Context Steering for Smarter Autonomous Movement
Cutting-Edge Artificial Intelligence
Polarith AI is a comprehensive system for creating autonomously moving characters for your game or simulation. Being the result of years of research, AI experience and intense development, it uses new context steering algorithms to overcome the issues and difficulties classic steering approaches suffer from. By using our technology, you will massively reduce your steering code base, AI interdependencies and the effort for handling unwanted special cases. Instead of concentrating on getting your movement AI to work, you will be able to focus on things that really matter: The design of the AI behaviours for creating an interesting and astonishing movement that simply stands out.
Create and Prototype Great AI Rapidly
Forget about how you have used movement AI systems so far. Our artificial intelligence allows you to combine behaviours as easy as layers like it is known from image manipulation tools. Every shipped AI behaviour can be parametrized easily to achieve completely different effects without even touching the code at all. Besides these inbuilt behaviours, the system allows you to easily write you own ones with just a few lines of code.
The Context Matters
The major difference of context steering compared to classic approaches is that a decision is made based on the contextual information of an agent’s environment instead of weighting or prioritizing the output of the well-known classic steering (although you implicitly have this feature in Polarith AI, too). That is why the decisions made by our technology appear to be much more natural because it works more in the way humans make their decisions. When you decide about your future, you often do not simply add one possibility to another, instead you balance pros and cons to make the right decision which fits you best. That is exactly how Polarith AI works and how this balancing is applied can precisely be designed by you, the AI developer.
Much More Natural Decisions
Look at the example below where classic steering without a higher-level abstraction logic tends to run into deadlocks. Our small blue agent makes a very complex decision here and all it takes is a simple Seek steering. It decided to go for the right interesting object instead for the left one, although the right object is further away than the left one. Why? Because in the context of its situation, there is also a dangerous object on its left, so it knows that it is safer to go for the right object first. Polarith AI lets your agents consider these information at every time without the need for additional logic to handle such situations.
Scaling Based on Your Needs
Polarith AI gives you full control on how your agents observe the virtual world, whereby the sensor setup of an agent has direct impact on the performance. So you can create characters acting very accurate or hundreds of individuals getting by with less precision. This works very similar to the well-known level of detail (LOD) techniques used for graphics. For example, you can have nearby characters which operate precisely (using a high-resolution sensor) and far away characters (using a low-resolution sensor) so that no computation time is wasted. It is all up to your needs.
Observes the World as Desired
The plugin lets you control precisely how your agents observe the environment. Therefore, they can use circle shapes as well as line shapes (which work astonishingly great for spline-based racing simulations). Of course, you can use our editors to build your own custom sensor as well.
Ready for Multithreading
Our artificial intelligence lets you set up how frequent the system or single agents are updated. In addition to the scalability of the context steering approach, our system is entirely designed and built to support multithreading, whereby it smoothly works in harmony with Unity. So, the system lets you distribute the AI workload equally over as many threads as you want.
We know that AI tends to be very individual. Even though we try to make the inbuilt behaviours as universal as possible, there might be situations you need to write your own behaviours which match your application best. The API of Polarith AI is entirely written in C# and designed keeping that in mind. With help of the documentation, you will easily be able to extend the system to your needs. In order to give you some ideas, there are example AI behaviours which can be studied on GitHub at anytime.
Unity PluginUnity 5.3.0+ | all versions | all platforms
- Local decision making: Context steering
- Design-oriented and reusable
- Over 20 inbuilt plug-and-play behaviours
- Custom behaviours by programming C#
- Line, circle and custom sensors for 2D/3D
- Collider/visual AABB, OBB and NavMesh
- Single, crowd and swarm simulation
- Fits pathfinding and state handling
- Unique scalability with LOD technology
- High performance and multithreading
- Custom editors and in-scene debugging
Built for You
Everything we do, we do with passion. Besides all the things we have already done, there are way more features we would like to implement, and we will if you let us. With that said, every bought plugin is giving us the chance to make things even greater.
- Inbuilt path structure and behaviours
- Automatic LOD switching
- Overhauled custom UI
- Advanced asynchronous load balancing
- Racing behaviours
Possible Future Features
- Advanced 3D and mesh based sensors
- Lazy percept receiving
- Advanced terrain behaviours
- Faster spacial perception queries
- Fuzzy/utility logic (general decision making)
We advice to combine Polarith AI with pathfinding to master complex scenarios like labyrinths autonomously. Therefore, the inbuilt behaviours enable agents to follow waypoints very easily.
We want you to create the greatest AI for your application. So it would be a real pleasure for us to help you out as best as we can. Just send us a mail using our contact form or utilize the following possibilities for being supported.
We will respond most certainly in less than half a day!
Learn How It Works Best
We try to make your learning phase as comfortable as possible. Therefore, we have prepared a manual, a detailed (API) documentation and, a lot of example scenes you get buying the plugin. In addition, we will publish more and more video tutorials over time. If that is not enough or you are confronted with problems, just shoot us a mail, and together, we will find decent solutions.
Follow our quick start guide to get comfortable with Polarith AI. There is a whole new world to explore and if you already like steering, you will love context steering.
The product manual of Polarith AI contains general information about the whole system and allows you to gain deeper knowledge about the basic principles and the algorithms behind our technology.
Get comfortable and grab a cup of coffee or any other magical beverage, and delve deeper into the realms of Polarith AI. Learn how to extend the plugin to your needs and get to know how capable our movement AI really is.
Our Technology in Your Individual Application
If you do not want to or cannot use Unity but you are still interested in using context steering for your project, then contact us. The Polarith AI plugin is only the tip of the iceberg concerning our artificial intelligence expertise. Together, we make the AI of your project really stand out.
Tell Your Story
Are you using our technology in your project? We would love to hear and tell your story!