Self-driving cars and autonomous robots: Where to now?

Nov 21, 2013 by Michael Brünig, The Conversation
Science fiction to non-fiction: the next generation of robots promises to be ultra intelligent. Credit: andreybl

There isn't a radio-control handset in sight as a nimble robot briskly weaves itself in and out of the confined tunnels of an underground mine.

Powered by ultra-intelligent sensors, the robot intuitively moves and reacts to the changing conditions of the terrain, entering areas unfit for human testing. As it does so, the robot transmits a detailed 3D map of the entire location to the other side of the world.

While this might read like a scenario from a George Orwell novel, it is actually a reasonable step into the not-so-distant future of the next generation of robots.

A recent report released by the McKinsey Institute predicts the potential economic contribution of new technologies such as advanced robotics, mobile internet and 3D printing are expected to return between US$14 trillion and US$33 trillion globally per year by 2025.

Technology advisory firm Gartner also recently released a report predicting the "smart machine era" to be the most disruptive in the history of IT. This trend includes the proliferation of contextually aware, intelligent personal assistants, smart advisers, advanced global industrial systems and the public availability of early examples of .

If the global technology industry and governments are to reap the productivity and economical benefits from this new wave of robotics they need to act now to identify simple yet innovative ways to disrupt their current workflows.

Self-driving cars

The automotive industry is already embracing this movement by discovering a market for driver assistance systems that includes parking assistance, autonomous driving in "stop and go" traffic and emergency braking.

In August 2013, Mercedes-Benz demonstrated how their "self-driving S Class" model could drive the 100-kilometre route from Mannheim to Pforzheim in Germany. (Exactly 125 years earlier, Bertha Benz drove that route in the first ever automobile, which was invented by her husband Karl Benz.)

The car they used for the experiment looked entirely like a production car and used most of the standard sensors on board, relying on vision and radar to complete the task. Similar to other autonomous cars, it also used a crucial extra piece of information to make the task feasible – it had access to a detailed 3D digital map to accurately localise itself in the environment.

There isn't a radio-control handset in sight as a nimble robot briskly weaves itself in and out of the confined tunnels of an underground mine.

Powered by ultra-intelligent sensors, the robot intuitively moves and reacts to the changing conditions of the terrain, entering areas unfit for human testing. As it does so, the robot transmits a detailed 3D map of the entire location to the other side of the world.

Credit: Mark Strozier

While this might read like a scenario from a George Orwell novel, it is actually a reasonable step into the not-so-distant future of the next generation of robots.

A recent report released by the McKinsey Institute predicts the potential economic contribution of new technologies such as advanced robotics, mobile internet and 3D printing are expected to return between US$14 trillion and US$33 trillion globally per year by 2025.

Technology advisory firm Gartner also recently released a report predicting the "smart machine era" to be the most disruptive in the history of IT. This trend includes the proliferation of contextually aware, intelligent personal assistants, smart advisers, advanced global industrial systems and the public availability of early examples of autonomous vehicles.

If the global technology industry and governments are to reap the productivity and economical benefits from this new wave of robotics they need to act now to identify simple yet innovative ways to disrupt their current workflows.

Self-driving cars

The automotive industry is already embracing this movement by discovering a market for that includes parking assistance, autonomous driving in "stop and go" traffic and emergency braking.

In August 2013, Mercedes-Benz demonstrated how their "self-driving S Class" model could drive the 100-kilometre route from Mannheim to Pforzheim in Germany. (Exactly 125 years earlier, Bertha Benz drove that route in the first ever automobile, which was invented by her husband Karl Benz.)

The car they used for the experiment looked entirely like a production car and used most of the standard sensors on board, relying on vision and radar to complete the task. Similar to other autonomous cars, it also used a crucial extra piece of information to make the task feasible – it had access to a detailed 3D digital map to accurately localise itself in the environment.

When implemented on scale, these autonomous vehicles have the potential to significantly benefit governments by reducing the number of accidents caused by human error as well as easing traffic congestion as there will no longer be the need to implement tailgating laws enforcing cars to maintain large gaps in between each other.

In these examples, the task (localisation, navigation, obstacle avoidance) is either constrained enough to be solvable or can be solved with the provision of extra information. However, there is a third category, where humans and autonomous systems augment each other to solve tasks.

This can be highly effective but requires a human remote operator or depending on real time constraints, a human on stand-by.

The trade-off

The question arises: how can we build a robot that can navigate complex and dynamic environments without 3D maps as prior information, while keeping the cost and complexity of the device to a minimum?

