Volume 1 Issue 1, January 2019

Ken Goldberg reflects on how four exciting sub-fields of robotics — co-robotics, human–robot interaction, deep learning and cloud robotics — accelerate a renewed trend toward robots working safely and constructively with humans.

Debate about the impacts of AI is often split into two camps, one associated with the near term and the other with the long term. This divide is a mistake — the connections between the two perspectives deserve more attention, say Stephen Cave and Seán S. ÓhÉigeartaigh.

To be useful in a variety of daily tasks, robots must be able to interact physically with humans and infer how to be most helpful. A new theory for interactive robot control allows a robot to learn when to assist or challenge a human during reaching movements.

Memristor-based chips could lead the way to fast, energy-efficient AI hardware accelerators.

A new vision for robot engineering, building on advances in computational materials techniques, additive and subtractive manufacturing as well as evolutionary computing, describes how to design a range of specialized robots uniquely suited to specific tasks and environmental conditions.

Arguably one of the most promising as well as critical applications of deep learning is in supporting medical sciences and decision making. It is time to develop methods for systematically quantifying uncertainty underlying deep learning processes, which would lead to increased confidence in practical applicability of these approaches.

Deep neural networks have become very successful at certain machine learning tasks partly due to the widely adopted method of training called backpropagation. An alternative way to optimize neural networks is by using evolutionary algorithms, which, fuelled by the increase in computing power, offers a new range of capabilities and modes of learning.

Robots need to estimate and adapt to human behaviour, especially when human dynamics change over time. Now adaptive game theory controllers can help robots adapt to human behaviour in a reaching task.

Not all mathematical questions can be resolved, according to Gödel’s famous incompleteness theorems. It turns out that machine learning can be vulnerable to undecidability too, as is illustrated with an example problem where learnability cannot be proved nor refuted.

Deep neural networks are increasingly popular in data-intensive applications, but are power-hungry. New types of computer chips that are suited to the task of deep learning, such as memristor arrays where data handling and computing take place within the same unit, are required. A well-used deep learning model called long short-term memory, which can handle temporal sequential data analysis, is now implemented in a memristor crossbar array, promising an energy-efficient and low-footprint deep learning platform.

Most machine learning approaches extract statistical features from data, rather than the underlying causal mechanisms. A different approach analyses information in a general way by extracting recursive patterns from data using generative models under the paradigm of computability and algorithmic information theory.

Yuanfang Guan explains how taking part in data challenges has helped her learn new analytical techniques and creatively apply them on a variety of datasets.