AI News, Video Friday: Segway Robot Demo, Pepper the Retail Worker, and Megakopter World Record

Video Friday: Segway Robot Demo, Pepper the Retail Worker, and Megakopter World Record

Video Friday is your weekly selection of awesome robotics videos, collected by your soon-to-be snow-buriedAutomaton bloggers.

Giving drones the ability to dodge obstacles in complicated environments is huge, partially because it’s one of those things that everyone developing a delivery drone acts like they’ll just be able to somehow do.

Eliminating the landing gear significantly increases the payload capability of a solar-powered aircraft – it is easier to land during crosswind conditions, making landings in unfavourable weather conditions possible.”

View from shore of EMILY escorting a refugee boat as it goes through the area that the deeper water patrol boats (such as the Hellenic Coast Guard cutters use in the channel between Turkey and Greece and the smaller rigid hull inflatable boats used by NGOs) cannot enter due to draft restrictions but is too far out for lifeguards on shore to wade and has to be approached by a swimming lifeguard.

If the boat capsizes, people fall or misjudge the depth and jump off, or the boat runs aground, the lifeguards in patrol boats are not in position to help.

Also notice that they start taking off and throwing out lifejackets before landing and start waving, probably not thinking what happens if the boat suddenly runs aground or they fall over while getting out.

The lifeguards on the boats (you see the team in wetsuits in the rubber boat on the right) and on land would have to swim floatation devices out, taking valuable time and risking panicking people trying to climb on their heads.

A professor at the Harvard School of Engineering and Applied Sciences (SEAS), her research draws on inspiration from social insects and multicellular biology, with the goal of creating globally robust systems made up of many cooperative parts.

Lee: Manifolds and Decision Making in Intelligent Systems Current AI systems for perception and action incorporate a number of techniques: optimal observer models, Bayesian filtering, probabilistic mapping, trajectory planning, dynamic navigation, and feedback control.

I will also highlight some new research on machine learning for these systems, and discuss the role of geometrical structures and noise in synthetic and biological approaches to classification and decision making.

U.S. Navy's Drone Boat Swarm Practices Harbor Defense

Drone boats belonging to the U.S. Navy have begun learning to work together like a swarm with a sharedhive mind.

Four drone boats showed off their improved control and navigation softwareby patrolling an area of 4 nautical miles by 4 nautical miles.

After exchanging greetings with U.S. sailors, the suicide bombers detonated their deadly payload, killing 17 crew members and wounding 39.

In the test, the drone boats tried to coordinate their actionsto executefour different behaviors without direct human control: patrol, classification, track, and trail.

In that case, a swarm of five autonomous boats escorted a manned ship and then broke off to intercept a vessel acting as a possible intruder.

If human supervisors disagreewith how the drone boat swarm classified a certain vessel as being “friendly,” theycould reclassify the vessel as “unfriendly” so that the roboboats would react appropriately to the potential threat.

That means existing manned vessels could be converted intodrone boatsat a much lower cost compared with developing a robot boat from scratch.Navy researchers have also been using components of the CARACaS software in the separate Sea Hunterprogram that has been building a larger robotic ship for tracking submarines.

Next up, ONR wantsto ensure that their drone boat swarm can seamlessly switch between the different robotic behaviors when appropriate.“Behavior switching cues may be different depending on what the mission is,” Brizzolara said.“It’s not only about behaviors, but also about stitching behaviors together in a certain way.”

Tesla's toy boat: A drone before its time

Using a small, radio-transmitting control box, he was able to maneuver a tiny ship about a pool of water and even flash its running lights on and off, all without any visible connection between the boat and controller.

Indeed few people at the time were aware that radio waves even existed and Tesla, an inventor often known to electrify the crowd with his creations, was pushing the boundaries yet again, with his remote-controlled vessel.