A high-resolution 3D map of Guangzhou, China. Credit: Colin Zhu

Using as few sensors as possible, a robot needs to be able to get a consistent picture of its environment and its surroundings to enable it to respond to changing and unknown conditions.

This is the same question that stood before us at the dawn of robotics research and was addressed in the 1980s and 1990s to deal with spatial uncertainty. However, the decreasing cost of sensors, the increasing computing power of embedded systems and the ability to provide 3D maps, has reduced the importance of answering this key research question.

In an attempt to refocus on this central question, we – researchers at the Autonomous Systems Laboratory at CSIRO – tried to stretch the limits of what's possible with a single sensor: in this case, a laser scanner.

In 2007, we took a vehicle equipped with laser scanners facing to the left and to the right and asked if it was possible to create a 2D map of the surroundings and to localise the vehicle to that same map without using GPS, inertial systems or digital maps.

The result was the development of our now commercialised Zebedee technology – a handheld 3D mapping system incorporates a laser scanner that sways on a spring to capture millions of detailed measurements of a site as fast as an operator can walk through it.

This video is not supported by your browser at this time.

While the system does add a simple inertial measurement unit which helps to track the position of the sensor in space and supports the alignment of sensor readings, the overall configuration still maximises information flow from a very simple and low cost setup.

It achieves this by moving the smarts away from the sensor and into the software to compute a continuous trajectory of the sensor, specifying its position and orientation at any time and taking its actual acquisition speed into account to precisely compute a 3D point cloud.

The crucial step of bringing the technology back to the robot still has to be completed. Imagine what is possible when you remove the barrier of using an autonomous vehicle to enter unknown environments (or actively collaborating with humans) by equipping robots with such mobile 3D mapping technologies. They can be significantly smaller and cheaper while still being robust in terms of localisation and mapping accuracy.

From laboratory to factory floor

A specific area of interest for this robust mapping and localisation is the manufacturing sector where non-static environments are becoming more and more common, such as the aviation industry. Cost and complexity for each device has to be kept to a minimum to meet these industry needs.

With a trend towards more agile manufacturing setups, the technology enables lightweight robots that are able to navigate safely and quickly through unstructured and dynamic environments like conventional manufacturing workplaces. These fully autonomous robots have the potential to increase productivity in the production line by reducing bottlenecks and performing unstructured tasks safely and quickly.

The pressure of growing increasing global competition means that if manufacturers do not find ways to adopt these technologies soon they run the risk of losing their business as competitors will soon be able to produce and distribute goods more efficiently and at less cost.

It is worth pushing the boundaries of what information can be extracted from very simple systems. New systems which implement this paradigm will be able to gain the benefits of unconstrained autonomous robots but this requires a change in the way we look at the production and manufacturing processes.

Explore further: Epson to unveil autonomous dual-arm robot that sees, senses, thinks, and reacts

Related Stories

Humanoid robot that sees and maps

Jul 02, 2013

(Phys.org) —Computer vision algorithms that enable Samsung's latest humanoid robot, Roboray, to build real-time 3D visual maps to move around more efficiently have been developed by researchers from the ...

Flying robots get off the ground

Jun 17, 2013

Attaching a platform to a high-rise building to evacuate people in an emergency, or creating a landing stage for an aircraft on uneven terrain - these are just two areas in which flying robots could have ...

World-first 3-D mobile mapping project

Apr 15, 2013

Australian researchers are using a novel mobile laser 3D mapping system called Zebedee to preserve some of the country's oldest and most culturally significant heritage sites.

Recommended for you

Government ups air bag warning to 7.8M vehicles

1 hour ago

The U.S. government is adding more than 3 million vehicles to a rare warning about faulty air bags that have the potential to kill or injure drivers or passengers in a crash.

Fighting cyber-crime one app at a time

1 hour ago

This summer Victoria University of Wellington will be home to four Singaporean students researching cyber threats. The students have been working with Dr Ian Welch, a lecturer in Victoria's School of Engineering and Computer ...

Using sound to picture the world in a new way

2 hours ago

Have you ever thought about using acoustics to collect data? The EAR-IT project has explored this possibility with various pioneering applications that impact on our daily lives. Monitoring traffic density ...

User comments : 7

Adjust slider to filter visible comments by rank

Display comments: newest first

TheGhostofOtto1923
1 / 5 (3) Nov 21, 2013
"...the "smart machine era" to be the most disruptive in the history of IT"

-Obamacare is an early indication of the massive changes the insurance industry will have to undergo to accomodate this new tech. It should make healthcare profoundly cheaper by reducing the number of professionals needed to administer it. And AI diagnosis and robotic surgery will alter the concept of liability in fundamental ways. The insurance industry in its present form simply cannot adjust to this new paradigm without being forced to.

