다중 로봇 제조 물류 작업을 위한 안전성과 효율성 학습
Safety and Efficiency Learning for Multi-Robot Manufacturing Logistics Tasks
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
With the recent increase of multiple robots cooperating in smart manufacturing logistics environments, it has become very important how to predict the safety and efficiency of the individual tasks and dynamically assign them to the best one of available robots. In this paper, we propose a novel task policy learner based on deep relational reinforcement learning for predicting the safety and efficiency of tasks in a multi-robot manufacturing logistics environment. To reduce learning complexity, the proposed system divides the entire safety/efficiency prediction process into two distinct steps: the policy parameter estimation and the rule-based policy inference. It also makes full use of domain-specific knowledge for policy rule learning. Through experiments conducted with virtual dynamic manufacturing logistics environments using NVIDIA’s Isaac simulator, we show the effectiveness and superiority of the proposed system.
Abstract
With the recent increase of multiple robots cooperating in smart manufacturing logistics environments, it has become very important how to predict the safety and efficiency of the individual tasks and dynamically assign them to the best one of available robots. In this paper, we propose a novel task policy learner based on deep relational reinforcement learning for predicting the safety and efficiency of tasks in a multi-robot manufacturing logistics environment. To reduce learning complexity, the proposed system divides the entire safety/efficiency prediction process into two distinct steps: the policy parameter estimation and the rule-based policy inference. It also makes full use of domain-specific knowledge for policy rule learning. Through experiments conducted with virtual dynamic manufacturing logistics environments using NVIDIA’s Isaac simulator, we show the effectiveness and superiority of the proposed system.
참고문헌 (16)
- Edward Tunstel, "Rule–based reasoning and neural network perception for safe off–road robot mobility", Expert Systems, 19(4), pp.191~200 (2002), Wiley[DOI]
- Arne Kreutzmann, "Towards Safe Navigation by Formalizing Navigation Rules", TransNav, the International Journal on Marine Navigation and Safety of Sea Transportation, 7(2), pp.161~168 (2013), Faculty of Navigation[DOI]
- Z. Jiang, "Neural Logic Reinforcement Learning", Machine Learning (2019)[DOI]
- A. Payani, "Incorporating Relational Background Knowledge into Reinforcement Learning via Differentiable Inductive Logic Programming", Machine Learning (2020)
- Maximiliano Rojas, "An Easy to Use Deep Reinforcement Learning Library for AI Mobile Robots in Isaac Sim", Applied Sciences, 12(17), pp.8429~ (2022), MDPI AG[DOI]
- V. Mnih, "Playing atari with deep reinforcement learning", Machine Learning (2013)[DOI]
- J. Schulman, "Proximal Policy Optimization Algorithms", Machine Learning (2017)
- Richard Evans, "Learning Explanatory Rules from Noisy Data", Journal of Artificial Intelligence Research, 61, pp.1~64 (2018), AI Access Foundation[DOI]
- A. Payani, "Inductive Logic Programming via Differentiable Deep Neural Logic Networks", Artificial Intelligence (2019)
- O. Rivlin, "Generalized Planning With Deep Reinforcement Learning", Artificial Intelligence (2020)
- V. Zambaldi, "Relational Deep Reinforcement Learning", Machine Learning (2018)[DOI]
- J. Janisch, "Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks", Machine Learning (2021)
- S. Garg, "Symbolic Network: Generalized Neural Policies for Relational MDPs", the 37th International conference on machine learning (2020)
- D. Adjodah, "Symbolic Relation Networks for Reinforcement Learning", 32nd Conference on Neural Information Processing Systems (NIPS 2018) (2018)
- S. Das, "Fitted Q-Learning for Relational Domains", Machine Learning (2020)
- T. Gokhale, "Blocksworld Revisited : Learning and Reasoning to Generate Event-Sequences from Image Pairs", Computer Vision and Pattern Recognition (2019)