I love to talk about the coming robocar world. Over the next few decades, more and more trips will be made in robocars, and more and more people will reduce or give up car ownership to live the robotaxi life. This won’t be instantaneous, and it will happen in some places decades before it happens in others, but I think it’s coming.

As Hurricane Florence raged across the coastline of Northern Carolina, 600 miles north the 174th Attack Wing Nation Guard base in Syracuse, New York was on full alert. Governor Cuomo just hung up with Defence Secretary Mattis to ready the airbase’s MQ-9’s drone force to “provide post-storm situational awareness for the on-scene commanders and emergency personnel on the ground.” Suddenly, the entire country turned to the Empire State as the epicenter for unmanned search & rescue operations.

Followers of this blog will know that I have been working for some years on simulation-based internal models – demonstrating their potential for ethical robots, safer robots and imitating robots. But pretty much all of our experiments so far have involved only one robot with a simulation-based internal model while the other robots it interacts with have no internal model at all.

Will a robot take my job?
Media headlines often speculate about robots taking our jobs. We’re told robots will replace swaths of workers from taxi drivers to caregivers. While some believe this will lead to a utopian future where humans live a life of leisure provided for by robots, the dystopian view sees automation as a risk to the very fabric of society. Such hopes and fears have preceded the introduction of new technologies for centuries – the Luddites for example destroyed weaving machines in the 19th century to protest the automation of their sector. What we see, time and time again, is that technology drives productivity and wealth, which translates to more and better jobs down the line. But can we expect the same to happen with robots, or is this time different?

This week’s hot story was again from Amir at The Information and there is even more detail in the author’s Twitter thread.

The newsletter The Information reports Uber’s investors are pushing Uber to sell its self-drive division to some other large player. The division has, of course, been nothing but trouble for Uber, and as I have noted several times, Uber is one of the few large players in this space that doesn’t have to build their own tech. They have the #1 brand in selling rides, and selling rides is what the robotaxi business is all about.

Last June, a massive dust storm engulfed Mars and immobilized the most famous robots in the galaxy, Opportunity and Curiosity. This is not the first time that Martian dirt has prevented Opportunity from recharging its solar panels. Its creators originally predicted that the planet’s harsh weather conditions would limit the rover’s mission to ninety sols (the equivalent of 93 earth days). This year, if it survives the current tempest, Opportunity will celebrate its 15th working anniversary on the red planet.

Waymo recently announced two new partnerships for their fleet of robotaxis.

A few weeks ago we had the kick-off meeting, in York, of our new 4 year EPSRC funded project Autonomous Robot Evolution (ARE): cradle to grave. We – Andy Tyrrell and Jon Timmis (York), Emma Hart (Edinburgh Napier), Gusti Eiben (Free University of Amsterdam) and myself – are all super excited. We’ve been trying to win support for this project for five years or so, and only now succeeded. This is a project that we’ve been thinking, and writing about, for a long time – so to have the opportunity to try out our ideas for real is wonderful.

Robots become every day more ‘intelligent’. What if robots were intelligent enough to say NO to war? This would be a happier future.

This short film is a light-hearted comedy that aims to launch an interesting discussion and motivate reflexion on the killer-robots topic. The fictional scenario describes a future where robots contract out and refuse to be employed in human warfare. This optimistic point of view can be inspirational to engineers and roboticists developing a robotic future.

For a lot of people, being a passenger in a car can easily lead to motion sickness, particularly if they try to do something like looking down to read a book or stare at a phone. Not everybody gets this, but it’s enough to be a big issue for the robocar world. Drivers usually don’t feel this much, but in the robocar world, everybody’s a passenger.

Ever since the première of “Steamboat Willie” in 1928, The Walt Disney Company has pushed the envelope of imagination. Mickey Mouse is still more popular worldwide than any single human actor. In fact, from that one cel an entire world of animated characters was born. The entertainment powerhouse demonstrated last week a new generation of theatrics with a flying robot-like stuntman (hero pause and all) that is destined to become a leading player in the age of autonomy.

