The Windows installer for the latest version of AnimatLab can be obtained here AnimatLab V2 Version 2.1.5. You can find the source code for AnimatLab on the SDK page. You should have Windows 7 or greater operating system. A machine with a good graphics accelerator is strongly recommended. We have plans to get this application running on other operating systems in the near future.
Please see the "Getting Started" page to find the key tutorials you will show you what you need to know to get up to speed on installing and using AnimatLab. There is now a video tutorial on how to use the new features and the user interface for AnimatLab 2!
If you have any problems with installing or using AnimatLab then please check the postings on the forums section. If you do not see anything already there on your problem then please add it and we will try and respond.
An AnimatLab Handbook is also now available. It provides details on how to use the various features of AnimatLab. It comes as either a PDF or a word document.
If you still need version 1 of AnimatLab then you can download it as well, AnimatLab V1.0. The original SDK is also available. However, please be aware that version 1 is no longer being supported. There will be no new updates for this version of the application. So unless you have a really good reason for using the older version I would strongly recommend you use the new version. The original Locust simulations and human myotactic reflex simulation from the first AnimatLab papers are available in their original download locations also.
The AnimatSimulator is now available for download for the Ubuntu operating system. The simulator should also run in other versions of Linux, but to use those you will need to go to the Linux SDK page and compile directly from source. Also, the install package available here is only for 64 bit versions of the Ubuntu (amd64). It has been tested on Ubuntu 12.04. If you want to use it on a different version of Ubuntu, or have trouble getting it work on your system then please see the SDK page here for detailed instructions on how to build from source. The debian install package can be downloaded here (animatsimulator_2.1.2_amd64.deb). The steps needed to get it to install are listed below. Terminal commands are shown with a grey background, while packages that need to be installed are shown in light blue.
AnimatLab 2.1.5 Release.
This is a minor release that fixes some licensing issues to make sure it is free.
AnimatLab 2.1.4 Release This is a minor release for a bug fix related to the AnimatSerial interface.
AnimatLab 2.1.2 is a Major Release The first version of the AnimatLab Robotics Framework is released! It has taken longer than I hoped it would to get this release finished. However, I ended up having to add a lot more features than I thought I would have to in order to make it really useful. Getting the release and tutorials out is such a big job that I wanted to get more functionality in before I had to deal with that. There is still more work to do to get the robotics framework to do all the things I want, but I felt this was a good stopping point where I could get it out into the hands of other people to start using. The new robotics framework takes AnimatLab beyond pure neuromechanical simulation, and makes it very easy for almost anyone to build real, biologically inspired robots that use nervous systems based on how real animals control their behaviors. The framework makes it easy because it takes most of the difficult engineering work of interfacing with the hardware out of the equation. You can build very complex, biomimetic robots without having to write a single line of source code, or know anything beyond some very basics of electronics, and all of this using commercial off the shelf components. You can build AnimatLab simulations just as you are used to doing, and later on add robot part interfaces that connect motorized joints and sensors to corresponding real servos and sensors, and your neural control system does not know, or care, whether it is talking to real hardware or the simulation. I have also added controls to allow you to use joysticks and other interfaces to interact with the nervous system simulation. So for instance, you can use a wireless joystick to move a robot arm within your simulation. The Robotics Framework runs in both 32 bit and 64 bit windows, and it runs on Ubuntu. I have also tested it on both an Odroid U3 and NVIDIA Jetson TK1 micro-computer. Finally, I have created seven new detailed video tutorials, totaling over two hours, that show you in a step-by-step fashion how to use the robotics framework to build and control a working robot arm, along with new documentation of the framework. Major Changes 1. You can now add robot part interfaces to your existing simulations to control real hardware using the neural network control system from your simulation. Please see the Robotics documentation for more details. 2. AnimatLab now has a framework in place to allow physical devices to interact with a neural network in a simulation or on a robot. Right now only the wireless XBee commander joystick is supported, but I plan to add keyboard and standard joystick interactivity soon. Please see the remote control documentation for more details. 3. I have created realistic mesh files for all parts of the base Bioloid robot frame kit. They are available for free in the AnimatWarehouse. 4. Contact sensors can now become "sticky." Your neural network can turn on/off the stickiness of a contact sensor, and when it is on and comes into contact with another part in the scene they will stick together until stickiness is turned off. I used this in the robot arm simulation to allow the gripper to pick up parts. However, there are a number of other applications. For example, you could simulate a gecko's ability to walk up walls. 5. You can now specify a target data type for adapters. Previously the incoming data type for a node was hard-coded. Now it is possible for the user to change it. The main place where this is used is to allow you to have two adapters connected to a joint where one lets you control the target position and the other sets the target velocity. 