System Bits: Nov. 6

Keeping data private
To preserve privacy during data collection from the Internet, Stanford University researchers have developed a new technique that maintains personal privacy given that the many devices part of our daily lives collect information about how we use them.

Stanford computer scientists Dan Boneh and Henry Corrigan-Gibbs created the Prio method for keeping collected data private.

Researchers at Stanford have developed a new system for preserving privacy during data collection from the internet.
Source: Stanford University

Corrigan-Gibbs, a graduate student in computer science who co-developed this system, said, “We have an increasing number of devices – in our lightbulbs, in our cars, in our toasters – that are collecting personal data and sending it back to the device’s manufacturer. More of these devices means more sensitive data floating around, so the problem of privacy becomes more important. [Prio] is a way to collect aggregate usage statistics without collecting individual user data in the clear.”

Prio works by breaking up and obscuring individual information through a technique known as “secret sharing” and only allowing for the collection of aggregate reports, so, an individual’s information is never reported in any decipherable form, they noted.

Prio is currently being tested by Mozilla in a version of Firefox called Nightly, which includes features Mozilla is still testing.

According to the researchers, on Nightly, Prio ran in parallel to the current remote data collection (telemetry) system for six weeks, gathering over 3 million data values. There was one glitch but once that was fixed, Prio’s results exactly matched the results from the current system.

Further details about the system can be found here.

Cars as robot traffic managers
Bringing machine learning to traffic management, U.C. Berkeley engineers have developed a system aimed specifically at the road-sharing combination of autonomous, semi-autonomous and manned vehicles.

The team reminded that self-driving cars may one day do more than just get us from point A to point B. By adjusting their speed and position while they merge, or by pacing their average speed on the road, they could also help reduce the bottlenecks and random slowdowns on busy thoroughfares  like the San Francisco Bay Bridge, getting us where we’re going faster and more efficiently than if we all drove ourselves, they said.

To this point, the U.C. Berkeley transportation engineers are developing a tool that uses a type of artificial intelligence called deep reinforcement learning to help autonomous, semi-autonomous and human-driven vehicles share the road.

U.C. Berkeley engineers have developed Flow, to help solve real-world traffic problems.
Source: UC Berkeley

The project, called Flow, presented its first proposed standards for solving real-world traffic problems recently at the Conference on Robotic Learning in Zurich, Switzerland.

Electrical engineering and computer sciences professor Alexandre Bayen, director of the UC Berkeley Institute of Transportation Studies and the study’s principal investigator, said, “Flow solves large-scale, multi-vehicle problems by using simulations that are much more efficient than what can be produced without the aid of artificial intelligence. We’ve made it a cloud-based, open-source system so the development community can continue to build on it.”

The proposed standards give researchers benchmarks for comparing different traffic management algorithms. For example, in one benchmark or “task,” featuring a computer model of the Bay Bridge, researchers can test to see how quickly their algorithm gets cars off the bridge — and more importantly, how it stacks up against similar algorithms.

“Unless we’re working on the same problem, it’s hard to compare results. Are you looking at a New York highway or a California freeway? A group of 20 cars or 50? You need an apples-to-apples comparison to understand which solution works better,” said Eugene Vinitsky, co-lead author on the study and Ph.D. student in Bayen’s lab. 

Drone fleets operate where GPS signals are unreliable
MIT researchers reminded that finding lost hikers in forests can be a difficult and lengthy process, as helicopters and drones can’t get a glimpse through the thick tree canopy. Recently, they said, it’s been proposed that autonomous drones, which can bob and weave through trees, could aid these searches. But the GPS signals used to guide the aircraft can be unreliable or nonexistent in forest environments. Now, however, in a paper being presented at the International Symposium on Experimental Robotics conference, the MIT researchers describe an autonomous system for a fleet of drones to collaboratively search under dense forest canopies that use only onboard computation and wireless communication — no GPS required.

MIT researchers describe an autonomous system for a fleet of drones to collaboratively search under dense forest canopies using only onboard computation and wireless communication — no GPS required.

Source: MIT


Each autonomous quadrotor drone is equipped with laser-range finders for position estimation, localization, and path planning, the team explained, and as the drone flies around, it creates an individual 3-D map of the terrain. Algorithms help it recognize unexplored and already-searched spots, so it knows when it’s fully mapped an area. An off-board ground station fuses individual maps from multiple drones into a global 3-D map that can be monitored by human rescuers.

See the full details here.