Tag Archives: Envelopment Maneuver

A Human-Level Intelligence at Quatre Bras

17 Replies

Quatre Bras, June 16, 1815. Click to enlarge

Napoleon has humbugged me, by God!” Lord Wellington swore. “He has gained twenty-four hours’ march on me!” 1)David Chandler, Waterloo: The Hundred Days, Macmillan Publishing Co., Inc. New York 1980, p. 85 And, indeed, he had.

The Armée du Nord, racing north on the roadnet from Paris to Brussels, now occupied the crucial strategic ‘central position’ between the Anglo-Allied army under Wellington assembling at Quatre Bras in the west, and the Prussian army under Blücher at Ligny in the east. Napoleon, outnumbered by the combined forces of Wellington and Blücher only had one realistic option: destroy his opponent’s armies separately before they could combine and destroy him.

Napoleon divided the Armée du Nord into two wings (the left commanded by Marshal Ney and the right by the Emperor, himself). The Imperial Guard would serve as the strategic reserve. In our previous blog, we showed the MATE (Machine Analysis of Tactical Environments) artificial intelligence analysis of the battle of Ligny.

The starting positions of the Armée du Nord (Blue) and the Anglo-Allied Army (Red) at the battle of Quatre Bras. Screen shot from General Staff: Black Powder. Click to enlarge.

The positions in the above screen shot come from the West Point Atlas of the Napoleonic Wars and Chandler’s Waterloo: The Hundred Days. I’ve ordered Mike Robinson’s The Battle of Quatre Bras, 1815 (which is very highly regarded) but it’s coming from Europe and will be a while before it arrives. I’ll update the positions accordingly when it arrives.

Today MATE is going to show off a new trick that it learned.

MATE AI analysis of Blue’s position. General Staff screen shot. Click to enlarge.

Text output and author’s commentary of MATE’s analysis of Blue’s position at the battle of Quatre Bras.

The salient points of MATE’s analysis of Blue (Ney’s) position at the battle of Quatre Bras are:

  • Red (Wellington) has an open flank (in fact, both of Red’s flanks are exposed but MATE has calculated a left flanking maneuver is shorter than a right flanking maneuver)
  • Blue has a reserve cavalry division (Line #25 in the text output above, Battle Group #3, Pire’s 2nd Cavalry Division) that is in position to spearhead the left flanking maneuver ahead of
  • Battle Group #1 (the 6th Division commanded by Prince Jerome) which will follow as the main strike force of the left flanking maneuver (Line #23)
  • Battle Groups #0 and #2 (Reilles and Foy’s divisions) will be the fixing force attacking Gémioncourt in the classic envelopment maneuver (see below):
  • Battle Group #4 (Kellerman’s reserve cavalry division) will snatch the important crossroads at Thyle.

In other words, Battle Groups #3 and #1 will be the Enveloping Force and Battle Groups #0 and #2 will be the Fixing Force as illustrated in the above graphic from the U. S. Army Field Manual 3-21. Algorithms for implementing this maneuver (an early version of MATE) first appear in my paper, Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.

And MATE’s new trick? It’s in line #25, above. If there is a Battle Group that is composed entirely of  cavalry and horse artillery, and it is close enough, it will be used as the spearhead for the flanking maneuver.

MATE’s analysis of Ligny. Screen shot from General Staff AI Editor. Click to enlarge.

But, in this situation (Ligny, above) MATE has calculated that Battle Group #1 will get to the crucial Choke Point (labeled in black, above) before the reserve cavalry Battle Group #4 will arrive and would create a tremendous bottleneck at the very choke point that MATE wants to quickly capture. Consequently, the cavalry has been left in reserve.

Mini MATE FAQ

Can MATE read and analyze any battle map from history?

No. MATE is integrated into the General Staff Wargaming System. MATE can only ‘understand’ Order of Battle (OOB) tables created in the General Staff Army Editor, maps created in the General Staff Map Editor and scenarios created in the General Staff Scenario Editor.

What is meant by a ‘human-level’ artificial intelligence?

