Real Time Trajectory Prediction Using Deep Conditional Generative Models

TL;DR

This paper introduces a deep conditional generative model for real-time trajectory prediction in robotics, enabling fast, accurate long-term forecasts with quantified uncertainty, suitable for time-critical tasks.

Contribution

The paper presents a novel deep generative model that improves long-term trajectory prediction accuracy and latency over existing methods for robotic applications.

Findings

More accurate long-term predictions than RNNs and physical models

Lower latency inference suitable for real-time robotics

Effective in a robot table tennis scenario

Abstract

Data driven methods for time series forecasting that quantify uncertainty open new important possibilities for robot tasks with hard real time constraints, allowing the robot system to make decisions that trade off between reaction time and accuracy in the predictions. Despite the recent advances in deep learning, it is still challenging to make long term accurate predictions with the low latency required by real time robotic systems. In this paper, we propose a deep conditional generative model for trajectory prediction that is learned from a data set of collected trajectories. Our method uses encoder and decoder deep networks that maps complete or partial trajectories to a Gaussian distributed latent space and back, allowing for fast inference of the future values of a trajectory given previous observations. The encoder and decoder networks are trained using stochastic gradient variational Bayes. In the experiments, we show that our model provides more accurate long term predictions with a lower latency that popular models for trajectory forecasting like recurrent neural networks or physical models based on differential equations. Finally, we test our proposed approach in a robot table tennis scenario to evaluate the performance of the proposed method in a robotic task with hard real time constraints.