METHODS OF TASK AND MOTION PLANNING FOR ROBOTS: APPLICATIONS AND LIMITATIONS
-
Published:2023-10-06
Issue:04
Volume:16
Page:20-27
-
ISSN:2733-2055
-
Container-title:ETM - Equipment, Technologies, Materials
-
language:en
-
Short-container-title:ETM
Author:
Aygun Guseynova Aygun Guseynova,Javad Aliyev Javad Aliyev
Abstract
Robots are increasingly required to perform more complex tasks, which in turn demand advanced planning algorithms. Task and Motion Planning (TAMP) methods, studied for decades, have made significant progress but still face various challenges. This document provides an overview of TAMP's development, encompassing problem-solving, simulation environments, methods, and remaining limitations. It particularly compares different simulation environments and methods used in various tasks, offering a practical guide and overview for beginners. Task planning is typically seen as planning in discrete spaces, while motion planning deals with continuous spaces. Significant progress has been made in integrating discrete and continuous planning methods to address TAMP problems. A recent survey has focused on TAMP integration, summarizing various methods for solving multimodal motion planning and TAMP problems. It introduces general concepts but primarily focuses on methods that operate in fully observable environments, which are far from real-world applications. Additionally, it demonstrates TAMP problem-solving in a theoretical manner that may not be user-friendly for beginners looking to apply these methods in practice. Therefore, this article aims to provide a practical and broader overview to readers, facilitating an easy entry into the field of TAMP for solving various tasks.
Keywords: task and motion planning, simulation environment, learning methods, TAMP.
Publisher
Education Support and Investment Fund NGO
Reference8 articles.
1. Barto, A. G. and Mahadevan, S. (2003). Recent advances in hierarchical reinforcement learning. Discrete event dynamic systems, 13(1):41–77. 2. Chitnis, R., Hadfield-Menell, D., Gupta, A., Srivastava, S., Groshev, E., Lin, C., and Abbeel, P. (2016). Guided search for task and motion plans using learned heuristics. In 2016 IEEE International Conference on Robotics and Automation (ICRA), pages 447–454 IEEE. 3. Driess, D., Ha, J.-S., and Toussaint, M. (2020). Deep visual reasoning: Learning to predict action sequences for task and motion planning from an initial scene image. In Robotics: Science and Systems 2020 (RSS 2020) RSS Foundation. 4. Gan, C., Schwartz, J., Alter, S., Mrowca, D., Schrimpf, M., Traer, J., De Freitas, J., Kubilius, J., Bhandwaldar, A., Haber, N., et al. (2021). Threedworld: A platform for interactive multi-modal physical simulation. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1). 5. Garrett, C. R., Chitnis, R., Holladay, R., Kim, B., Silver, T., Kaelbling, L. P., and Lozano-P´erez, T. (2021). Integrated task and motion planning. Annual review of control, robotics, and autonomous systems, 4:265–293.
|
|