Purpose
This paper aims to present an optimization algorithm combined with the impedance control strategy to optimize the robotic dual peg-in-hole assembly task, and to reduce the assembly time and smooth the contact forces during assembly process with a small number of experiments.
Design/methodology/approach
Support vector regression is used to predict the fitness of genes in evolutionary algorithm, which can reduce the number of real-world experiments. The control parameters of the impedance control strategy are defined as genes, and the assembly time is defined as the fitness of genes to evaluate the performance of the selected parameters.
Findings
The learning-based evolutionary algorithm is proposed to optimize the dual peg-in-hole assembly process only requiring little prior knowledge instead of modeling for the complex contact states. A virtual simulation and real-world experiments are implemented to demonstrate the effectiveness of the proposed algorithm.
Practical implications
The proposed algorithm is quite useful for the real-world industrial applications, especially the scenarios only allowing a small number of trials.
Originality/value
The paper provides a new solution for applying optimization techniques in real-world tasks. The learning component can solve the data efficiency of the model-free optimization algorithms.
Towards computer-assisted neurosurgery, scene understanding algorithms for microscope video data are required. Previous work utilizes optical flow to extract spatiotemporal context from neurosurgical video sequences. However, to select an appropriate optical flow method, we need to analyze which algorithm yields the highest accuracy for the neurosurgical domain. Currently, there are no benchmark datasets available for neurosurgery. In our work, we present an approach to generate synthetic data for optical flow evaluation on the neurosurgical domain. We simulate image sequences and thereby take into account domainspecific visual conditions such as surgical instrument motion. Then, we evaluate two optical flow algorithms, Farneback and PWC-Net, on our synthetic data. Qualitative and quantitative assessments confirm that our data can be used to evaluate optical flow for the neurosurgical domain. Future work will concentrate on extending the method by modeling additional effects in neurosurgery such as elastic background motion.
Machine learning-based solutions rely heavily on the quality and quantity of the training data. In the medical domain, the main challenge is to acquire rich and diverse annotated datasets for training. We propose to decrease the annotation efforts and further diversify the dataset by introducing an annotation-efficient learning workflow. Instead of costly pixel-level annotation, we require only image-level labels as the remainder is covered by simulation. Thus, we obtain a large-scale dataset with realistic images and accurate ground truth annotations. We use this dataset for the instrument localization activity task together with a studentteacher approach. We demonstrate the benefits of our workflow compared to state-of-the-art methods in instrument localization that are trained only on clinical datasets, which are fully annotated by human experts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.