This 31-foot-long device was powered and controlled through a hardwired tether and manipulated by a remote on-shore operator, with the goal of harbor defense by delivering an explosive payload into invading vessels.

When Tesla unveiled his own invention at the 1898 exhibition, the display consisted of an indoor pool, a 4-foot-long miniature ship and a control box equipped with various levers.

Inside the boat's hull, there was an electric motor driving both the propeller and rudder, a storage battery and a mechanism for receiving the radio signals sent from the control box.

Without the limits of a wired connection between the controls and the remote device, Tesla's invention would allow operators to effect changes in speed and direction, and control on-board gadgets (such as lights or moving parts), even from a moving vehicle.

Inside the Navy’s Secret Swarm RobotExperiment

Between them, they carry a variety of payloads, loud speakers and flashing lights, a .50-caliber machine gun and a microwave direct energy weapon or heat ray.

Detecting the enemy vessel with radar and infrared sensors, they perform a series of maneuvers to encircle the craft, coming close enough to the boat to engage it and near enough to one another to seal off any potential escape or access to the ship they are guarding.

Aerial drones like the Predator or Reaper are operated by two-man human teams, a pilot to steer the drone and a sensor operator to control the various mechanical eyes and ears.

We’ve taken that capability and extended it to multiple [unmanned surface vehicles] operating together… within that, we’ve designed team behaviors,” Robert Brizzolara, the manager of the SWARM program for ONR, told reporters.

ONR adapted it for the Navy’s needs but the philosophical history of swarm robotics can be traced to this 1995 paper in which artificial intelligence researchers James Kennedy and Russell Eberhardt argue that the collective behaviors that birds, fish, insects and humans display in response to rewards or threats could be captured mathematically and brought to bear on improving artificially intelligent entities in a simulation.

Kennedy and Eberhardt lay out some the major tenets for writing algorithms to mimic natural flocking or schooling behavior.  It’s a matter of quickly rating different known variables, threat, reward, and environment.

Last month, Harvard researcher Radhika Nagpal demonstrated the largest robotic swarm, 1,024 small bots collaborating wordlessly to create a variety of different shapes.  It’s an ongoing area of military investment as well, most notably the U.S. Army Research lab’s Micro-Autonomous Systems Technology or MAST program, which has awarded millions in grants to develop swarms of tiny flying bug robots for surveillance and intelligence gathering missions.

They can plan different actions to take in response to rapidly changing circumstances, weighing costs versus benefits of taking one route or another and do so in perfect collaboration in a chaotic environment.

The Navy is eager to keep the secret sauce under the lid, but the scope of the problem, the modeling challenges and mathematical solutions, can be gleaned in this recent paper titled Model-Predictive Asset Guarding by Team of Autonomous Surface Vehicles In Environment With Civilian Boat. The research isn’t directly related to the Navy experiment, but there’s a lot of overlap. “The outlined problem can be decomposed into multiple components, e.g., accelerated simulation, trajectory planning for collision- free guidance, learning of interception behaviors, and multi-agent task allocation and planning,” the researchers write.

The Navy’s breakthrough marks the clearest indication yet that more missions are falling to increasingly automated—and weaponized—systems, with human presence retreating ever deeper into the background.

“Growing autonomy in weapons poses a grave threat to humanitarian and human rights law, as well as international peace and security… In modern combat it is often heartbreakingly difficult to tell the difference between a fighter and a non-combatant.

“When the vast majority of countries outlawed anti-personnel landmines — a goal now endorsed by President Obama — they established that weapons which maim or kill absent of direct human control are morally reprehensible.”

The security of these systems is also of critical importance because hackers, criminals, or enemies who take control of autonomous attack systems could wreak enormous havoc,” said Omohundro.

But recent Defense Department budget decisions actually reflect a waning enthusiasm for unmanned systems, as Alex Velez-Green notes in a provocative piece for the Harvard Political Review, in which casts funding for AI development as hampered by sunk cost projects such as the F-35.