The goal of this research is to create physically simulated biped characters equipped with a rich repertoire of motor skills. The user can control the characters interactively by modulating their control objectives. The characters can interact physically with each other and with the environment. We present a novel network-based algorithm that learns control policies from unorganized, minimally-labeled human motion data. The network architecture for interactive character animation incorporates an RNN-based motion generator into a DRL-based controller for physics simulation and control. The motion generator guides forward dynamics simulation by feeding a sequence of future motion frames to track. The rich future prediction facilitates policy learning from large training data sets. We will demonstrate the effectiveness of our approach with biped characters that learn a variety of dynamic motor skills from large, unorganized data and react to unexpected perturbation beyond the scope of the training data.

No abstract

No abstract

We present a novel retargeting algorithm that transfers the musculature of a reference anatomical model to new bodies with different sizes, body proportions, muscle capability, and joint range of motion while preserving the functionality of the original musculature as closely as possible. The geometric configuration and physiological parameters of musculotendon units are estimated and optimized to adapt to new bodies. The range of motion around joints is estimated from a motion capture dataset and edited further for individual models. The retargeted model is simulation‐ready, so we can physically simulate muscle‐actuated motor skills with the model. Our system is capable of generating a wide variety of anatomical bodies that can be simulated to walk, run, jump and dance while maintaining balance under gravity. We will also demonstrate the construction of individualized musculoskeletal models from bi‐planar X‐ray images and medical examination.

In context-aware computing, the context aggregation is an important function of the context management. In an infrastructure-based smart space, a centralized context management system need not concern about its resource consumption for context aggregation. However, in a personal smart space which consists of only resource-constrained mobile devices, not only global resource consumption of the personal smart space but also that of the device which plays a role of a context manager (coordinator) must be minimized. In this paper, we propose a task decomposition scheme in which heavy context aggregation tasks to be imposed on a centralized coordinating device are decomposed and distributed to all the participating mobile devices (clients) in a mobile smart space. By decomposing and distributing the heavy aggregation operations the processing overhead upon the coordinating device can be minimized while providing equivalent context aggregation capability for applications, but maintaining the total amount of processing of all devices not to be significantly increased.