Tag Archives: Antietam

Antietam & AI

MATE AI selected Objectives for Blue, 3D Line of Sight (3DLOS) and Range of Influence (ROI) displayed for the Antietam: Dawn General Staff scenario. Screen shot from General Staff Sand Box. Click to enlarge.

The author walking across Burnside’s Bridge in 1966 (age 12).

I have been thinking about creating an artificial intelligence (AI) that could make good tactical decisions for the battle of Antietam (September 17, 1862, Sharpsburg, Maryland) for over fifty years. At the time there was little thought of computers playing wargames.1)However, it is important to note that Arthur Samuel had begun research in 1959 into a computer program that could play checkers. See. “Samuel, Arthur L. (1959). “Some Studies in Machine Learning Using the Game of Checkers”. IBM Journal of Research and Development.” What I was envisioning was a board wargame with some sort of look-up tables and coffee grinder slide rules that properly configured (not sure how, actually) would display what we now call a Course of Action (COA), or a set of tactical orders. I didn’t get too far on that project but I did create an Antietam board wargame when I was 13 though it was hardly capable of solitaire play.

The Antietam scenario from The War College (1992). This featured 128 pre-rendered 3D views generated from USGS Digital Elevation Model Maps.

In 1992 I created my first wargame with an Antietam scenario: The War College (above). It used a scripted AI that isn’t worth talking about. However, in 2003 when I began my doctoral research into tactical AI I had the firm goal in my mind of creating software that could ‘understand‘ the battle of Antietam.

TIGER Analysis of the battle of Antietam showing Range of Influence of both armies, battle lines and RED’s avenue of retreat. TIGER screen shot. Appears in doctoral thesis, “TIGER: A Machine Learning Tactical Inference Generator,” University of Iowa 2009

The TIGER program met that goal (the definition of ‘understand’ being: performing a tactical analysis that is statistically indistinguishable from a tactical analysis performed by 25 subject matter experts; e.g.. active duty command officers, professors of tactics at military institutes, etc.).

In the above screen shot we get a snapshot of how TIGER sees the battlefield. The darker the color the greater the firepower that one side or the other can train on that area. Also shown in the above screen shot is that RED has a very restricted Avenue of Retreat; the entire Confederate army would have to get across the Potomac using only one ford (that’s the red line tracing the road net to the Potomac).  Note how overlapping ROIs cancel each other out. In my research I discovered that ROIs are very important for determining how battles are described. For example, some terms to describe tactical positions include:

  • Restricted Avenue of Attack
  • Restricted Avenue of Retreat
  • Anchored Flanks
  • Unanchored Flanks
  • Interior Lines
  • No Interior Lines

A Predicate Statement list generated by MATE for the battle of Antietam.

Between the time that I received my doctorate in computer science for this research and the time I became a Principal Investigator for DARPA on this project the name changed from TIGER to MATE (Machine Analysis of Tactical Environments) because DARPA already had a project named TIGER. MATE expanded on the TIGER AI research and added the concept of Predicate Statements. Each statement is a fact ascertained by the AI about the tactical situation on that battlefield. The most important statements appear in bold.

The key facts about the tactical situation at Antietam that MATE recognized were:

  • REDFOR’s flanks are anchored. There’s no point in attempting to turn the Confederate flanks because it can’t be done.
  • REDFOR has interior lines. Interior lines are in important tactical advantage. It allows Red to quickly shift troops from one side of the battlefield to the other while the attacker, Blue, has a much greater distance to travel.
  • REDFOR’s avenue of retreat is severely restricted. If Blue can capture the area that Red must traverse in a retreat, the entire Red army could be captured if defeated. Lee certainly was aware of this during the battle.
  • BLUEFOR’s avenue of attack is not restricted. Even though the Blue forces had two bridges (Middle Bridge and Burnside’s Bridge) before them, MATE determined that Blue had the option of a wide maneuver to the north and then west to attack Red (see below screen shot):

MATE analysis shows that Blue units are not restricted to just the two bridge crossings to attack Red. MATE screen shot.

  • BLUEFOR has the superior force. The Union army was certainly larger in men and materiel at Antietam.
  • BLUEFOR is attacking across level ground. Blue is not looking at storming a ridge like at the battle of Fredericksburg.

MATE AI selects these objectives for Blue’s attack. General Staff Sand Box screen shot. Click to enlarge.

