Long Time Sequential Task Learning From Unstructured Demonstrations
نویسندگان
چکیده
منابع مشابه
Complex Task Learning from Unstructured Demonstrations
A simple system that allows end-users to intuitively program robots is a key step in getting robots out of the laboratory and into the real world. Although in many cases it is possible for an expert to successfully program a robot to perform complex tasks, such programming requires a great deal of knowledge, is time-consuming, and is often task-specific. In response to this, much recent work ha...
متن کاملSemantically Grounded Learning from Unstructured Demonstrations
SEMANTICALLY GROUNDED LEARNING FROM UNSTRUCTURED DEMONSTRATIONS
متن کاملLearning grounded finite-state representations from unstructured demonstrations
Robots exhibit flexible behavior largely in proportion to their degree of knowledge about the world. Such knowledge is often meticulously hand-coded for a narrow class of tasks, limiting the scope of possible robot competencies. Thus, the primary limiting factor of robot capabilities is often not the physical attributes of the robot, but the limited time and skill of expert programmers. One way...
متن کاملIntentionGAN: Multi-Modal Imitation Learning from Unstructured Demonstrations
Traditionally, imitation learning has focused on using isolated demonstrations of a particular skill [3]. The demonstration is usually provided in the form of kinesthetic teaching, which requires the user to spend sufficient time to provide the right training data. This constrained setup for imitation learning is difficult to scale to real world scenarios, where robots have to be able to execut...
متن کاملLearning Complex Manipulation Tasks from Heterogeneous and Unstructured Demonstrations
Motivated by the current state-of-the-art in Robot Learning from Demonstration (LfD), in this paper, we tackle two central issues in the learning pipeline: namely, dealing with (1) heterogeneity and (2) unstructuredness in demonstrations of complex manipulation tasks. We build upon our previous work on transform-invariant segmentation and action discovery [1], to learn the underlying action seq...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2019
ISSN: 2169-3536
DOI: 10.1109/access.2019.2929107