Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision making tasks with a non-trivial element of exploration requires either specifying carefully designed reward functions or relying on indiscriminate, novelty seeking exploration bonuses. Human supervisors can provide effective guidance in the loop to direct the exploration process, but prior methods to leverage this guidance require constant synchronous high-quality human feedback, which is expensive and impractical to obtain. In this work, we propose a technique - Human Guided Exploration (HUGE), that is able to leverage low-quality feedback from non-expert users, which is infrequent, asynchronous and noisy, to guide exploration for reinforcement learning, without requiring careful reward specification. The key idea is to separate the challenges of directed exploration and policy learning - human feedback is used to direct exploration, while self-supervised policy learning is used to independently learn unbiased behaviors from the collected data.

Dragonfly is scheduled to begin exploring Titan by 2034 using a series of multi-kilometer surface flights. This paper outlines the preliminary design of the navigation filter for the Dragonfly Mobility subsystem. The software architecture and filter formulation for lidar, visual odometry, pressure sensors, and redundant IMUs are described in detail. Special discussion is given to developments to achieve multi-kilometer surface flights, including optimizing sequential image baselines, modeling correlating image processing errors, and an efficient approximation to the Simultaneous Localization and Mapping (SLAM) problem.

Fink and team have published a paper in Advances in Space Research that details a "communication network that would link rovers, lake landers, and even submersible vehicles through a so-called mesh topology network, allowing the machines to work together as a team, independently from human input," according to a press release. The scientists named their patent-pending concept the "Breadcrumb-Style Dynamically Deployed Communication Network" paradigm or DDCN, based on the fairy tale'Hansel and Gretel'. According to Fink, DDCN could help resolve one of NASA's Space Technology Grand Challenges by helping overcome the limited ability of current technology to safely traverse environments on comets, asteroids, moons, and planetary bodies. "If you remember the book, you know how Hansel and Gretel dropped breadcrumbs to make sure they'd find their way back. In our scenario, the'breadcrumbs' are miniaturized sensors that piggyback on the rovers, which deploy the sensors as they traverse a cave or other subsurface environment," explained Fink.

Artificial intelligence is already changing the world by making life simpler and more convenient for all of us. It blocks unwanted emails and knows exactly what we like on Netflix. It can even predict future health issues so we can take the necessary steps to prevent them. AI is also having an effect on our careers. There are very few industries that are not currently being disrupted.

Artificial intelligence (AI) continues to grow from strength to strength, penetrating various industries including the finance, medical, automotive and aviation industries all over the world, and goes beyond just being technology's artificial interaction with a person or system. British semiconductor and software design company, ARM, which designs chips for Apple's Macbooks, for example, recently introduced a'next-gen chip design' focused on AI as it will "continue to grow more central to mobile computing over the next several years, both through the proliferation of smart-assistants, autonomous vehicles, and beyond." This proliferation has extended to marketing as well - with AI, there's continual, real-time, automatic optimisation based on large-scale response data which allows marketers to tailor communication with each individual according to their needs, thus impacting the customer journey. According to an article by McKinsey & Company, a customer reaching a decision to buy an item isn't at the end of his or her journey, but rather at the beginning of another. More than 60 per cent of people who bought facial skin care products, for instance, do further research online after making a purchase - a touch point which McKinsey calls "unimaginable" when the idea of the marketing funnel was conceived.

Velo3D, based in Santa Clara, Calif., has 22.1 million in venture investment to do something in 3-D printing: That makes it fourth among 2015's best-funded stealth-mode tech companies in the United States, according to CB Insights. This dollar number is about all the hard news that has come out of this startup, founded in 2014 by Benyamin Butler and Erel Milshtein. But job postings, talks at conferences, and other breadcrumbs left along Velo3D's development trail--has created a sketchy outline of this company's plans. Consider which 3-D printing technology is ready for disruption: metal. Printing of metal objects--done regularly in industry, particularly aerospace--uses a different, and, to date, far more expensive technology: selective laser sintering.

Video Friday is your weekly selection of awesome robotics videos, collected by your mysophobic Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. XDog is a small electric quadruped designed and built by Xing Wang, a graduate student at Shanghai University, with support from his adviser Jia Wenchuan. The robot has 12 motors (each leg has 3 DoF), and uses force sensors on each foot, IMU, and joint-angle sensors for control.