We now come to General Staff which uses the MATE AI. General Staff clearly has a much higher resolution than the original TIGER program (1155 x 805 terrain / elevation data points versus 102 x 66, or approximately 138 times the resolution / detail). In the above screen shot the AI has selected five Objectives for Blue. I’ve added the concept of a ‘battle group’ – units that share a contiguous battle line – which in this case works out as one or two corps. Each battle group has been assigned an objective. How each battle group achieves its objective is determined by research that I did earlier on offensive tactical maneuvers 2)See, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” link to paper.

As always, I appreciate comments and questions. Please feel free to email me directly with either.

References

References
1 However, it is important to note that Arthur Samuel had begun research in 1959 into a computer program that could play checkers. See. “Samuel, Arthur L. (1959). “Some Studies in Machine Learning Using the Game of Checkers”. IBM Journal of Research and Development.”
2 See, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” link to paper.

Computational Military Reasoning (Tactical Artificial Intelligence) Part 2

In my last blog post I described how the TIGER / MATE programs classified battles (in computer science terms ‘objects’) based on attributes and that anchored or unanchored flanks was one such attribute. After demonstrating the algorithm for calculating the presence or absence of anchored flanks we saw how the envelopment and turning tactical maneuvers were implemented. In this blog post we will look at another attribute: restricted avenues of attack and restricted avenues of retreat.

The only avenue of retreat from the Battle of First Bull Run back to Washington was over a narrow Stone Bridge. When a wagon overturned panic ensued. Library of Congress.

One classic example of a restricted avenue of retreat was the narrow stone bridge crossing Cub Run Creek which was the only eastern exit from the First Bull Run battlefield. The entire Union army would have to pass over this bridge as it fell back on Washington, D.C. When artillery fire caused a wagon to overturn and block the bridge, panic ensued.

At the battle of Antietam Burnside tried to force his entire corps over a narrow bridge to attack a Confederate position on the hill directly above. The bridge was famously carried by the 51st New York Infantry and 51st Pennsylvania Infantry who demanded restoration of their whiskey rations in return for this daring charge. From the original Edwin Forbes drawing. Click to enlarge.

Burnside’s Bridge at the battle of Antietam is a famous example of a restricted avenue of attack. Burnside was unaware that Snavely Ford was only 1.4 miles south of the stone bridge and allowed a back door into the Confederate position. Consequently, he continued to throw his corps across the bridge with disastrous results.

How to determine if there is a restricted line of attack or a restricted line of retreat on a battlefield

From the perspective of computer science restricted avenues of retreat and restricted avenues of attack are basically the same problem and can be solved with a similar algorithm.

As before we must first establish that there is agreement among Subject Matter Experts (SMEs) of the existence of – and the ability to quantify – the attributes of ‘Avenue of Attack’, ‘Avenue of Retreat’ and ‘Choke Point’.

The following slides are from an unclassified briefing that I gave to DARPA (the Defense Advanced Research Project Agency) on my MATE program (funded by DARPA research grant W911NF-11-200024):

All slides can be enlarged by clicking on them.

Now that we have determined if there is a restricted avenue of attack the next blog post will discuss what to do with this information; specifically the implementation of the infiltration and penetration offensive maneuvers.

As always, if you have any questions please feel free to email me.

References:

TIGER: An Unsupervised Machine Learning Tactical Inference Generator, Sidran, D. E. Download here.

Computational Military Reasoning (Tactical Artificial Intelligence) Part 1

I coined the phrase ‘computational military reasoning’ in grad school to explain what my doctoral thesis in computer science was about. ‘Computational reasoning’ is a formal method for solving problems (technically, you don’t even need a computer). But, for our purposes it means a computer solving ‘human-level’ problems. A classic example of this would be calculating the fastest route on a map between two points. In computer science we call this a ‘least weighted path’ algorithm and I did my Q (Qualifying) Exam on this subject. I have also written extensively on the subject including these blog posts.

So, ‘computational military reasoning’ is a, “computer solving human-level military problems.” Furthermore, we can divide computational military reasoning into two subcategories: strategic and tactical (Russian military dogma also adds a third category, ‘grand strategy’); however, for now, let’s concentrate on tactical artificial intelligence; or battlefield decisions.

Tactical AI is divided into two parts: analyzing – or reading – the battlefield and acting on that information by creating a set coherent orders (commonly known as a COA or Course of Action) that exploit the weaknesses in our enemy’s position that we have found during our battlefield analysis.