Perhaps you have heard of the famous Turing Test (from Alan Turing’s Computing Machinery and Intelligence). In it he describes, “The Imitation Game,” where a computer is in one room behind a closed door, and a human is another room behind a closed door. A third person, the ‘interrogator’, can only ask questions via a teletype (an ancient I/O device consisting of a keyboard and a printer) and must determine in which room the computer is and in which room is the human. In Turing’s original paper the interrogator would ask questions of the two subjects such as, “Please write me a sonnet on the subject of the Forth Bridge,” and, “Add 34957 to 70764.” Currently, no Artificial Intelligence (AI) could pass such a test; the subject area is far too broad. However, it has been my thesis, that an AI could pass such a test if the subject area is restricted to a narrow field of human endeavor, such as commanding units on a battlefield. If, in the above Turing test, the computer in one room was replaced with MATE, the human in the other room was replaced by Napoleon, and the teletype was replaced by the General Staff Wargaming System, I argue that MATE could (or soon will be able to) pass such a test (subject matter experts would not be able to discern if it was MATE or Napoleon giving orders).

Can MATE analyze current military situations?

Though MATE came out of the TIGER (Tactical Inference GenERator) project funded by DARPA, it is currently set up specifically for the General Staff: Black Powder project which limits analysis to scenarios in the 18th and 19th centuries. It is intended that this project will be followed up with General Staff: Modern Warfare to specifically work with 20th and 21st century combat.

References

References
↑1 David Chandler, Waterloo: The Hundred Days, Macmillan Publishing Co., Inc. New York 1980, p. 85

A Wargame 55 Years in the Making (Part 3)

4 Replies

The goal of my doctoral research was to create a suite of algorithms that were capable of making ‘human-level’ tactical and strategic decisions. The first step is designing a number of ‘building block’ algorithms, like the least weighted path algorithm that calculates the fastest route between two points on a battlefield while avoiding enemy fire that we saw in last week’s post. Another important building block is Kruskal’s Minimum Spanning Tree algorithm which allows the computer to ‘see’ lines of units.

I use terms like ‘see’ and ‘think’ to describe actions by a computer program. I am not suggesting that current definitions of these terms would accurately apply to computer software. However, it is simply easier to write that a computer ‘sees’ a line of units or ‘thinks’ that this battlefield situation ‘looks’ similar to previously observed battlefields. What is actually happening is that units are represented as nodes (or vertices) in a a graph and some basic geometry is being applied to the problem. Next week we will use probabilities. But, at the end of the day, it’s just math and computers, of course, don’t actually ‘see’ anything.

Examples of how Kruskal's Minimum Spanning Tree algorithm can be used to separate groups of units into cohesive lines. These figures are taken from, "Implementing the Five Canonical Offensive Maneuvers in a CGF Environment." by Sidran, D. E. & Segre, A. M.

Examples of how Kruskal’s Minimum Spanning Tree algorithm can be used to separate groups of units into cohesive lines. These figures are taken from, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” by Sidran, D. E. & Segre, A. M.

When you and I look at a map of a battle we immediately see the opposing lines. We see units supporting each other, interior lines of communication, and lines of advance and retreat. The image, below, shows how the program (in this case, TIGER, the Tactical Inference Generator which was written to demonstrate my doctoral research) ‘sees’ the forces at the battle of Antietam. The thick black line is the ‘MST Spine’. You and I automatically perceive this as the ‘front line’ of the Confederate forces, but this is a visual representation of how TIGER calculates the Confederate front line. Also important is that TIGER perceives REDFOR’s flanks as being anchored (that is to say, BLUE does not have a path to the flanking objective, the tip of the green vector, that does not go through RED Range of Influence, ROI, or Zone of Control).

Figure 1. TIGER screen shot of ‘flanking attribute’ calculations for the battle of Antietam (September 17, 1862, 0600 hours). Note the thick black line that repres ents the MST spine of REDFO R Group 0, the extended vectors th at calculate the Flanking Goal Objective Point and BLUEFOR and REDFOR ROI (red and blue shading). REDFOR (Confederate) has anchored flanks.

TIGER screen shot of ‘flanking attribute’ calculations for the battle of Antietam (September 17, 1862, 0600 hours). Note the thick black line that represents the MST spine of REDFOR Group 0, the extended vector that calculates the Flanking Goal Objective Point and BLUEFOR and REDFOR ROI (red and blue shading). REDFOR (Confederate) has anchored flanks. From, “Algorithms for Generating Attribute Values for the Classification of Tactical Situations,” by Sidran, D. E. & Segre, A. M.

