Abstract-- Hard-constraint trajectory planners often rely on commercial solvers and demand substantial computational resources. Existing soft-constraint methods achieve faster computation, but either (1) decouple spatial and temporal optimization or (2) restrict the search space. T o overcome these limitations, we introduce MIGHTY, a Hermite spline-based planner that performs spatiotemporal optimization while fully leveraging the continuous search space of a spline. In simulation, MIGHTY achieves a 9.3% reduction in computation time and a 13.1% reduction in travel time over state-of-the-art baselines, with a 100% success rate. In hardware, MIGHTY completes multiple high-speed flights up to 6.7 m/s in a cluttered static environment and long-duration flights with dynamically added obstacles. Trajectory planning for autonomous navigation has been extensively studied, with a wide variety of parameterizations and formulations [3], [6], [7], [9], [12], [14]-[17], [19]-[23].

A tiny California start-up is looking to printers to solve the housing crisis – actually, a very large 3D printer. The company, Mighty Buildings, has been showcasing small (350 square foot) studio apartment models of its new "ADU" units (Accessory Dwelling Units) aimed at backyards and selling for around $115,000. That is, if you do the work and deal with local governments to get all the permits, connect the utilities and install the unit. Have Mighty set it up for you, and you're looking around $184,000. Sam Ruben, the co-founder of the firm, says Mighty can have the home in place in just over two weeks.

Train a neural network on flawed data and you'll have one that makes lots of mistakes. Most neural networks learn to distinguish between things by sampling different groups. This is supervised learning, and it only works if someone labels the data first so that the network knows what it's looking at. But how can you find the "right" data to train your AI, and confirm its quality? Well, what you feed your machine might surprise you.

Last year, we saw VR surge in prominence, but our picks this year are more conventional -- not to mention more diverse. The usual suspects include the iPhone X and Surface Laptop for getting helping us get things done, and the Nintendo Switch and the Sonos One for their ability to let us luxuriate at home and on the road. There's some more unexpected stuff on our list, too, like the easy-to-use DJI Spark drone as well as the Mighty, a tiny music player that won over much of the Engadget staff. Ultimately, we appreciated these picks for the ways they made our lives more pleasant, even if only a little. Apple's latest iPhone is a radical departure from the company's tried-and-true smartphone formula, but you'd better get used to it.

NATIONAL HARBOR, Md -- In comments that conjure up dystopian images of a future dominated by robot soldiers controlled by Skynet, researchers with the Pentagon's futuristic think tank said they are working on better ways to merge the rapid decision making of computers with the analytical capabilities of humans. In fact, scientists at the Defense Advanced Research Projects agency, or DARPA, are even looking into advanced neuroscience in hopes of one day merging computerized artificial intelligence with the human brain. "I think the future [of] warfighting is going to look a lot more like less incredibly smart people working with more incredibly smart machines," said DARPA Deputy Director Steve Walker during a briefing with reporters at the 2016 Air Force Association Air, Space and Cyber conference here. "And how those two things come together is going to define how we move forward." Walker said researchers are already finding ways to help machines better collaborate with human operators.