 

It is said that as Napoleon traveled across Europe with his staff he would question them about the terrain that they were passing; “Where is the best defensive position? What are the best attack routes?” Where would you position artillery? What ground is favorable for cavalry attack?”

We take it for granted that such analysis of terrain and opposing forces positioned upon it is a skill that can be taught to humans. My doctoral research 1)TIGER: An Unsupervised Machine Learning Tactical Inference Generator; This thesis can be downloaded free of charge here. successfully demonstrated the hypothesis that an unsupervised machine learning program could also learn this skill and perform battlefield analysis that was statistically indistinguishable2)Using a one sided Wald test resulted in  p = 0.0001.In other words, it was extremely unlikely that TIGER was ‘guessing correctly’. from analyses performed by Subject Matter Experts (SMEs) such as instructors at West Point and active duty combat command officers.

Supervised & Unsupervised Machine Learning

Netflix recommendations are a supervised learning program. Every time you ‘like’ a movie the program ‘learns’ that you like ‘documentaries’; for example. Any program that has you ‘like’ or ‘dislike’ offerings is a supervised learning program. You are the supervisor and by clicking on ‘like’ or ‘dislike’ you are teaching the program.

TIGER is an unsupervised machine learning program. That means it has to figure everything out for itself. Rather than being taught, TIGER is ‘fed’ a series of ‘objects’ that have ‘attributes’ and it sorts them into like categories. For TIGER the objects are snapshots of battlefields.

Screen capture from TIGER. An ‘object’ has been loaded into TIGER for analysis; in this case a ‘snapshot’ of the battle of Antietam at 1630 hours on September 17, 1863. Click to enlarge.

How TIGER perceives the battlefield

When you and I look at a battlefield our brains, somehow, make sense of all the NATO 2525B icons scattered around the topographical map. I don’t know how our brains do it, but this is how TIGER does it:

Screen capture from TIGER: How TIGER converts unit positions into lines and frontages using a Minimum Spanning Tree (MST). Click to enlarge.

By combining 3D Line of Sight with Range of Influence (how far weapons can fire and how accurate they are at greater distances displayed, above, with lighter colors) with a Minimum Spanning Tree algorithm3)Kruskal’s algorithm, https://en.wikipedia.org/wiki/Kruskal%27s_algorithm the above image is how TIGER ‘sees’ the battlefield of Antietam. This is an important first step for evaluating object attributes.

How to determine the attribute of anchored or unanchored flanks

Battlefields are ‘objects’ that are made up of ‘attributes’. One of these attributes is the concept of anchored and unanchored flanks. While anyone who plays wargames probably has a good idea what is meant by a ‘flank’, following formal scientific methods I had to first prove that there was agreement among Subject Matter Experts (SMEs) on the subject. This is from one of the double-blind surveys given to SMEs:

Screen shot from online double-blind survey of Subject Matter Experts on identifying the presence of Anchored and Unanchored Flanks. Click to enlarge.

And their responses to the situation at Antietam:

Subject Matter Experts response to the question of the presence of Anchored or Unanchored flanks at Antietam. Click to enlarge.

And another double-blind survey question asked of the SMEs about anchored or unanchored flanks at Chancellorsville:

Response to double-blind survey question asked of SMEs about anchored and unanchored flanks at Chancellorsville. Click to enlarge.

So, we have now proven that there is agreement among Subject Matter Experts about the concept of ‘anchored’ and ‘unanchored’ flanks and, furthermore, some battlefields exhibit this attribute and others don’t.

Following is a series of slides from a debriefing presentation that I gave to DARPA (Defense Advanced Research Projects Agency) as part of my DARPA funded research grant (W911NF-11-200024) describing the algorithm that MATE (the successor to TIGER) uses to calculate if a flank is anchored or unanchored and how to tactically exploit this situation with a flanking maneuver. This briefing is not classified. Click to enlarge slides.

