GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of sessions by day, pass type, topic, and format. With this Session Viewer, you can view GDC 2023 session details and speakers, and share your favorites via social media. You will be able to build your schedule and access it during the show via export or Mobile App, once live. Sessions do fill up and seating is first come, first serve, so arrive early to sessions that you would like to attend.

Machine Learning Summit: 'Wobbledoll': ML-Powered Self-Balancing Synthesis Ragdoll

Nan Ma  (Senior Game Engine Developer, LIGHTSPEED STUDIOS)

Location: Room 2010, West Hall

Date: Tuesday, March 21

Time: 4:40 pm - 5:10 pm

Pass Type: All Access Pass, Summits Pass

Topic: Programming

Format: Lecture

Vault Recording: Video

Audience Level: All

Realistic full-body physical interactions have long been a major challenge for the gaming industry. Numerous solutions have been proposed, from basic animation and IK-based solution to more intricate middleware such as Euphoria by Natural Motion. However, many development teams find these approaches are either designed to only function under specific conditions or overwhelmingly complicated and impractical to implement. Machine learning can be utilized as an aid in the execution of realistic full-body physical interactions. Our methods have demonstrated the potential for generating high-fidelity motions for a variety of physical interactions, whilst being substantially more accessible in terms of engineering complexity.


Attendees will be informed of how machine learning contributes to comprehensive reaction solutions that work harmoniously with locomotion systems. Additionally, they will be apprised of AI training analysis and in-game profile results along with the tech demo, which provides a thorough technical evaluation for the performance of both offline training and real-time execution.

Intended Audience

This session is intended for game developers who wish to address pertinent technical issues and designers who aspire to engage in further research and development in the realm of physical animation powered by Artificial Intelligence.