T. rex (AI) successfully locates and hunts prey on Dinosaur Island.

A T. rex named George successfully found, tracked, pursued and attacked an Edmontosaurus named Julie. Click to enlarge.

A T. rex named George successfully found, tracked, pursued and attacked an Edmontosaurus named Julie. Click to enlarge.

It has been said that nobody wants to see how politics or sausages are made. Artificial Intelligence (AI), for some, may also be added to that list. Today’s blog topic is about achieving an important milestone in the AI behind Dinosaur Island: a T. rex ‘looked’ around his virtual world (using a 3D line of sight algorithm), spotted potential prey (an Edmontosaurus regalis named Donna) pursued it using an optimized A* least weighted path algorithm that avoided steep slopes and boggy terrain (the attack was up hill) , then saw a more attractive target (an Edmontosaurus regalis named Julie), changed his pursuit and successfully overtook the prey.

This AI is unique and probably the first time such a series of events has been demonstrated in a 3D virtual world environment. Below are step by step screen captures showing the events:

Screen capture with all AI tracing turned on. There are three dinosaurs in this image. George sees Donna (dark red line)

Screen capture with all AI tracing turned on. There are three dinosaurs in this image. George sees Donna (dark red line), Donna is looking almost due east (dark red line) at the forest of Araucaria trees where she wants to go to eat, the cloud of yellow is the AI looking at alternative paths for Donna to climb up a hill, Julie is also looking at the same forest of Araucaria trees to her northeast and the AI (yellow path) has plotted the best route for her to climb the hill. (Click to enlarge).

AI2

This screen capture taken 10 seconds later shows Donna approaching the Araucaria forest to the east and Julie climbing the hill towards the same forest to the northeast. George now sees that Julie is the closest prey and switches his attack to her (dark red line) and races toward her. (Click to enlarge).

George has

Ten seconds later, George has closed the distance and has attacked Julie from the flank. (Click to enlarge).

It’s important to remember that Dinosaur Island will ship in full 3D; these screen shots are of the AI testing environment which is in 2D.

Now that we have created a ‘perfect killing’ AI we will have to make it ‘stupider’ by adding distractions and imperfections.

Share

Are we making the dinosaurs too smart?

Traces of the artificial intelligence (AI) calculations for dinosaurs' optimal paths to food. Screen capture.

Traces of the artificial intelligence (AI) calculations for dinosaurs’ optimal paths to food. The AI chooses paths with least steep slopes and avoids terrain (like swamps) that would unnecessarily slow the dinosaur down. Screen capture.

Yes, I know in Jurassic Park velociraptors could open doors (I would post a picture, but I’m worried about lawsuits so here’s a link to the clip instead). Luckily, on Dinosaur Island we don’t have any doors, kitchens, cages, Land Rovers or electric fences so we don’t have to worry about writing the artificial intelligence (AI) routines for the dinosaurs to deal with these objects.

Instead, we’re interested in if the dinosaur can see the food (I discussed 3D line of sight algorithms in, “Dinosaurs, tanks and light of sight algorithms,” here). And, if and only if, the dinosaur can see the food, how does the dinosaur get to the food? The fastest way for the dinosaur to get to the food can be solved using a least weighted path algorithm which I discussed in this blog here.

Now, the question is, “are we making the dinosaurs too smart?” The image at the top of today’s blog is a screen capture of the AI ‘looking’ at different ways to get to the objective (in this case, food that has been identified previously using the 3D line of sight algorithm). From literally thousands of possible routes (some only deviating by a meter from another possible route) the optimal, or fastest route across the landscape (avoiding steep hills and terrain that would slow the dinosaur down) is chosen.

Is this really how a dinosaur thought?

Probably not. What I suspect, and again, I’m a computer scientist, not a paleontologist, is that dinosaurs, especially a dinosaur pursuing prey, ran straight towards the target until it encountered something (an obstacle, a steep hill, swampy land) and only then considered going on an alternative path.

So, I will probably rewrite the AI so it’s not optimal. But for now, we’ve got some really smart predators on Dinosaur Island. Not opening doors smart. But smarter than the real thing.

SmallRuleBelow is a screen capture of the optimized AI least weighted path algorithm.

Screen shot of optimal least weighted path algorithms (taking slope and terrain into effect). Screen capture (click to enlarge).

Screen shot of optimal least weighted path algorithms (taking slope and terrain into effect). Dark red lines: 3D Line of sight (the food that the dinosaur is looking at). Orange lines: final path for dinosaur. Yellow areas: alternative paths that were evaluated and discarded. Screen capture (click to enlarge).

