Compensation Methods for Industrial Robotics Under Varying Payloads with Deep Reinforcement Learning
نویسندگان
چکیده
Due to the weak rigidity of an industrial robot, its end effector usually has poor absolute positioning accuracy, especially under varying payloads. Such situation is common in scenarios handling, machining and tool changing. Conventional off-line calibration or compensation methods can only eliminate systematic errors, while such are invalid dynamic errors brought by This paper proposes a deep reinforcement learning(DRL) approach solve problem consideration external payloads changed manually. An online full closed loop system established verify proposed method, which consists KUKA robot KR6, Leica laser tracker, BECKHOFF PLC controller. The tracker work as slavers master controller, between communication accomplished using EtherCAT. Logically, controlled mxAutomation connected embedded EtherCAT slave card. Experiments on demonstrate effectiveness DRL methods. range from 1.177Kg 4.179 Kg, position accuracy be maintained no more than 0.4mm algorithm.
منابع مشابه
Massively Parallel Methods for Deep Reinforcement Learning
We present the first massively distributed architecture for deep reinforcement learning. This architecture uses four main components: parallel actors that generate new behaviour; parallel learners that are trained from stored experience; a distributed neural network to represent the value function or behaviour policy; and a distributed store of experience. We used our architecture to implement ...
متن کاملAsynchronous Methods for Deep Reinforcement Learning
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neura...
متن کاملAccelerated Methods for Deep Reinforcement Learning
Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turnaround time remains a key bottleneck in research and in practice. We investigate how to optimize existing deep RL algorithms for modern computers, specifically for a combination of CPUs and GPUs. We confirm that both policy gradient and Q-value learning algorithms can be adapted to learn using many parallel ...
متن کاملEfficient Parallel Methods for Deep Reinforcement Learning
We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to on-policy, off-policy, value based and policy gradient based algorithms. Given its inherent parallelism, the framework can be efficiently implemented on a GPU, ...
متن کاملReinforcement Learning for Humanoid Robotics
Reinforcement learning offers one of the most general framework to take traditional robotics towards true autonomy and versatility. However, applying reinforcement learning to high dimensional movement systems like humanoid robots remains an unsolved problem. In this paper, we discuss different approaches of reinforcement learning in terms of their applicability in humanoid robotics. Methods ca...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Advances in transdisciplinary engineering
سال: 2022
ISSN: ['2352-751X', '2352-7528']
DOI: https://doi.org/10.3233/atde221198