher success rate and shorter task completion time than various baselines. Due to the proposed model's high effectiveness even in severe lighting, initial positions, and hole conditions, and the offline training framework's high sample-efficiency and short training time, this approach can be easily applied to construction.