Share

How a dinosaur is not like a tank.

A cross-section view of the elevation that a T. Rex (named Bob) will have to traverse to get to an Edmontosaurus regalis (named Gertie). Click to enlarge.

A cross-section view of the elevation that a T. Rex (named Bob) will have to traverse to get to an Edmontosaurus regalis (named Gertie). A very steep riverbank is between Bob and Gertie. Vertical axis: elevation in meters, horizontal axis: distance to goal in meters. Click to enlarge.

A few days ago I wrote about Dinosaurs, tanks and line of sight algorithms and how my previous work in modeling and simulations (M&S) for military wargames (specifically line of light algorithms) was applicable in Dinosaur Island. Today I am working on the models for dinosaur movement, speed, and what are called “least weighted path” algorithms.

You are probably familiar with least weighted path algorithms even if the term is new to you. Least weighted path algorithms are used to calculate routes in GPS units for cars or smartphones or for various internet sites like MapQuest, Google or Bing. When calculating a route there are a number of criteria to chose from. Does the user want:

  • The fastest route?
  • The shortest route?
  • The most fuel efficient route?
  • The route that avoids certain features (such as specific terrain, topography or extreme slopes)?

These options are what ‘weight’ the potential routes in a ‘least weighted’ path algorithm. For example, taking the Interstate is often the fastest route (least amount of time) but frequently is not the shortest route (least amount of distance).

Back in grad school I did my ‘comprehensive exam’ for PhD students on the subject of least weighted path algorithms. There are two very popular algorithms that solve this problem: one is Dijkstra’s algorithm (which is an exhaustive search solution) and the other is the A* algorithm, by Peter Hart, Nils Nilsson and Bertram Raphael. The primary difference between Dijkstra’s algorithm and the A* algorithm is that Dijkstra’s is guaranteed to return the optimal solution but it often takes the most time to calculate. The A* algorithm is much faster to calculate but is not guaranteed to return the optimal (or perfect) solution. In computer games we almost always use the A* algorithm because speed of calculations (especially over large maps) is more important than having the absolutely perfect route. At the bottom of this blog are links to descriptions of these algorithms and my research paper discussing an optimization of A*.

But, what does this have to do with dinosaurs and tanks?

When working on an M&S involving vehicles (like tanks) our primary concern is finding the fastest way for the tank to get from Point A to Point B. Sometimes, we want the tank to avoid entering into an area where the enemy (called OPFOR, or ‘Opposition Forces’ in military parlance) can hit it with their weapons (this is called ‘range of influence’ or ROI). This is illustrated below:

This image shows how MATE will calculate the least weighted path for a unit using roads, terrain, elevation and avoiding enemy weapons range for 'path weights'. (Click to enlarge.)

This image shows how MATE will calculate the least weighted path for a unit using roads, terrain and elevation and avoiding enemy weapons range for ‘path weights’. (Click to enlarge.)

We also want the tank to take advantage of roads and avoid swamps, rivers and ponds.The maximum speed of a tank traveling on a road is higher than the maximum speed of a tank traveling across a field. This is not the case with a T. rex or an Edmontosaurus regalis.

Another difference between tanks and dinosaurs is that as long as a tank has fuel it can go at 100% of their maximum speed (on a specific terrain) without problems. This simply isn’t the case with dinosaurs. As dinosaurs expend energy (and remember, energy is the ‘currency’ of Dinosaur Island, see: The currency of Dinosaur Island) they get tired and they can’t run as fast or as far. Also, dinosaurs run at their maximum speed only for short distances and only in extreme emergencies or at the very end of a hunt when they attack.

The illustration at the top of the blog also points out another major difference between tanks and dinosaurs: modern tanks (specifically the M1A1) has a published specification of being able to climb a 60 degree slope at a speed of 7.2 km/h (see here). That’s pretty impressive. It’s unlikely that that a T. rex could navigate a slope that steep. In the cross-section at the top of this blog we show the slopes that Bob, the T. rex, will encounter following a straight line to Gertie, the Edmontosaurus.

Clearly we’re going to need to use a least weighted path algorithm for calculating dinosaur movement so that they will avoid steep riverbanks and crevices. We also will create a table of ‘energy costs’ that dinosaurs will incur as they travel across various terrains (like swamp). These values will be used in our least weighted path algorithm.

SmallRule

Some links about least weighted path algorithms:

  • Dijkstra’s algorithm on Wikipedia has a very easy to follow description with a couple of cool animations to show how it works. Link here.

