Multi-Critic Reinforcement Learning for Garment Handling: Addressing Unpredictability in Temporal-Phase Continuous Contact Tasks

This research unveils a novel Multi-Critic Reinforcement Learning framework designed to navigate the multifaceted challenges associated with multi-phased garment handling tasks, notably marked by persistent contact and erratic deformations between textiles and solid bodies. These tasks, ubiquitous in domestic and industrial environments, encompass activities such as dressing, fabric printing, and pressing, and are complicated by the unpredictability of textile states and the intricacy of devising control strategies. Our reinforcement learning model combines multiple time-sequenced Critic networks with traditional Deep Deterministic Policy Gradient (DDPG) techniques, thereby equipping the system to adapt to the diverse effects of fabric distortions throughout various stages. The effectiveness of this approach is demonstrated through a multi-phase pre-printing operation and further validated by real-world implementations, showing significant improvements in coverage and a substantial reduction in wrinkle formation, with its versatility further confirmed by a complex vertical dressing task. We anticipate future applications of this framework in a range of complex problems, not just garment handling. The model used in this paper can be found at https://github.com/jkk5454/multiddpg.git. Note to Practitioners—This paper addresses garment handling challenges where deformable clothes are in continuous contact with objects, such as pulling a T-shirt over a print bench before silk printing and dressing in a vertical hanger. Unlike previous research focusing on handling clothes in the air (like folding or unfolding), we tackle the complexities introduced by continuous contact, which can alter a garment’s shape and affect the task. We segment these tasks into distinct phases and employ Multi-Critic Reinforcement Learning to evaluate each phase, enabling us to predict their overall impact. Specifically, we divide a task like pulling a T-shirt over a workbench of the pre-printing tasks in garment printing into three phases and use Multi-Critic DDPG to generate control trajectories for a flat, correctly positioned surface. The practical applicability of our algorithm was further validated through experiments involving the dragging task on a realistic printing board and the vertical dressing task using an ironing board. This approach aims to facilitate garment handling tasks like dragging, dressing, and ironing, involving multiple phases and continuous contact with obstacles. However, the current simulation environment significantly differs from the real world, challenging policy transfer. Future work will concentrate on narrowing this simulation-to-reality gap.