Early detection of pulmonary nodules in computed tomography (CT) images is essential for successful outcomes among lung cancer patients. Much attention has been given to deep convolutional neural network (DCNN)-based approaches to this task, but models have relied at least partly on 2D or 2.5D components for inherently 3D data. In this paper, we introduce a novel DCNN approach, consisting of two stages, that is fully three-dimensional end-to-end and utilizes the state-of-the-art in object detection. First, nodule candidates are identified with a U-Net-inspired 3D Faster R-CNN trained using online hard negative mining. Second, false positive reduction is performed by 3D DCNN classifiers trained on difficult examples produced during candidate screening. Finally, we introduce a method to ensemble models from both stages via consensus to give the final predictions. By using this framework, we ranked first of 2887 teams in Season One of Alibaba's 2017 TianChi AI Competition for Healthcare.

This paper addresses a variant of multi-agent path finding (MAPF) in continuous space and time. We present a new solving approach based on satisfiability modulo theories (SMT) to obtain makespan optimal solutions. The standard MAPF is a task of navigating agents in an undirected graph from given starting vertices to given goal vertices so that agents do not collide with each other in vertices of the graph. In the continuous version (MAPF$^\mathcal{R}$) agents move in an $n$-dimensional Euclidean space along straight lines that interconnect predefined positions. For simplicity, we work with circular omni-directional agents having constant velocities in the 2D plane. As agents can have different sizes and move smoothly along lines, a non-colliding movement along certain lines with small agents can result in a collision if the same movement is performed with larger agents. Our SMT-based approach for MAPF$^\mathcal{R}$ called SMT-CBS$^\mathcal{R}$ reformulates the Conflict-based Search (CBS) algorithm in terms of SMT concepts. We suggest lazy generation of decision variables and constraints. Each time a new conflict is discovered, the underlying encoding is extended with new variables and constraints to eliminate the conflict. We compared SMT-CBS$^\mathcal{R}$ and adaptations of CBS for the continuous variant of MAPF experimentally.

Stanford University launched its Institute for Human-Centered AI on Monday. Known as Stanford HAI, the institute's charter is to develop new technologies while guiding AI's impact on the world, wrestle with ethical questions, and come up with helpful public policies. The Institute intends to raise US $1 billion to put towards this effort. The university kicked off Stanford HAI (pronounced High) with an all-day symposium that laid out some of the issues the institute aims to address while showcasing Stanford's current crop of AI researchers. The most anticipated speaker on the agenda was Microsoft co-founder Bill Gates.

A version of this article appears in the IEEE Robotics & Automation Magazine (Volume 26, Issue 1, March 2019). In mid-November, we received the sad news that Alphabet is closing SCHAFT, a spinoff of the University of Tokyo robotics lab. The decision comes one year after Boston Dynamics was sold to SoftBank, the company that also acquired Aldebaran Robotics (known for the Pepper and Nao robots). During the 2018 IEEE/Robotics Society of Japan International Conference on Intelligent Robots and Systems, we heard that Rethink Robotics, which created the collaborative robot industry and had a large impact on our view of robots in industrial applications, had closed its doors. Some months before, Jibo and Mayfield Robotics, makers of Kuri, were forced to shut down sales and operations.

In the past four months, airports have been brought to a standstill by the sight of drones hovering above runways. Last week, rules came into force in the UK that make it illegal to fly drones within 5 kilometres of an airport. But is there anything more we can do to stop them becoming a weaponised nuisance?

A swarm of robots inspired by living cells can squeeze through gaps and keep moving even if many of its parts fail. Living cells gather together and collectively migrate under certain conditions, such as when inflammatory cells travel through the bloodstream to a wound site to help the healing process. To mimic this, Hod Lipson at Columbia University in New York and his colleagues created 25 disc-shaped robots that can join together. Each is equipped with cogs that cause the robot's outer shell to expand and contract and magnets around its perimeter that let it stick to neighbouring bots. Individually, the bots can't move, but once stuck together, the swarm can slither across a surface by making individual bots expand and contract at different times.

The world's smallest bears copy one another's facial expressions as a means of communication. A team at the University of Portsmouth, UK, studied 22 sun bears at the Bornean Sun Bear Conservation Centre in Malaysia. In total, 21 matched the open-mouthed expressions of their playmates during face-to-face interactions. When they were facing each other, 13 bears made the expressions within 1 second of observing a similar expression from their playmate. "Mimicking the facial expressions of others in exact ways is one of the pillars of human communication," says Marina Davila-Ross, who was part of the team.

The 2020 Democratic candidates are out of the gate and the pollsters have the call! Bernie Sanders is leading by two lengths with Kamala Harris and Elizabeth Warren right behind, but Cory Booker and Beto O'Rourke are coming on fast! The political horse-race season is upon us and I bet I know what you are thinking: "Stop!" Every election we complain about horse-race coverage and every election we stay glued to it all the same. The problem with this kind of coverage is not that it's unimportant.

Film is a universal language of modern societies. Larger-than-life images, stories, ideas, and characters portrayed in films can speak across the globe. This makes science and technology--which have shaped the modern world but remain little understood and poorly integrated into mainstream culture--a rich subject for film and a goldmine for filmmakers. From the mad scientist films of the '20s and '30s to the postnuclear dystopias of the '50s; and from the ecological disaster flics of the '70s and '80s to the space adventures of recent years, films have periodically reflected society's hopes and fears about science. But we can do better when it comes to dramatizing the great, ongoing human enterprise to understand and enhance the world around and inside us.

Late last year, I picked up John Carreyrou's "Bad Blood," which chronicles the long con pulled by Elizabeth Holmes, an entrepreneur who dropped out of Stanford at nineteen to found Theranos, a company that she claimed would reinvent the biomedical industry. I was instantly engrossed--"Bad Blood" unfolds like a thriller, offering a breathless barrage of details exposing how Holmes deceived her investors and colleagues at nearly every turn. Holmes wanted to disrupt the blood test: she boasted that her company was developing a method for running hundreds of lab tests from a single drop of blood, employing a machine called "The Edison" that used nanotechnology and robotics to analyze the sample. In just a few short years, thanks to Carreyrou's investigations and leaks from whistle-blowers, Holmes went from Silicon Valley's golden girl--named the youngest self-made female billionaire by Forbes--to a disgraced fraudster whose company was under investigation by the U.S. Securities and Exchange Commission. "Bad Blood" does a formidable job charting the Theranos ordeal, but it doesn't get into Holmes's head.