  • A* search algorithm on Wikipedia also has a couple of very nice animations to show how it works and pseudocode. Link here. By the way, I once sent Nils Nilsson an email asking him what the ‘A’ in A* stood for and he replied, “algorithm.” Now you know.

  • “An Analysis of Dimdal’s (ex-Jonsson’s) ‘An Optimal Pathfinder for Vehicles in Real-World Terrain Maps,‘ the paper for my Comprehensive Exam can be downloaded here.
Share

Tyrannosaurus rex hunting an Edmontosaurus regalis

A Tyrannosaurus rex (Barney) on the left has identified an Edmontosaurus regalis (Gertie) on the right. Screen capture (click to enlarge).

A Tyrannosaurus rex (Barney) on the left has identified an Edmontosaurus regalis (Gertie) on the right. Red lines indicate respective dinosaur’s goals (food). (Click to enlarge.)

Today the AI (Artificial Intelligence) routines for the inhabitants of Dinosaur Island to identify food were put in place and tested. The above screen capture shows the results: Gertie, a hungry Edmontosaurus regalis, has spied a forest of Araucaria trees on higher ground about 55 meters to the north-northeast. Barney, a very hungry nine year-old Tyrannosaurus rex has spotted Gertie 145 meters almost due east on the other side of a creek bed lined with Nipa plants. This doesn’t look good for Gertie. Will one and a half football fields be enough of a head start? How long will Barney pursue dinner before the energy expended will be too great? Look at Barney’s health. He hasn’t eaten for a while and he doesn’t have much energy left.

A reminder: the 2D ‘top down’ version of Dinosaur Island is just for testing and scenario creation purposes. Dinosaur Island will be released in full 3D. Dinosaur Island is a unique interactive simulation of real dinosaurs in their natural environment.

Share

Thirst or hunger? What is more important to a dinosaur?

A drinking hadrosaur from I think the reference of the

A drinking hadrosaur from a set of 1916 German collector cards “Tiere der Urwelt” (Animals of the Prehistoric World) by Heinrich Harder, from here. (Copyright expired.)

What is more important to an animal that is very hungry and very thirsty: water or food? I just encountered this problem when writing the AI code for dinosaurs finding food and water. When ‘new’ dinosaurs are currently created in Dinosaur Island they haven’t yet eaten or drunk water so the stored values for every new animal is ‘0’. Obviously, we can, and will, change that so ‘new’ dinosaurs are created with some values (these ‘new’ dinosaurs are not ‘just hatched’ dinosaurs but rather adult animals that are created and placed on Dinosaur Island for testing purposes).

Screen capture showing a very thirsty Edmontosaurus named Gertie who is now walking towards the closest observed water. (Click to enlarge)

Screen capture showing a very thirsty Edmontosaurus named Gertie who is now walking towards the closest observable water (click to enlarge).

The above screen capture from Dinosaur Island shows a very thirsty Edmontosaurus, named Gertie, that can see fresh water (solid blue line) in a nearby tributary. It is interesting to note that because of the height of the river bank Gertie can only see the water on the far side of the tributary. Nonetheless, Gertie is now moving towards the water she can see and will stop and drink as soon as she encounters it.

While working on the AI routines for a dinosaur finding water (see also Dinosaurs, tanks and line of sight algorithms here) I realized that some dinosaurs travel in herds and that where the herd goes is the decision of the leader. Consequently, we will need to have the ability to designate one dinosaur in a group as the leader and the others as followers. Were dinosaur herds matriarchal (led by the senior female, like elephants)? Were dinosaur herds patriarchal (like buffalo)? We just don’t know the answer to these questions but we will be able to explore the possibilities by using Dinosaur Island and observing the results.SmallRule

After posting yesterday’s blog I received an email from my friend, Siobhan, who wrote, “I think dinosaurs are closer to elephants than buffalo, and thus require a matriarch.  Please tell me who I need to pay off and how to see a matriarch implemented! (that’s me subtly casting a vote).

Bribery isn’t necessary. We believe Dinosaur Island should be flexible enough to allow the user to set up any scenario they wish. Today we added the following to the ‘Dinosaur Species’ dialog box:

Just added Herd Leadership variable (Matriarch, Patriarch or Neither in bottom right). Screen capture (click to enlarge).

The just added Herd Leadership variable (Matriarch, Patriarch or Neither in bottom right). Edmontonsosaurus, by default, is now a matriarchal herd. Screen capture (click to enlarge).

Edmontosaurus regalis is now, by default, a matriarchal herd which means that the senior female decides where the herd goes, where it eats, where it drinks, where it rests and how to avoid predators. The default for Tyrannosaurus rex is ‘Neither’ or no herd leadership.

 

Share