Design and control of an automatic high-viscosity sealant filling system

In this article, a novel vision-based automatic liquid filling control system is proposed. The method can be used for many high-viscosity liquid filling applications, especially for packaging of fuel tank sealant in the aerospace industry. Due to the high viscosity and highly adhesive properties, filling and packaging this type of liquid can have challenges in terms of time and cost. A new control scheme based on motion synchronization with vision feedback is proposed in this article, which enables a new filling method for this type of liquid. The method can effectively resolve the challenges and enable an efficient filling process. Considering the time delay caused by image processing of the vision system, the Smith delay compensator is employed with an iterative learning control framework to improve the reliability of the feedback control under disturbances. The hardware implementation and experimental results demonstrate the convergence of tracking errors over the learning iterations, proving the effectiveness of the proposed control algorithm.

A robotic shared control teleoperation method based on learning from demonstrations

In teleoperation, the operator is often required to command the motion of the remote robot and monitor its behavior. However, such an interaction demands a heavy workload from a human operator when facing with complex tasks and dynamic environments. In this article, we propose a shared control method to assist the operator in the manipulation tasks to reduce the workload and improve the efficiency. We adopt a task-parameterized hidden semi-Markov model to learn a manipulation skill from several human demonstrations. We utilize the learned model to predict the manipulation target given the current observed robotic motion trajectory and subsequently estimate the desired robotic motion given the current input of the operator. The estimated robotic motion is then utilized to correct the input of the operator to provide manipulation assistance. In addition, a set of virtual reality devices are used to capture the operator’s motion and display the vision feedback from the remote site. We evaluate our approach through two manipulation tasks with a dual-arm robot. The experimental results show the effectiveness of the proposed method.