A human-based genetic algorithm applied to the problem of learning in-hand manipulation tasks
نویسندگان
چکیده
The in-hand manipulation problem with anthropomorphic robotic hands constitutes a challenging area of research. While imitation learning and programming by demonstration have demonstrated to help in this problem, other supervised learning techniques providing more interactivity between an expert teacher and the robot have several advantages. The humanbased genetic algorithm is able to enhance such interactivity. In this work, some experiments applied to the learning of simple inhand manipulation primitives using this relatively new paradigm will demonstrate its scope.
منابع مشابه
A hybrid model based on machine learning and genetic algorithm for detecting fraud in financial statements
Financial statement fraud has increasingly become a serious problem for business, government, and investors. In fact, this threatens the reliability of capital markets, corporate heads, and even the audit profession. Auditors in particular face their apparent inability to detect large-scale fraud, and there are various ways to identify this problem. In order to identify this problem, the majori...
متن کاملA New Hybrid Meta-Heuristics Approach to Solve the Parallel Machine Scheduling Problem Considering Human Resiliency Engineering
This paper proposes a mixed integer programming model to solve a non-identical parallel machine (NIPM) scheduling with sequence-dependent set-up times and human resiliency engineering. The presented mathematical model is formulated to consider human factors including Learning, Teamwork and Awareness. Moreover, processing time of jobs are assumed to be non-deterministic and dependent to their st...
متن کاملTask Complexity Manipulation and EFL learners’ interactions in the process of collaborative pre-planning
Today, learners’ interaction and collaborative task performance have attracted increasing attention from language teachers and researchers. The present study investigated whether collaborative pre-planning, task complexity manipulation, and language proficiency level play a role in learners’ interactions. To this end, 128 EFL learners from two different language proficiency levels carried out t...
متن کاملA multi-objective genetic algorithm for a mixed-model assembly U-line balancing type-I problem considering human-related issues, training, and learning
Mixed-model assembly lines are increasingly accepted in many industrial environments to meet the growing trend of greater product variability, diversification of customer demands, and shorter life cycles. In this research, a new mathematical model is presented considering balancing a mixed-model U-line and human-related issues, simultaneously. The objective function consists of two separate com...
متن کاملA knowledge-based NSGA-II approach for scheduling in virtual manufacturing cells
This paper considers the job scheduling problem in virtual manufacturing cells (VMCs) with the goal of minimizing two objectives namely, makespan and total travelling distance. To solve this problem two algorithms are proposed: traditional non-dominated sorting genetic algorithm (NSGA-II) and knowledge-based non-dominated sorting genetic algorithm (KBNSGA-II). The difference between these algor...
متن کامل