We consider the task of generating segmentation masks for the target object from an object manipulation instruction, which allows users to give open vocabulary instructions to domestic service robots. Conventional segmentation generation approaches often fail to account for objects outside the camera's field of view and cases in which the order of vertices differs but still represents the same polygon, which leads to erroneous mask generation. In this study, we propose a novel method that generates segmentation masks from open vocabulary instructions. We implement a novel loss function using optimal transport to prevent significant loss where the order of vertices differs but still represents the same polygon. To evaluate our approach, we constructed a new dataset based on the REVERIE dataset and Matterport3D dataset. The results demonstrated the effectiveness of the proposed method compared with existing mask generation methods. Remarkably, our best model achieved a +16.32% improvement on the dataset compared with a representative polygon-based method.

It's no secret that filters can transform us into almost anything - whether it be a dog or a dancing hotdog. But Snapchat has now taken this up a notch, with the launch of a new tool that uses artificial intelligence (AI) to completely reimagine your photographs. The so-called'Dreams' feature will allow users to create fantasy-themed AI selfies in just a few taps - and the results are unbelievably realistic. Deep-sea mermaids and Renaissance-era royals are among the initial pack of eight complimentary Dreams that can be created, while others start at $0.99. The AI tool will be launched first in Australia and New Zealand, before making its way to other Snapchatters across the globe in a couple of weeks.

Understanding the 3D geometry of a 2D image makes it possible to improve applications like mixed reality, photo editing, self-driving cars, and robotics.

Transforming your camera's RAW sensor data into a usable image is calculation-intensive and sometimes, your computer doesn't have the muscle to get it right. For the next version of Lightroom, Adobe has introduced a feature called "Enhance Details" that uses AI to tackle the process, called "demosaicing." The neural network works on Bayer images (Canon, Nikon, Sony, Olympus) as well as X-Trans (Fujifilm) to increase detail while reducing problems like moire and false colors. Demoisaicing is particularly tricky in parts of an image with lots of texture, detail and colors. "Myriad mathematical calculations are required to perform the interpolation necessary to build an image," Adobe stated in a white paper.

Maybe you've read the statistics on how many drones are filling our skies: The FAA anticipates 7 million by 2020. Perhaps you've heard about how drones are revolutionizing commercial operations. It's possible you know someone who has a drone of their own, or seen a quadcopter hovering over your local park. The reality is there's no shortage of drones filling our homes, stores, skies, and seas. It should come as no surprise that the technology is steadily making its way into our media.

These methods and ideas are discussed here. LOLA's console and see an LOLA's hard drive had decided to crash Performing all computation on board has several advantages: The video data are not corrupted by radio-transmission noise, commands are not lost, and there's no communication lag that might result in These findings are consistent with those of previous competitors (Nourbakhsh, Powers, and Birchfield 1995). On the down side, the on-board image processor contributes significantly to the battery drain, which is partly the result of its intended desktop use. Still, we are able to get about two hours of operation to each charge. Nomadic Technologies is currently making efforts to offer a version that is better suited for mobile robot use. Figure 1.

We have developed an autonomous robot system that takes well-composed photographs of people at social events, such as weddings and conference receptions. In this article, we outline the overall architecture of the system and describe how the various components interrelate. We also describe our experiences deploying the robot photographer at a number of real-world events. The system is capable of operating in unaltered environments and has been deployed at a number of real-world events. This article gives an overview of the entire robot photographer system, and provides details of the architecture underlying the implementation.

In this article we give a summary of three components of the exhibition: the Small-Scale Manipulation Challenge: Robotic Chess; the Learning by Demonstration Challenge; and the Education Track. We also describe the participating teams, highlight the research questions they tackled, and briefly describe the systems they demonstrated. The program has a long tradition of demonstrating innovative research at the intersection of robotics and artificial intelligence. In both the workshop and exhibition portions of the event, we strive to have the robotics program be a venue that pushes the science of embodied AI forward. Over the past few years, a central point of the event has been the discussion of common robot platforms and software, with the primary goal of focusing the research community's energy toward common "challenge" tasks.

Fleet owners are very interested in filling their boats as fast as possible with the fewest and most qualified personnel, thus reserving maximum occupancy for their refrigerated storage. During an expedition, which can last between one to two weeks, the fish processing machinery operates around the clock (figure 1). Typically, fishes are brought on the boat and dropped into metal pockets that convey them through cleaning, cutting, and filleting machines. Anomalies, which must be detected at the beginning of the chain, include a fish of the wrong species or a damaged fish. Such anomalies must be rejected immediately.

"As if the debate over immigration and guest worker programs wasn't complicated enough, now a couple of robots are rolling into the middle of it. Vision Robotics, a San Diego company, is working on a pair of robots that would trundle through orchards plucking oranges, apples or other fruit from the trees. In a few years, troops of these machines could perform the tedious and labor-intensive task of fruit picking that currently employs thousands of migrant workers each season. The robotic work has been funded entirely by agricultural associations, and pushed forward by the uncertainty surrounding the migrant labor force. Farmers are'very, very nervous about the availability and cost of labor in the near future,' says Vision Robotics CEO Derek Morikawa."