Now that TIGER can see the opposing lines and recognize their flanks we can calculate the routes for implementing the Course of Action (COA) for various offensive maneuvers. U. S. Army Field Manual 3-21 indicates that there are five, and only five, offensive maneuvers. The first is the Penetration Maneuver (note: the algorithms for these and the other maneuvers appear in, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” by Sidran, D. E. and Segre, A. M.) and can be downloaded from ResearchGate and Academia.edu.

The Penetration Maneuver is described in U.S. Army Field Manual 3-21 and as implemented by TIGER. Note how TIGER calculates the weakest point of REDFOR's line. From, "Implementing the Five Canonical Offensive Maneuvers in a CGF Environment." by Sidran, D. E. and

The Penetration Maneuver is described in U.S. Army Field Manual 3-21 and as implemented by TIGER. Note how TIGER calculates the weakest point of REDFOR’s line. From, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” by Sidran, D. E. and Segre, A. M. Click to enlarge.

The next maneuver is the Infiltration Maneuver. Note that to implement the Infiltration Maneuver, BLUEFOR must be able to infiltrate REDFOR’s lines without entering into RED’s ROI:

The Infiltration Maneuver.

The Infiltration Maneuver as described in U.S. Army Field Manual 3-21 and as implemented by TIGER. Note how TIGER reaches the objectives without entering into REDFOR ROI. From, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” by Sidran, D. E. and Segre, A. M. Click to enlarge.

The next maneuver is the Turning Maneuver. Note: in order to ‘turn an enemy’s flanks’ one first must be able to recognize where the flanks of a line are. This is why the earlier building block of the MST Spine is crucial.

The Turning Maneuver as illustrated in U. S. Army Field Manual 3-21 and in TIGER.

The Turning Maneuver as illustrated in U. S. Army Field Manual 3-21 and in TIGER. From, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” by Sidran, D. E. and Segre, A. M. Click to enlarge.

Certainly the most complex offensive maneuver is the Envelopment Maneuver which requires two distinct movements and calculations for the attacking forces: first the attacker must decide which flank (left or right) to go around and then the attacker must designate a portion of his troops as a ‘fixing force’. Think of an envelopment maneuver as similar to the scene in Animal House when Eric “Otter” Stratton (played by Tim Matheson) says to Greg Marmalard (played by James Daughton), “Greg, look at my thumb.” Greg looks at Otter’s left thumb while Otter cold-cocks Marmalard with a roundhouse right. “Gee, you’re dumb,” marvels Otter. In an envelopment maneuver the fixing force is Otter’s left thumb. Its purpose is to hold the attention of the victim while the flanking force (the roundhouse right) sweeps in from ‘out of nowhere’. In the next post I will show a real-world example of an Envelopment Maneuver created by my MATE (Machine Analysis of Tactical Environments) program for DARPA.

The Envelopment Maneuver as shown in U. S. Army Field Manual 3-21 and as implemented in TIGER.

The Envelopment Maneuver as shown in U. S. Army Field Manual 3-21 and as implemented in TIGER. From, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” by Sidran, D. E. and Segre, A. M. Click to enlarge.

Lastly, and obviously the maneuver of last resort, is the Frontal Assault:

The Frontal Assault Maneuver from

The Frontal Assault Maneuver from, “Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.” by Sidran, D. E. and Segre, A. M. Click to enlarge.

All that I’ve done in this post is show some of the things that the TIGER program does. What I haven’t done is show how the algorithms work and that’s because they are described in the papers, below. Obviously, this is a subject that I find pretty interesting, so feel free to ask me questions (you can use the Contact Us page).

It is my intention to incorporate these algorithms into the General Staff wargame. However, I’ve been told by a couple of game publishers that users don’t want to play against a human-level AI. What do you think? If you’ve read this far I would really appreciate it if you would answer the survey below.
[os-widget path=”/drezrasidran/survey-11-27″ of=”drezrasidran” comments=”false”]

Papers that were cited in this post with download links:

“An Analysis of Dimdal’s (ex-Jonsson’s) ‘An Optimal Pathfinder for Vehicles in Real-World Terrain Maps'”

In PDF Format

“Algorithms for Generating Attribute Values for the Classification of Tactical Situations.”

In PDF Format

“Implementing the Five Canonical Offensive Maneuvers in a CGF Environment.”

In PDF Format