Human Motion Prediction

Human motion prediction estimates future body poses or paths from observed movement, often using skeleton sequences and sometimes scene, object, social, or language cues. Methods include temporal Transformers and graph networks, as well as probabilistic models, diffusion, and flow matching that represent multiple plausible futures; physical constraints can help keep predictions smooth and anatomically consistent. Researchers evaluate pose forecasts on benchmarks such as Human3.6M and AMASS, and pedestrian paths on ETH/UCY, with growing attention to interaction-rich settings and robot collaboration. A central challenge is balancing accurate point forecasts with diverse, calibrated, physically plausible futures that generalize from clean motion-capture data to noisy real-world observations.