"This trend includes the proliferation of contextually aware, intelligent personal assistants, smart advisers, advanced global industrial systems and the public availability of early examples of autonomous vehicles."

-Which doesnt mention the decreasing physical separation and increasing intimacy of the interface. Our senses will extend out into these machines. Their components will become an inseparable part of us. More reasons for obamacare and similar upheaval.
QuixoteJ
1 / 5 (1) Nov 22, 2013
Driverless cars are for idiots.

We hand over control of airplanes to a computer during stable and easily controlled phases of a flight, and only ever let the autopilot control landings a small percentage of the time under decent weather conditions. The autopilot is monitored and controlled by two trained pilots who are ready to disengage it at a moment's notice in order to more safely control the aircraft should the situation warrant it, and, as far as I know, the autopilot never taxis the airplane on the ground (when it is like a big car).

The average trip in a car is not like the cruising/descent phases of an aircraft when the autopilot is a good option. Unless you plan to hire a professionally trained driver ("pilot") who will in turn operate the autodrive, don't ever take your hands off the wheel or trust a computer to operate your car entirely the way you want it to.
TheGhostofOtto1923
1 / 5 (3) Nov 22, 2013
Machines will be far more capable than humans at driving, flying, conducting, and piloting simply because they have unwavering attention and are not subject to emotion.

When machines take over these tasks for us (and they will) the only source of accidents will be human error as it now is. Faulty design, parts, maintenance, programming, and malice. But in far far fewer numbers.
QuixoteJ
1 / 5 (1) Nov 22, 2013
When machines take over these tasks for us (and they will) the only source of accidents will be human error as it now is. Faulty design, parts, maintenance, programming, and malice. But in far far fewer numbers.
Right now there are X number of accidents while 0.000001% of vehicles are autonomous. Are you *seriously* implying that there will be fewer accidents due to design, parts, maintenance, or programming after increasing the autonomous percentage by a million?

Are you referring to the design, parts, maintenance, programming that is done by companies as inexpensively as possible with known, quantitative "acceptable" defect levels at manufacturing?

Also, if you really think machines will be "far more" capable at flying or driving in all situations then you haven't thought about that long enough.
TheGhostofOtto1923
1 / 5 (3) Nov 23, 2013
increasing the autonomous percentage by a million?
-This statement makes absolutely no sense.
you haven't thought about that long enough.
-Are you the guy who said only a few years ago that self-driving cars were impossible? Or was that some other luddite? You can think the situation through using obsolete info and still reach the same wrong conclusions.

As self-driving vehicles become pervasive they will begin talking to one another, conveying info about road and traffic conditions far ahead. They will be able to avoid trouble and they will know what the car in front of them is going to do long before you do.

They will receive info from traffic networks on congestion and hazards, and be able to offfer you alternate routes. They will never tailgate, speed, or otherwise drive dangerously. They wont be texting or eating when the guy in front of them swerves to avoid a deer. They are not subject to road rage and they never become intoxicated.
TheGhostofOtto1923
1 / 5 (3) Nov 23, 2013
Self-driving cars have the potential to save some 20,000 lives and millions of accidents a year.
http://www.washin...atch-on/

-And because of this the insurance companies will make them mandatory in most areas, initially for high-risk individuals and eventually for everybody but jay leno.

"Google's self-driving cars have now traveled more than 435,000 miles in California" and has only been involved in one accident. This actually occurred when a person was driving.
QuixoteJ
1 / 5 (1) Nov 25, 2013
increasing the autonomous percentage by a million?
-This statement makes absolutely no sense
Right now there are X autonomous cars on the road, which have Y accidents caused by defects in their autonomous "features". When there are 1000000*X autonomous cars on the road, there will be 1000000*Y accidents caused by their autonomous "features". The autonomous features will be designed and manufactured at the lowest cost possible. We are talking cars here, not space vehicles.

That's the way it will happen. Granted, the X is actually zero right now, but as soon as that becomes a one and grows, so will the problems with it grow in number.

I disagree with you about the insurance... I don't think insurance companies want driverless cars. Because they KNOW there will be accidents, but then who do you blame? Who pays? Who was at fault? Ford? Toyota? They would have to pass laws to make passengers responsible for accidents and that's insane.