19 October 2015 – Dr. Yin Kangkang and her collaborators won the Best Paper Award for their paper entitled ‘Learning Reduced-Order Feedback Policies for Motion Skills’, at the ACM SIGGRAPH/Eurographics Symposium on Computer Animation 2015 (SCA 2015) that was held in Los Angeles in early August.
Explaining their work, Dr. Yin said, “We introduce a method for learning low-dimensional linear feedback strategies for the control of physics-based animated characters around a given reference trajectory. This allows for learned low-dimensional state abstractions and action abstractions, thereby reducing the need to rely on manually designed abstractions such as the center-of-mass state or foot-placement actions. Once learned, the compact feedback structure allows simulated characters to respond to changes in the environment and changes in goals. The approach is based on policy search in the space of reduced-order linear output feedback matrices. We show that these can be used to replace or further reduce manually-designed state and action abstractions. The approach is sufﬁciently general to allow for the development of unconventional feedback loops, such as feedback based on ground reaction forces. Results are demonstrated for a mix of 2D and 3D systems, including tilting-platform balancing, walking, running, rolling, targeted kicks, and several types of ballhitting tasks.”
Researchers and practitioners from around the world gather at The Symposium on Computer Animation (SCA) to present and discover innovations in the software and technology of computer animation. The conference offers a ‘focused, intimate gathering, with single track program and emphasis on community interaction’, allowing attendees to discuss their work with each other and potentially inspire collaborations.