Over the last week I had 5 playtesters trying out my current version of the game.

To pass the level there was a requirement that the player had to survive for a certain amout of time to pass the level they played. This time was converted into a score and a target score had to be reached; I noticed that players liked accumulating points rather than finishing the level quickly. I did not like this so the target is now a bar that fills up instead of accumulates.

A roaring consensus told me that the single object of surviving for a certain length of time in order to pass the level was incredibly boring. My playtesters agreed that a second of object, a snatch and grab kind of play, would be far more interesting.

I felt the whole game was a little fast for my liking, my play testers on the other hand thought it was a little slow. I’ve decide to alternate the speed of the game a little bit, speeding up the guards to make them feel like they are actually chasing you while adding a penalty for having the player run.

I asked if I should leave the particle filter on during game play; the playtesters thought, while interesting, it made the game far easier.

Some players commented on the movement of the guards and some of their more subtle behaviour. I am endeavour to fix them as best as possible.

Other suggestions mostly were around having pick-ups/power-ups, snares, laser alarms and other things to create more challenging gameplay.

So far my thesis topic has been a big learning curve for me. I had never really thought of trying my hand at game design, which is why I was slightly hesitant when I came to understand that the game engine I would be using for experimentation was somewhat “a work in progress”.  Throughout the uni break I was working almost diligently on modification of the game mechanics to something I was happy to start working with. It is a pleasure to say that I am almost there.

I am happy to report that I am pretty much to schedule with what I had intend to have ready by second semester. I have namely been experimenting with different  methods of motion planning and am surprised as how something so simple can drastically change the feel of game play. The two methods I have mainly been looking at are;

1. Delauny Triangularization using equidistant points between the level boundaries
2. Random Roadmap methods which employ generating a number of random points across the level and running Delauny triangularization across them as to create suitable paths for the AI to explore.

While the first method is quite simplistic and reliable, the paths the AI take can be reasonably limited in the exploration space. The second methods is interesting as every game is slightly different, and with the monotony of testing it is nice to have the playing ground mixed up; but whether this is suitable for an actual, solid implementation, I’m not sure. What I am doing at the moment is working on constructing my own paths about the level, “hand drawn” if you will.

As far as tracking goes I have implemented a shared particle filter. Every guard contributes to the maintaining and updating of the single distribution. I have found, while being a very simplistic approach, that it is unsuitable. During the resampling portion of the particle filter algorithm, a single focal point tends to emerge when the distribution contains less than about 500 particles. This becomes incredibly boring to play with as every guard then heads towards this single point, converging uselessly – especially when the centre of the mass is chosen. The guards paths then tend to overlap more than my liking, and this is not the behavior I would like to see emerging.

So far I have not experimented to much with planning algorithms, but the night is still young, as it were. So far I have only looked at choosing points at random from the cloud or sampling them in order to find the mean of the distribution. As above, sampling the mean of the single distribution makes the game play quite boring. What I would like to try is taking a handful of particles, randomly, and finding their mean as to determine a psuedo-mean. I am hoping this method will provide what I originally sort after and reduce the overlapping of search paths.

Upon doing further research and receiving feedback from my presentation, the direction and focus of my thesis has slightly shifted. I will still be proceeding with the development of an artificial agent that plays the pursuit evasion game, ArtOfStealth, convincingly and realistically, but I will also be looking at creating a modifiable agent framework which can be used to create different functionality and behaviours by using a parameterised and expendable particle filter.

I will also be running a series of experiments using a range of different modifications of this particle filter to see what different kinds of behaviours I can achieve by the modification of 3 main components; the number of particles used to represent the probability density function, the motion model used to predict the movement of player and hence the particles, and also the  observation model used to update the particle distribution.

There are a huge number of different aspects I could look at in this project but I will be trying to narrow the scope such that I don’t get too sidetracked from my initial proposal and also so my project doesn’t blow out of proportion in terms of work and complexity. Because of this I will be looking at only a limited number of algorithms for use in the decision making process and planning process.