Tomorrow is Today

More Robot Tool-Use: Wheeled Robot Builds a Ramp to Climb a Box

Researchers from Harvard University and Worcester Polytechnic Institute have taken inspiration from animals like weaver birds, termites, and beavers, and developed robots capable of using cheap materials to build large structures.

…Beavers (and weaver birds) build things by sticking together large numbers of sticks. This new robot can do something very similar with prefabricated sticks (toothpicks) and glue.

…the robot in question has a deposition mechanism with which it “flings” individual toothpicks after adding glue to them. While it has approximately zero control over placing the toothpicks into any sort of arrangement that would make structural sense, the sheer number of toothpicks plus a generous helping of glue means that eventually, the bot can build ramps or anything else that on some level consists of a random pile of wood and glue.

(via [IROS 2012] Robot Builds Ramp by Randomly Flinging 3,600 Toothpicks - IEEE Spectrum)

UPDATE: Google’s Cat-Video Identifying Neural Net Now Working to Improve Voice Commands, Image Search, Google Glass and Self-Driving Cars

Google is now using these neural networks to recognize speech more accurately, a technology increasingly important to Google’s smartphone operating system, Android, as well as the search app it makes available for Apple devices.

“We got between 20 and 25 percent improvement in terms of words that are wrong,” says Vincent Vanhoucke, a leader of Google’s speech-recognition efforts. “That means that many more people will have a perfect experience without errors.”

The neural net is so far only working on U.S. English, and Vanhoucke says similar improvements should be possible when it is introduced for other dialects and languages.

Other Google products will likely improve over time with help from the new learning software. The company’s image search tools, for example, could become better able to understand what’s in a photo without relying on surrounding text. And Google’s self-driving cars and mobile computer built into a pair of glasses could benefit from software better able to make sense of more real-world data.

(via Google Puts Its Virtual Brain Technology to Work - Technology Review)

See Also: “Google and Stanford have created the [digital equivalent of the] visual cortex of an infant human”

KPMG Report Sees Autonomous Cars in Dealerships Before 2020

Autonomous cars will be in showrooms as early as 2019, or maybe even sooner, according to a report released by KPMG and the Center for Automotive Research,

The report’s authors explain that “sensor-based technologies” and “connected-vehicle communications” need to converge. Essentially, cars need to be able to communicate with other vehicles on the road so they don’t bash into each other. They also need the ability to sense and respond to the surrounding infrastructure: stop signs, street lights, guardrails, and many other basic transportation signals.

(via Self-driving cars in 2019, report says | KurzweilAI)

3,000 Vehicle Test of Wifi Crash-Avoidance System Will Largest Ever Real-World Test of Smart Car Tech

The researchers plan to install wireless communication devices on nearly 3,000 vehicles that will let passenger cars, commercial trucks, and transit buses “talk” to each other, as well as to traffic lights and other road signals located at intersections, curves and highway sites throughout a test-pilot area in northeast Ann Arbor.

The connected vehicle technology involves both vehicle-to-vehicle and vehicle-to-infrastructure communications that transmit and receive vehicle data such as position, speed and direction. Drivers are alerted to a potential crash situation —such as a nearby vehicle unexpectedly braking, a sudden lane change, merging traffic, etc. — by a visual or audible warning inside their vehicles. The data generated and archived as part of the project will be used to inform future regulatory and policy decisions by the USDOT.

(via A 3,000-vehicle test of wireless crash-avoidance system | KurzweilAI)

Antivirus Researchers Examining Vulnerability of Smart Cars

As automakers add more and more technology to their vehicles, they’re also making them increasingly vulnerable to the same security flaws that affect PCs and mobile devices.

While the effects — and likelihood — of remote attacks are unknown, flaws in cars’ systems could theoretically be exploited to steal the vehicle, eavesdrop on a driver’s conversation, or even lead to navigation systems becoming confused and potentially cause accidents.

Studies have already proven that it is technically possible to hack into a car’s on-board warning systems and alter its tire pressure, as well as prevent it from using its brakes. To date, however, there have been no severe attacks on vehicles through viruses.

Nevertheless, Intel-owned McAfee has a number of staff, based in a West Coast garage, checking out ways to protect the new generation of technology-packed cars.

(via McAfee looks to combat vehicle viruses | Cutting Edge - CNET News)

Drone Manufacturers Look To Domestic Markets As Military Spending Slows

This year’s show is cast against a backdrop that is somewhat austere for the many, many robotics systems makers who exhibit here. Most of them do the majority of their businesses with governments around the world, many of which—like the United States—are facing huge cuts in military spending and a slowdown in the acquisition of new technologies.

But when the age of austerity closes a door, Congress every so often opens a window. The mandated integration of unmanned systems into the U.S. national airspace by 2015 has many makers of unmanned aerial systems looking to apply their technology to civilian skies, while unmanned ground vehicle makers are making inroads into spaces like telepresence, site security, ground-based infrastructure inspection, and cargo logistics.

(via The Coolest Warbots, Drones, and Unmanned Tech at the Robotic Systems Show | Popular Science)

EU to Mandate Autonomous Emergency Braking for Commercial Vehicles in 2013

New rules coming down from the European Commission will require all commercial vehicles to be fitted with autonomous emergency braking (AEB) technology by November 2013, and passenger vehicles could soon follow suit.

These cars will go beyond simply sending a signal to the driver when they detect an impending collision via radar, lidar (that’s like radar but with light), or video sensors and apply the brakes themselves.

…proponents of the system think it could drastically curtail traffic accidents (particularly fender benders at low speeds) and save billions of euros annually across Europe by reducing the economic productivity lost to accident-related congestion. One study commissioned by the EC showed traffic accidents could be cut by more than a quarter.

(via Europe Will Require New Vehicles to Include Autonomous Self-Braking System | Popular Science)

Micro-Drones Improving Intelligence, Autonomous Capabilities Point to Bigger Role in Military

…researchers led by Roland Brockers at the NASA Jet Propulsion Laboratory in Pasadena, California, have developed a MAV that uses a camera pointed at the ground to navigate and pick landing spots. It can even identify people and other objects. The system enables the drone to travel through terrain where human control and GPS are unavailable, such as a city street or inside a building.

A human operator needs to tell the drone only two things before it sets off: where it is and where its objective is. The craft figures out the rest for itself, using the camera and onboard software to build a 3D map of its surroundings. It can also avoid obstacles and detect surfaces above a predetermined height as possible landing zones. Once it selects a place to put down, it maps the site’s dimensions, moves overhead and lands.

In a laboratory experiment, a 50 centimetre by 50 centimetre quadrotor craft equipped with the navigation system was able to take off, travel through an obstacle-filled indoor space and land successfully on an elevated platform. Brockers’s team is now testing the system in larger, more complex environments.

…Vijay Kumar of the University of Pennsylvania in Philadelphia says that autonomous navigation and landing capabilities are unprecedented in a drone of this size. “Typically the information required to locate a landing site and stabilise a vehicle over it is coming in at a 100 times a second,” he says. “No one else has been able to design a system so small with this kind of processing power.”

(via Micro-drones: The new face of cutting-edge warfare - tech - 23 July 2012 - New Scientist)

Army Tech to Be Used in Domestic Drones to Prevent Accidents

Back in February Congress directed the Federal Aviation Administration to fast-track the integration of unmanned aerial systems into the U.S. national airspace, but it didn’t tell the FAA how exactly to do this.

To fly unmanned drones in shared airspace with conventional manned aircraft (or with other drones) is dangerous without a means for planes to know where other aircraft—manned and unmanned—are.

Termed “sense and avoid” (or “see and avoid”) this technology is a key but difficult piece of our drone-enabled future, and the Army just took some huge steps toward making it a reality.

The Army just wrapped a two-week trial of its Ground-Based Sense and Avoid system (GBSAA), and the results were overwhelmingly positive. There are two ways to accomplish sense and avoid: either imbue every aircraft with the sensor technology or the autonomous smarts to know when it comes into close proximity with another aircraft, or create a ground-based system that acts as a kind of automated air traffic controller for drones, notifying UAVs and their pilots when they are on dangerous paths, prompting them to alter courses.

The Army has been testing the latter for use around its domestic bases via a series of “vignettes” in which it used live Shadow unmanned aircraft to demonstrate the viability of their system. In each trial, an aircraft under control by the GBSAA was threatened by an “intruder” aircraft entering the airspace. In each scenario, the system was able to recognize the potential danger in plenty of time and divert the drone under its supervision to a new path out of harm’s way.

(via Army’s Smart ‘Sense and Avoid’ System Key to Letting Drones Cruise Domestic Skies | Popular Science)