BROWSE
Detail
Conference Paper
Learning a High-quality Robotic Wiping Policy Using Systematic Reward Analysis and Visual-Language Model Based Curriculum
Cited 0 time in 
Share 
Share
- Authors
- Yihong Liu, Dongyeop Kang, Sehoon Ha
- Issue Date
- 2025-05
- Citation
- International Conference on Robotics and Automation (ICRA) 2025, pp.2347-2353
- Language
- English
- Type
- Conference Paper
- Abstract
- Autonomous robotic wiping is an important task in various industries, ranging from industrial manufacturing to sanitization in healthcare. Deep reinforcement learning (Deep RL) has emerged as a promising algorithm, however, it often suffers from a high demand for repetitive reward engineering. Instead of relying on manual tuning, we first analyze the convergence of quality-critical robotic wiping, which requires both high-quality wiping and fast task completion, to show the poor convergence of the problem and propose a new bounded reward formulation to make the problem feasible. Then, we further improve the learning process by proposing a novel visual-language model (VLM) based curriculum, which actively monitors the progress and suggests hyperparameter tuning. We demonstrate that the combined method can find a desirable wiping policy on surfaces with various curvatures, frictions, and waypoints, which cannot be learned with the baseline formulation. The demo of this project can be found at: https://sites.google.com/view/highqualitywiping
- KSP Keywords
- Combined Method, Deep reinforcement learning, High-quality, Industrial manufacturing, Learning Process, Reinforcement learning(RL), language models, model-based, task completion, various curvatures