6. You can now setup a delay buffer on any adapter, and you have the ability to disable all output from an adapter for a given period immediately after the simulation starts in order to allow the neurons in your simulation to settle down to a steady state. 7. There are now CodeBlocks project files for all the simulation libraries for use on Linux. 8. I added a new Modulate Neuron Property synapse to the Firing rate neural plug-in. This allows you to modify any of the properties of the post-synaptic neuron based on the firing rate of the pre-synaptic neuron. 9. I have created a new video channel on YouTube. (https://www.youtube.com/channel/UCHZcRY-8XNgVi076gQ4v0UQ). I have transferred all of my video tutorials up to my YouTube channel, including the ones on the robotics framework. I am in the process of building a hexapod robot that will use a CUDA enhanced neural network to control its movements and behaviors. I plan to start posting a number of small videos to document my progress as I go along. So please subscribe to the channel so you can follow new videos as they are added. Here are links to the new video tutorials: AnimatLab Robotics Framework Introduction: http://youtu.be/0sl_BXC-us4 AnimatLab Robotic Arm Video Tutorial: Simulation Setup: http://youtu.be/pIiYzw6Buso AnimatLab Robotic Arm Video Tutorial: Robot Control Part 1: http://youtu.be/_U3dt9aYu4A AnimatLab Robotic Arm Video Tutorial: Robot Control Part 2: http://youtu.be/Chmfke9kWeM AnimatLab Robotic Arm Video Tutorial: Joystick Control: http://youtu.be/ZQgZ8FqBmCc AnimatLab Robotic Arm Video Tutorial: Position and Velocity Control: http://youtu.be/gqXyxMu545w PhantomX Hexapod Preview: http://youtu.be/2foAdjMvI1A Whats Next! I have already made a lot of progress integrating the CARLsim GPU-accelerated spiking neural network library (http://www.socsci.uci.edu/~jkrichma/CARLsim/) into AnimatLab. It will allow users to visually layout large populations of neurons and syanpses and run them on NVIDIA GPUs using CUDA. In particular, I am targeting the NVIDIA Jetson TK1 embedded supercomputer for robotic applications, but it will run on any NVIDIA graphics card.
AnimatLab 2.1.1 is a Minor Release AnimatLab simulations on Linux! This release of AnimatLab allows you to run the AnimatSimulator with the Bullet physics engine on Linux computers. I have tested it on Ubuntu 12.04, but it should work just as well on any other variant of Linux. The GUI editor will still only run on Windows for the moment. I plan to port it over to run on Linux as well over the next year, but there are a number of technical hurdles that have to be overcome to do that. So for the moment you must still use the GUI to build your simulations, and then you can export them and run them on the stand alone simulator on a Linux system. Below is a list of the changes for this release. Major Changes 1. There is now a new section on the AnimatLab download page for installing the simulator on 64-bit Ubuntu computers. I provide a debian install package and list out the steps you will need to perform to get that installed and working. 2. For those who want to do development, or get the simulator to run on a different variant of Linux, I have also added a new AnimatLab Linux SDK page. A tar.gz file is provided with all the source code necessary, along with a very detailed, and numerous, list of steps you will need to follow to get it to where it will compile and run. If you do get the simulator running on a different flavor of Linux then please let me know. 3. I modified the GUI to make it easy to export your simulations for Linux. When you select File/Export standalone sim there is now an operating system option in the export dialog. You will only be able to set the OS on physics engines where it is available (Robotics and Bullet at the moment). When you select Linux it will export the simulation files with the modifications necessary to run it on on that platform. The names of the library files and executable are different to comply with Linux naming conventions. 4. I have simplified the way that you start-up the AnimatSimulator. Previously, you had to specify "AnimatSimulator -Library library_name -Project sim_file", and the library you choose had to match the ones in the file or it could cause problems. Now all you have to do is specify the simulation file and it gets the library information from that. The new format is "AnimatSimulator sim_file". Whats Next! This month I will be receiving several micro-computers (Odroid U3, nVidia Tegra, and a Parallella). I plan to get the simulator running on all of those and add to the robotics framework to control motors and read sensors from those devices GPIO ports.
AnimatLab 2.1.0 is a major release The beta version of the open-source Bullet physics engine plug-in has now been released. This means that if you use Bullet for your physics, then the AnimatSimulator is now free and 100% open-source! The GUI editor does have a standard and Pro version, but all source code for the simulation component is fully open-sourced and available for download. Special thanks to Dr. Donald Edwards of Georgia State University for financially supporting the creation of this new physics plug-in. It has taken over half a year of work to get this beta version released. Here is a list of the changes in this new version.
Version 2.0.6 is a major release.
It has been a while since I last updated AnimatLab. The main reason for this is I have been working hard to finish off some of the last remaining large bugs, and I have been trying to finish off all the smaller bugs I could. So there are a whole lot of fixes in this release. I have broken this out into major and minor changes below. If you find any additional bugs then please report them on the bugs forum and I will attempt to get them fixed. This is the last Beta release of Animatlab 2.0. I plan for the next version to be a production release.
Major Issues/changes
Minor Issues
Version 2.0.5 fixed three minor bugs. Bug fixes are listed below.
Version 2.0.4 fixed several major bug fixes, and added a few new features. Fixes are listed below.
Version 2.0.3 fixed several major bug fixes. Bug fixes are listed below.
Version 2.0.2 had a number of bug fixes, and a significant new feature.
This project was supported by: