In this era of active development of autonomous vehicles, it becomes crucial to provide driving systems with the capacity to explain their decisions. In this work, we focus on generating high-level driving explanations as the vehicle drives. We present BEEF, for BEhavior Explanation with Fusion, a deep architecture which explains the behavior of a trajectory prediction model. Supervised by annotations of human driving decisions justifications, BEEF learns to fuse features from multiple levels. Leveraging recent advances in the multi-modal fusion literature, BEEF is carefully designed to model the correlations between high-level decisions features and mid-level perceptual features. The flexibility and efficiency of our approach are validated with extensive experiments on the HDD and BDD-X datasets.

According to the recently published Dice 2020 Tech Job Report, data engineer was the fastest-growing tech occupation in 2019, with a 50% year-over-year growth in the number of open job positions. As data engineering is a relatively new job category, I often get questions about what I do from people who are interested in pursuing it as a career. In this blog post, I will share my own story of becoming a data engineer and answer some frequently asked questions about data engineering. A couple of years ago, before becoming a data engineer, I mainly worked on database and application development (plus scale and performance testing). I loved working with RDBMS and data so much that I decided to pursue an engineering career that focuses on Big Data.

Alphabet's Loon has been using algorithmic processes to optimize the flight of its stratospheric balloons for years now -- and setting records for time spent aloft as a result. But the company is now deploying a new navigation system that has the potential to be much better, and it's using true reinforcement-learning AI to teach itself to optimize navigation better than humans ever could. Loon developed the new reinforcement-learning system, which it says is the first to be used in an actual product aerospace context, with its Alphabet colleagues at Google AI in Montreal over the past couple of years. Unlike its past algorithmic navigation software, this one is devised entirely by machine -- a machine that's able to calculate the optimal navigation path for the balloons much more quickly than the human-made system could, and with much more efficiency, meaning the balloons use much less power to travel the same or greater distances than before. How does Loon know it's better?

Efficiently navigating a superpressure balloon in the stratosphere1 requires the integration of a multitude of cues, such as wind speed and solar elevation, and the process is complicated by forecast errors and sparse wind measurements. Coupled with the need to make decisions in real time, these factors rule out the use of conventional control techniques2,3. Here we describe the use of reinforcement learning4,5 to create a high-performing flight controller. Our algorithm uses data augmentation6,7 and a self-correcting design to overcome the key technical challenge of reinforcement learning from imperfect data, which has proved to be a major obstacle to its application to physical systems8. We deployed our controller to station Loon superpressure balloons at multiple locations across the globe, including a 39-day controlled experiment over the Pacific Ocean.

Alphabet's Loon has shifted to a different type of navigation system for its internet-beaming balloons. Rather than relying on algorithms designed by humans, the balloons are using an artificial intelligence system Loon developed with Google AI over the last few years. A reinforcement learning (RL) system is now in charge of navigation for a fleet of balloons over Kenya, where Loon switched on its first commercial service earlier this year. Loon says this is the first use of an RL model in "a production aerospace system." It also noted the "development is exciting because it shows that reinforcement learning can be applied to real-world use cases."

High-flying balloons are bringing broadband connectivity to remote nations and post-disaster zones where cell towers have been knocked out. These "super-pressure" helium-filled polyethylene bags float 65,000 feet up in the stratosphere, above commercial planes, hurricanes, and pretty much anything else. But keeping a fleet of tennis-court-sized, internet-blasting balloons hovering over one spot has been a tricky engineering problem, just like keeping a boat floating in one place on a fast-moving river. Now researchers at Google spinoff Loon have figured out how to use a form of artificial intelligence to allow the balloon's onboard controller to predict wind speed and direction at various heights, then use that information to raise and lower the balloon accordingly. The new AI-powered navigation system opens the possibility of using stationary balloons to monitor animal migrations, the effects of climate change, or illegal cross-border wildlife or human trafficking from a relatively inexpensive platform for months at a time.

In November of 2018, the South China Morning Post reported that researchers from the Chinese Academy of Sciences intend to construct an underwater base in the South China Sea. According to the report, not only would the base be populated with AI robots, but the machines are expected to run it autonomously. Aside from this information, most elements of the project have remained under wraps – until now. Now, details are emerging about what could be the world's first Artificial Intelligence colony. With access to prototypes and scientific documents, New Scientists created a picture of what to expect.

But then there was the Chinese game of go (pictured), estimated to be 4000 years old, which offers more "degrees of freedom" (possible moves, strategy, and rules) than chess (2 10170). As futurist George Gilder tells us, in Gaming AI, it was a rite of passage for aspiring intellects in Asia: "Go began as a rigorous rite of passage for Chinese gentlemen and diplomats, testing their intellectual skills and strategic prowess. Later, crossing the Sea of Japan, Go enthralled the Shogunate, which brought it into the Japanese Imperial Court and made it a national cult." Then AlphaGo, from Google's DeepMind, appeared on the scene in 2016: As the Chinese American titan Kai-Fu Lee explains in his bestseller AI Super-powers,8 the riveting encounter between man and machine across the Go board had a powerful effect on Asian youth. Though mostly unnoticed in the United States, AlphaGo's 2016 defeat of Lee Sedol was avidly watched by 280 million Chinese, and Sedol's loss was a shattering experience. The Chinese saw DeepMind as an alien system defeating an Asian man in the epitome of an Asian game.

China launched its Chang'e 5 mission to the moon early Tuesday morning local time from the country's launch site on Hainan Island in the South China Sea. The country is seeking to bring soil and rock samples from the lunar surface back to Earth for the first time in its history, for scientific study. What's going to happen: Chang'e 5 should make it to the moon on November 27. The entire mission consists of four parts: an orbiter, a lander, an ascent stage, and a return capsule. The spacecraft are not equipped with any heating units to help the onboard electronics withstand the super-cold temperatures of the lunar night. That means the mission must collect its sample and start heading back to Earth within 14 days (the length of the lunar day).

China launched its Chang'e 5 spacecraft on 23 November, in the first mission designed to bring moon rocks back to Earth in more than four decades. The uncrewed Chang'e 5 probe will attempt to collect at least 2 kilograms of lunar dust and debris from the northern region of the Oceanus Procellarum, a previously unvisited area on the near side of the moon. If successful, the Chang'e 5 return mission will make China only the third country, after the US and the Soviet Union, to have retrieved samples from the moon. The last sample return mission was carried out in 1976 by the Soviet Union's Luna 24 robotic probe, which brought back around 170 grams to Earth. The Chang'e 5 launch happened early on Tuesday morning, Beijing time, from a Long March 5 rocket at a site in Wenchang on Hainan Island in the South China Sea.