Exploring the use of deep learning in task-flexible ILC
Growing demands in today's industry results in increasingly stringent performance and throughput specifications. For accurate positioning of high-precision motion systems, feedforward control plays a crucial role. Nonetheless, conventional model-based feedforward approaches are no longer sufficient to satisfy the challenging performance requirements. An attractive method for systems with repetitive motion tasks is iterative learning control (ILC) due to its superior performance. However, for systems with non-repetitive motion tasks, ILC is {generally} not applicable, {despite of some recent promising advances}. In this paper, we aim to explore the use of deep learning to address the task flexibility constraint of ILC. For this purpose, a novel Task Analogy based Imitation Learning (TAIL)-ILC approach is developed. To benchmark the performance of the proposed approach, a simulation study is presented which compares the TAIL-ILC to classical model-based feedforward strategies and existing learning-based approaches, such as neural network based feedforward learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningImitation LearningSimilar Papers 제목 키워드 기반
Exploring representation learning for flexible few-shot tasks
Existing approaches to few-shot learning deal with tasks that have persistent, rigid notions of classes. Typically, the learner observes data only from a fixed number of classes at training time and is asked to generaliz…
Few-Shot LearningRepresentation LearningGroup Anomaly Detection using Flexible Genre Models
An important task in exploring and analyzing real-world data sets is to detect unusual and interesting phenomena. In this paper, we study the group anomaly detection problem. Unlike traditional anomaly detection research…
Anomaly DetectionGroup Anomaly DetectionExploring a Continuous and Flexible Representation of the Lexicon
We aim at showing that lexical descriptions based on multifactorial and continuous models can be used by linguists and lexicographers (and not only by machines) so long as they are provided with a way to efficiently navi…
NavigateSemantic Textual SimilaritySuperScaler: Supporting Flexible DNN Parallelization via a Unified Abstraction
With the growing model size, deep neural networks (DNN) are increasingly trained over massive GPU accelerators, which demands a proper parallelization plan that transforms a DNN model into fine-grained tasks and then sch…
GPUSchedulingControlVAR: Exploring Controllable Visual Autoregressive Modeling
Conditional visual generation has witnessed remarkable progress with the advent of diffusion models (DMs), especially in tasks like control-to-image generation. However, challenges such as expensive computational cost, h…
Image Generation