Disclaimer: We may earn a commission if you make any purchase by clicking our links. Please see our detailed guide here.

Follow us on:

Google News

Facebook’s AI Research Department is Training AI to Play Boxing Matches

Bipasha Mandal
Bipasha Mandal
Bipasha Mondal is writer at TechGenyz

Join the Opinion Leaders Network

Join the Techgenyz Opinion Leaders Network today and become part of a vibrant community of change-makers. Together, we can create a brighter future by shaping opinions, driving conversations, and transforming ideas into reality.

Facebook is training AI to play boxing matches. Facebook’s artificial intelligence research department is responsible for this development. The researchers associated with this project have developed a learning framework that stimulates the training route of people engaged in learning various sports to learn basic skills, round-level strategies, and much more. Moreover, they have also developed a strategy for the encoder-decoder structure that allows physical simulation roles to be trained and learned. The researchers also showcased the strategies in the framework through boxing and fencing.

One of the main challenges the researchers had to face was multiplayer animation since it requires that the interaction between various characters is synchronized in time and space. Moreover, the fact that there is very little data on the coordination of different skills makes the project much harder. In the research paper titled “Control Strategies for Physically Simulated Characters Performing Two-player Competitive Sports”, FAIR explored some of the techniques of training control systems. It developed a framework that generates control strategies.

The brainchild of this program, the humanoid robot, consequently, has greater freedom and is driven by joint torque. FAIR’s project uses deep reinforcement learning for the characters to acquire basic skills and learn competition-level strategies. The framework developed by FAIR uses a set of sports data, which generates the control strategies of two physical simulation players, allowing the characters to perform a set of basic skills using the right technique, which will prompt the player to win the game.

For the simulation to work, the researchers will first have to collect some movement data and then engage the deep reinforcement learning method. Finally, the imitation strategy becomes a competitive strategy. For this, the researchers use a new strategy that consists of a task encoder and a motion decoder. However, there still are huge problems with this motion capture, mainly because of the interaction among multiple agents, which becomes difficult to capture. FAIR designed a framework to overcome this problem that captures the motion data. First, they capture the action using an agent, and then the required interaction is created through simulation and learning techniques.

The model developed by FAIR needs a significant amount of calculations to generate a legitimate competition model. More data becomes necessary for this model to apply to other sports, such as basketball or football. One solution to this problem is breakthroughs in learning algorithms or simply by collecting more data.

Although the model can generate two animated characters who can compete with each other, the quality of the input reference also decides the natural degree of action performance.

Although FAIR’s research still has many limitations, it is mostly concerned with coming up with a simulation method that allows humans to interact using AI. Hopefully, this will open up new forms of application in computer games, commercial films, and other sports events.


Partner With Us

Digital advertising offers a way for your business to reach out and make much-needed connections with your audience in a meaningful way. Advertising on Techgenyz will help you build brand awareness, increase website traffic, generate qualified leads, and grow your business.

Power Your Business

Solutions you need to super charge your business and drive growth

More from this topic