Think fast, robot: Algorithm that harnesses data from new sensor could make autonomous robots more nimble

May 29, 2014 by Larry Hardesty

One of the reasons we don't yet have self-driving cars and mini-helicopters delivering online purchases is that autonomous vehicles tend not to perform well under pressure. A system that can flawlessly parallel park at 5 mph may have trouble avoiding obstacles at 35 mph.

Part of the problem is the time it takes to produce and interpret data. An autonomous vehicle using a standard camera to monitor its surroundings might take about a fifth of a second to update its location. That's good enough for normal operating conditions but not nearly fast enough to handle the unexpected.

Andrea Censi, a research scientist in MIT's Laboratory for Information and Decision Systems, thinks the solution could be to supplement cameras with a new type of sensor called an event-based (or "neuromorphic") sensor, which can take measurements a million times a second.

At this year's International Conference on Robotics and Automation, Censi and Davide Scaramuzza of the University of Zurich present the first state-estimation —the type of algorithm robots use to gauge their position—to process data from event-based sensors. A running their algorithm could update its location every thousandth of a second or so, allowing it to perform much more nimble maneuvers.

"In a regular camera, you have an array of sensors, and then there is a clock," Censi explains. "If you have a 30-frames-per-second camera, every 33 milliseconds the clock freezes all the values, and then the values are read in order." With an event-based sensor, by contrast, "each pixel acts as an independent sensor," Censi says. "When a change in luminance—in either the plus or minus direction—is larger than a threshold, the pixel says, 'I see something interesting' and communicates this information as an event. And then it waits until it sees another change."

Featured event

When a standard state-estimation algorithm receives an image from a robot-mounted camera, it first identifies "features": gradations of color or shade that it takes to be boundaries between objects. Then it selects a subset of those features that it considers unlikely to change much with new perspectives.

Thirty milliseconds later, when the camera fires again, the algorithm performs the same type of analysis and starts trying to match features between the two images. This is a trial-and-error process, which can take anywhere from 50 to 250 milliseconds, depending on how dramatically the scene has changed. Once it's matched features, the algorithm can deduce from their changes in position how far the robot has moved.

Censi and Scaramuzza's algorithm supplements camera data with events reported by an event-based sensor, which was designed by their collaborator Tobi Delbruck of the Institute for Neuroinformatics in Zurich. The new algorithm's first advantage is that it doesn't have to identify features: Every event is intrinsically a change in luminance, which is what defines a feature. And because the events are reported so rapidly—every millionth of a second—the matching problem becomes much simpler. There aren't as many candidate features to consider because the robot can't have moved very far.

Moreover, the algorithm doesn't try to match all the features in an image at once. For each event, it generates a set of hypotheses about how far the robot has moved, corresponding to several candidate features. After enough events have accumulated, it simply selects the hypothesis that turns up most frequently.

In experiments involving a robot with a camera and an event-based sensor mounted on it, their algorithm proved just as accurate as existing state-estimation algorithms.

Getting onboard

One of the inspirations for the new work, Censi says, was a series of recent experiments by Vijay Kumar at the University of Pennsylvania, which demonstrated that quadrotor helicopters—robotic helicopters with four sets of rotors—could perform remarkably nimble maneuvers. But in those experiments, Kumar gauged the robots' location using a battery of external cameras that captured 1,000 exposures a second. Censi believes that his and Scaramuzza's algorithm would allow a quadrotor with onboard sensors to replicate Kumar's results.

Now that he and his colleagues have a reliable state-estimation algorithm, Censi says, the next step is to develop a corresponding control algorithm—an algorithm that decides what to do on the basis of the state estimates. That's the subject of an ongoing collaboration with Emilio Frazzoli, a professor of aeronautics and astronautics at MIT.

Explore further: Location, location: Tango prototype helps quadrotor navigate (w/ Video)

add to favorites email to friend print save as pdf

Related Stories

Solving a moving problem

Dec 11, 2013

Victoria University graduand Ben Drayton has come up with a way to help solve the problem of measuring distance to a moving object.

3-D mapping in real time, without the drift (w/ Video)

Aug 28, 2013

Computer scientists at MIT and the National University of Ireland (NUI) at Maynooth have developed a mapping algorithm that creates dense, highly detailed 3-D maps of indoor and outdoor environments in real time.

Recommended for you

Report: China to declare Qualcomm a monopoly

52 minutes ago

(AP)—Chinese regulators have concluded Qualcomm Inc., one of the biggest makers of chips used in mobile devices, has a monopoly, a government newspaper reported Friday.

Hoverbike drone project for air transport takes off

11 hours ago

What happens when you cross a helicopter with a motorbike? The crew at Malloy Aeronautics has been focused on a viable answer and has launched a crowdfunding campaign to support its Hoverbike project, "The ...

Study shows role of media in sharing life events

13 hours ago

To share is human. And the means to share personal news—good and bad—have exploded over the last decade, particularly social media and texting. But until now, all research about what is known as "social sharing," or the ...

User comments : 1

Adjust slider to filter visible comments by rank

Display comments: newest first

NoTennisNow
not rated yet May 30, 2014
Tough problem. The problem is to not waste counts when nothing is happening. More data isn't always better.