Character Control News
The latest Character Control coverage curated for game developers.
ACM Graphics details HIL, a hybrid imitation learning approach for dynamic athletic control that targets more responsive character motion. The work sits in ACM Transactions on Graphics 46(2) and points …
arXiv cs.GR details Co²Skill, a whole-body control policy that composes locomotion and dexterous manipulation for long-horizon human-environment interaction. The system uses a pretrained motion prior plus task- and phase-dependent observation …
arXiv cs.GR details LYRIC, a physics-based character controller that turns free-form language into contact-rich whole-body interactions. For game teams, the interesting part is the split between a task planner and …
arXiv cs.GR details DSD, a diffusion-based skill discovery method that learns a wider set of reusable humanoid motor skills. For game teams building animation or AI-driven characters, the pitch is …
A new muscle-driven locomotion system uses a fixed reflex controller plus reinforcement learning to tune just four biomechanical parameters. The result is more plausible gait, better symmetry, and stronger robustness …
A diffusion-based motion system now takes numeric effort signals instead of vague adverbs, which is a big deal for anyone trying to direct character intensity more precisely. The paper maps …
NaP-Control uses reinforcement learning to steer a diffusion policy’s latent noise, aiming for whole-body character control that is both fast and robust. The approach skips iterative test-time guidance, which can …