In discussion of the eventual cost of a robotaxi ride, I and others have forecast costs similar to the all-in cost of car ownership. Today that’s 40 to 60 cents/mile (plus parking) and for a one person electric “city car” it can be under 20 cents.

Readers of this blog will know that I’ve become very excited by the potential of robots with simulation-based internal models in recent years. So far we’ve demonstrated their potential in simple ethical robots and as the basis for rational imitation. Our most recent publication instead examines the potential of robots with simulation-based internal models for safety. Of course it’s not hard to see why the ability to model and predict the consequences of both your own and others’ actions can help you to navigate the world more safely than without that ability.

Our paper Simulation-Based Internal Models for Safer Robots demonstrates the value of anticipation in what we call the corridor experiment. Here a smart robot (equipped with a simulation based internal model which we call a consequence engine) must navigate to the end of a corridor while maintaining a safe space around it at all times despite five other robots moving randomly in the corridor – in much the same way you and I might have to navigate down a busy office corridor while others are coming in the opposite direction.

Here is the abstract from our paper:

In this paper, we explore the potential of mobile robots with simulation-based internal models for safety in highly dynamic environments. We propose a robot with a simulation of itself, other dynamic actors and its environment, inside itself. Operating in real time, this simulation-based internal model is able to look ahead and predict the consequences of both the robot’s own actions and those of the other dynamic actors in its vicinity. Hence, the robot continuously modifies its own actions in order to actively maintain its own safety while also achieving its goal. Inspired by the problem of how mobile robots could move quickly and safely through crowds of moving humans, we present experimental results which compare the performance of our internal simulation-based controller with a purely reactive approach as a proof-of-concept study for the practical use of simulation-based internal models.

So, does it work? Thanks to some brilliant experimental work by Christian Blum the answer is a resounding yes. The best way to understand what’s going on is with this wonderful gif animation of one experimental run below. The smart robot (blue) starts at the left and has the goal of safely reaching the right hand end of the corridor – its actual path is also shown in blue. Meanwhile 5 (red) robots are moving randomly (including bouncing off walls) and their actual paths are also shown in red; these robots are equipped only with simple obstacle avoidance behaviours. The larger blue circle shows blue’s ‘attention radius’ – to reduce computational effort blue will only model red robots within this radius. The yellow paths in front of the red robots in blue’s attention radius show blue’s predictions of how those robots will move (taking into account collisions with the corridor walls and with blue and each other). The light blue projection in front of blue shows which of the 34 next possible actions of blue that is internally modelled is actually chosen as the next action (which, as you will see, sometimes includes standing still).

What do the results show us? Christian ran lots of trials – 88 simulations and 54 real robot experiments – over four experiments: (1) the baseline in simulation – in which the blue robot has only a simple reactive collision avoidance behaviour, (2) the baseline with real robots, (3) using the consequence engine (CE) in the blue robot in simulation, and (4) using the consequence engine in the blue robot with real robots. In the results below (a) shows the time taken for the blue robot to reach the end of the corridor, (b) shows the distance that the blue robot covers while reaching the end of the corridor, (c) shows the “danger ratio” experienced by the blue robot, and (d) shows the number of consequence engine runs per timestep in the blue robot. The danger ratio is the percentage of the run time that anther robot is within the blue robot’s safety radius.

For a relatively small cost in additional run time and distance covered, panels (a) and (b), the danger ratio is very significantly reduced from a mean value of ~20% to a mean value of zero, panel (c). Of course there is a computational cost, and this is reflected in panel (d); the baseline experiment has no consequence engine and hence runs no simulations, whereas the smart robot runs an average of between 8 and 10 simulations per time-step. This is exactly what we would expect: predicting the future clearly incurs a computational overhead.

The Tempe police released a detailed report on their investigation of Uber’s fatality. I am on the road and have not had time to read it, but the big point, reported in many press was that the safety driver was, according to logs from her phone accounts, watching the show “The Voice” via Hulu on her phone just shortly before the incident.