Imitation learning through a demonstration interface is expected to learn policies for robot automation from intuitive human demonstrations. However, due to the differences in human and robot movement characteristics, a human expert might unintentionally demonstrate an action that the robot cannot execute. We propose feasibility-aware behavior cloning from observation (FABCO). In the FABCO framework, the feasibility of each demonstration is assessed using the robot's pre-trained forward and inverse dynamics models. This feasibility information is provided as visual feedback to the demonstrators, encouraging them to refine their demonstrations. During policy learning, estimated feasibility serves as a weight for the demonstration data, improving both the data efficiency and the robustness of the learned policy. We experimentally validated FABCO's effectiveness by applying it to a pipette insertion task involving a pipette and a vial. Four participants assessed the impact of the feasibility feedback and the weighted policy learning in FABCO. Additionally, we used the NASA Task Load Index (NASA-TLX) to evaluate the workload induced by demonstrations with visual feedback.

I had thought my job was safe from automation--a computer couldn't possibly replicate the complex creativity of human language in writing or piece together a coherent story. I may have been wrong. Authors beware, because an AI-written novel just made it past the first round of screening for a national literary prize in Japan. The novel this program co-authored is titled, The Day A Computer Writes A Novel. It was entered into a writing contest for the Hoshi Shinichi Literary Award.

It was a dark, overcast day, with clouds hovering low. The room was kept at the most appropriate temperatures and humidity, as usual. Yoko sat on a couch in an untidy manner, killing time with a silly game. But she would not talk to me. So begins a short story titled "A day when a computer writes fiction."

I had thought my job was safe from automation--a computer couldn't possibly replicate the complex creativity of human language in writing or piece together a coherent story. I may have been wrong. Authors beware, because an AI-written novel just made it past the first round of screening for a national literary prize in Japan. The novel this program co-authored is titled, The Day A Computer Writes A Novel. It was entered into a writing contest for the Hoshi Shinichi Literary Award.

A novel written by artificial intelligence was a finalist in Japan's Hoshi Shinichi Literary Award. The award is named after Hoshi Shinichi, a Japanese science fiction author whose books include The Whimsical Robot and Greetings from Outer Space. The unique contest accepts submissions from humans and machines, and judges for the prize, now in its third year, weren't told which novels were written by humans and which were penned by human-AI teams. This year was the first time the committee received submissions written by AI programs. The AI's novel is called The Day A Computer Writes A Novel, or Konpyuta ga shosetsu wo kaku hi in Japanese.

Many AIs are developed to sift through and make sense of Big Data. But behind-the-scenes, others are acquiring softer human skills and deploying their algorithms to make art. On Monday, Hitoshi Matsubara, a professor of computer science from the Future University in Hakodate in northern Japan, announced that his research team's short-form novel--co-created with an AI--had passed the initial screening of a domestic literary competition. Though their creation didn't nab the grand prix, the human-machine collaboration showed the early promises of what could be, if the team's AI is refined in the future. "So far, AI programs have often been used to solve problems that have answers, such as Go and shogi," said Matsubara, in a report by the Yomiuri Shimbun.

"The day a computer wrote a novel. The computer, placing priority on the pursuit of its own joy, stopped working for humans." A pretty profound line--considering this sentence is part of a book that was actually co-authored by an artificial intelligence (AI). While it may not have won the top prize, this short-form novel, which was a collaboration between humans and an AI program, managed to make it through the first round of screening for a national literary prize in Japan called the Nikkei Hoshi Shinichi Literary Award. Titled'The Day A Computer Writes A Novel,' the short story was a team effort between human authors, led by Hitoshi Matsubara from the Future University Hakodate, and, well, a computer. Matsubara, who selected words and sentences for the book, set the parameters for the AI to construct the novel before letting the program take over and essentially "write" the novel by itself.

As the English striker Gary Lineker famously said, "Football is a very simple game. For 90 minutes, 22 men go running after the ball, and at the end, the Germans win." Although the game is simple, analyzing it can be hard. Just what makes one team better than another? How much difference do tactics make? Is there really such a thing as a "lucky win?" Here, we try to answer these questions in the context of RoboCup. We take the giant set of log data produced by the simulator tournaments from 1997 to 1999 and feed it to a data-munching program that produces statistics on important game features. Using these statistics, we identify precisely what has improved in RoboCup and what still requires further work. Plus, because the data muncher can work in real time, we can also release it as a proxy server for RoboCup. This proxy server gives all RoboCup developers instant access to statistics while a game is in progress and is a promising step toward an important goal: understanding RoboCup.