Overview

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.

Latest papers

61 papers8 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jan 10, 2024

AdvMT: Adversarial Motion Transformer for Long-term Human Motion Prediction

Human motion prediction is a crucial capability for advanced robotic systems that interact with humans. In facilities with dynamic human-robot collaboration settings, robots must anticipate human movements to ensure safety, prevent collisions, and optimize cooperative tasks. Traditionally, motion forecasting is treated as a sequential modeling problem using historical pose data, but achieving long-term accuracy and physical realism remains challenging. We present Adversarial Motion Transformer (AdvMT), a novel approach that integrates a Transformer-based motion encoder with a temporal continuity discriminator to address these challenges. The Transformer captures rich spatio-temporal dependencies across human joints, while adversarial training with a continuity discriminator enforces smooth, natural motion trajectories that adhere to biomechanical constraints. Our training scheme includes a bone-length consistency term and adversarial loss to reduce common artifacts like pose freezing or unnatural transitions. In experiments on the Human3.6M motion dataset, AdvMT achieves state-of-the-art long-horizon prediction accuracy while also delivering robust short-term predictions. These improvements strengthen the prediction foundation for physical AI in manufacturing and human-robot collaboration, where anticipating human motion is a prerequisite for safe and efficient robot coordination.