BMW employs artificial intelligence for electric car
German car maker BMW AG is employing artificial intelligence (AI) to promote its first fully electric production car through an automated information service for UK customers, it said in a statement on 27 August. BMW i Genius uses specially developed software to interact with potential customers in a live question and answer format that works on a mobile platform. Users simply text in a question relating to BMW i and the BMW i Genius system will instantly respond with a detailed and helpful answer, the statement said. The adaptive system is capable of interpreting words, the context and the sentiment behind each question to respond. Subsequent questions can be asked, allowing an informative, real-time conversation. The system was developed by London Brand Management in a partnership facilitated by a business accelerator programme based in London’s Tech City called The Bakery and media agency Vizeum. To use the BMW i Genius service, users need to text their question to the phone shortcode 84737. The AI programme will activate and generate a response regarding the BMW i3 or i8. Two BMW i cars are confirmed for production, the fully-electric BMW i3 megacity vehicle and the plug-in hybrid BMW i8 sports car.
Scientists develop 3D mapping in real time
Computer scientists at MIT and National University of Ireland (NUI) at Maynooth have developed a mapping algorithm that creates dense, highly detailed 3D maps of indoor and outdoor environments in real time, according to a 28 August statement. The researchers tested their algorithm on videos taken with a low-cost Kinect camera, including one that explores the serpentine halls and stairways of MIT’s Stata Center. Applying their mapping technique to these videos, the researchers created rich, 3D maps as the camera explored its surroundings. As the camera circled back to its starting point, the researchers found that after returning to a location recognized as familiar, the algorithm was able to quickly stitch images together to effectively close the loop, creating a continuous, realistic 3D map in real time, the statement said. The technique solves a major problem in the robotic mapping community that’s known as loop closure or drift. As a camera pans across a room or travels down a corridor, it invariably introduces slight errors in the estimated path taken. A doorway may shift a bit to the right, or a wall may appear slightly taller than it is. Over relatively long distances, these errors are magnified, resulting in a disjointed map, with walls and stairways that don’t exactly line up.