The agent acquires a vocabulary of neuro-symbolic concepts for objects, relations, and actions, represented through a ...
Abstract: We propose a new approach to solving the problem of intention estimation in human-robot teleoperation for assembly tasks, which includes task estimation and action prediction. Our approach ...
If you are planning a trip through several cities and want to find the shortest route, you resort to algorithms, a well-defined sequence of deterministic operations. This article accompanies the ...
GluonTS is a Python toolkit for probabilistic time series modeling, built around Apache MXNet (incubating). GluonTS provides utilities for loading and iterating over time series datasets, state of the ...
Abstract: Post-training quantization (PTQ) is an effective solution for deploying deep neural networks on edge devices with limited resources. PTQ is especially attractive because it does not require ...