Ai Motion Control – A Generic Approach to Develop Control Policies for Robotic Manipulation Tasks

Abstract

Current robotic solutions are able to manage specialized tasks, but they cannot perform intelligent actions which are based on experience. Autonomous robots that are able to succeed in complex environments like production plants need the ability to customize their capabilities. With the usage of artificial intelligence (AI) it is possible to train robot control policies without explicitly programming how to achieve desired goals. We introduce AI Motion Control (AIMC) a generic approach to develop control policies for diverse robots, environments and manipulation tasks. For safety reasons, but also to save investments and development time, motion control policies can first be trained in simulation and then transferred to real applications. This work uses the descriptive study I according to Blessing and Chakrabarti and is about the identification of this research gap. We combine latest motion control and reinforcement learning results and show the potential of AIMC for robotic technologies with industrial use cases.

A review of AI-assisted motion control

“…Model-based system engineering covered by digital twins and AI can be employed to monitor and process big data sets and "tune" the production a step further [10] . Philip et al [11] introduce AI Motion Control (AIMC) as a generic approach to developing adaptive control policies to succeed in complex environments without predefined programming. However, adaptive motion control is mainly for various robotics manipulations, not for general motion control.…”

Methods of Intelligent Control in Mechatronics and Robotic Engineering: A Survey

“…Schematically, the reinforcement learning procedure is shown in Figure 2. Kurrek et al [24] described a general approach to developing a control policy for various robots, environments, and manipulative tasks. The environment can be either physical or virtual, implemented as a computer program.…”

Review of Deep Reinforcement Learning-Based Object Grasping: Techniques, Open Challenges, and Recommendations

“…The push policies were trained in simulation, and the learning was subsequently transferred to a real robot. However, this approach requires augmented reality tags (AR-tags), which are developed in the constrained context of detecting and pushing an object with a robot arm against a uniform green-screen backdrop [160]. A learning push policy to drive mobile robots outdoors was presented in [161].…”