How to generate a Course of Action for a flank attack

Once TIGER / MATE has detected an ‘open’ or unanchored flank it will then plot a Course of Action (COA) to maneuver its forces to perform either a Turning Maneuver or an Envelopment Maneuver. Returning to the previous DARPA debriefing presentation (Click to enlarge):

MATE analysis of the battle of Marjah (Operation Moshtarak February 13, 2010)

The following two screen captures are part of MATE’s analysis of the battle of Marjah suggesting an alternative COA  (envelopment maneuver) to the direct frontal assault that the U. S. Marine force actually performed at Marjah. Click to enlarge:

Conclusions & Comments about Computational Military Reasoning (Tactical Artificial Intelligence) & Battlefield Analysis (Part 1)

Usually, at this point when I give this lecture, I look out to my audience and ask for questions. I really don’t want to lose anybody and we’ve got a lot more Tactical AI to talk about. So far, I’ve only covered how my programs (TIGER / MATE) analyze a battlefield in one particular way (does my enemy – OPFOR in military terms – have an exposed flank that I can pounce on?) and there is a lot more battlefield analysis to be performed.

It’s easy, as a computer scientist, to use computer science terminology and shorthand for explaining algorithms. But, I worry that the non computer scientists in the audience will not quite get what I’m saying.

Do you have any questions about this? If so, I would really like to hear from you. I’ve been working on this research for my entire professional career (see A Wargame 55 Years in the Making) and, frankly, I really like talking about it. As a TA said to me many years ago when I was an undergrad, “There are no stupid questions in computer science.” So, please feel free to write to me either using our built in form or by emailing me at Ezra [at] RiverviewAI.com

References

References
1 TIGER: An Unsupervised Machine Learning Tactical Inference Generator; This thesis can be downloaded free of charge here.
2 Using a one sided Wald test resulted in  p = 0.0001.In other words, it was extremely unlikely that TIGER was ‘guessing correctly’.
3 Kruskal’s algorithm, https://en.wikipedia.org/wiki/Kruskal%27s_algorithm

Free Scenarios Numbers Six Through Ten!

We are continuing the list of thirty free scenarios that will be rewards for early backers of the General Staff Kickstarter campaign. These battle scenarios were the top vote-getters voted by you. Click here for the top 1-5 vote-getters.

The Battle of Austerlitz December 3, 1805. Click to enlarge.

Not surprisingly, this is not the first time that we have visited the battle of Austerlitz. Below is a screen shot from The War College (UMS III) which is, indeed, an ancestor of the General Staff Wargaming System.

Screen capture of Austerlitz from the War College (UMS III), a solid model 3D real-time simulation.

Austerlitz, sometimes called the Battle of Three Emperors, is one of Napoleon’s greatest victories. The General Staff system of multiple command layers should make for an interesting simulation of Austerlitz as orders travel from the Emperor to the subordinate commanders and then down to units. It will be very interesting to see how the new artificial intelligence routines react to this tactical situation.

Fantastic engraving of the battle of Saratoga from the Library of Congress. Definitely click to enlarge.

One of the most interesting features of General Staff is the ability to use the same map for different scenarios and we will certainly do that for the two scenarios at Saratoga in 1777. These two battles – the first considered a Pyrrhic British victory and the second a great American victory under the leadership of General Gates – eventually resulted in Burgoyne’s defeat which certainly encouraged French King Louis XVI to intervene on the side of the Americans.

German map of the battle of Gravelotte – Saint Privat made shortly after the battle. Click to enlarge.

Most Americans – myself included – know very little about the Franco-Prussian War so it was especially interesting to read up on the battle of Gravelotte (or Gravelotte–St. Privat) on 18 August 1870. The largest battle of the Franco-Prussian War, the Prussian victory sealed the fate of the French later trapped and besieged at Metz.

The Battle of Antietam scanned from the Official Military Atlas of the American Civil War and imported into the General Staff Map Editor. Click to enlarge.

The author walking across Burnside’s Bridge in 1966 (age of 12).

The Antietam battlefield is very special place for me. It is not as well known as Gettysburg and – at least during the 1960s – attracted very few visitors.  However, almost all of the battlefield is federal property and, unlike Gettysburg, has been preserved. It is eerily quiet.

Antietam is my ‘favorite’ battlefield; if one can have a favorite battlefield. I would visit Antietam with my father most summers. To the right is a picture my father took of me crossing Burnside’s Bridge in 1966. I was twelve at the time. In 1968 my father and I would visit Antietam for the last time. A month later he died of cancer.

Burnside’s Bridge – named after IX Corps Commander Major General Ambrose Burnside who was assigned the task of taking this bridge – is the key tactical feature in the southern part of the Antietam battlefield. We will do a General Staff scenario concentrating on this part of the battle.