Prediction of Human Full-Body Movements with Motion Optimization and Recurrent Neural Networks
This work addresses the problem of predicting complex human movements for applications like human-robot coordination, but it appears incremental as it combines existing methods (RNNs and optimization) in a novel framework.
The paper tackles human full-body movement prediction by decoupling short-term dynamics using a recurrent neural network and long-term environmental constraints via gradient-based trajectory optimization, demonstrating improved prediction over state-of-the-art methods on real motion data and showing applicability to robot trajectory planning.
Human movement prediction is difficult as humans naturally exhibit complex behaviors that can change drastically from one environment to the next. In order to alleviate this issue, we propose a prediction framework that decouples short-term prediction, linked to internal body dynamics, and long-term prediction, linked to the environment and task constraints. In this work we investigate encoding short-term dynamics in a recurrent neural network, while we account for environmental constraints, such as obstacle avoidance, using gradient-based trajectory optimization. Experiments on real motion data demonstrate that our framework improves the prediction with respect to state-of-the-art motion prediction methods, as it accounts to beforehand unseen environmental structures. Moreover we demonstrate on an example, how this framework can be used to plan robot trajectories that are optimized to coordinate with a human partner.