Technical Report for Real-Time Certified Probabilistic Pedestrian Forecasting

TL;DR

This paper introduces a real-time probabilistic pedestrian forecasting method using learned differential equations, significantly improving prediction accuracy over existing approaches for autonomous navigation.

Contribution

It presents a novel differential equation-based approach for probabilistic forecasting that is computationally efficient and suitable for real-time autonomous systems.

Findings

Achieves higher prediction accuracy than state-of-the-art methods.

Operates at real-time speeds with a naive Python implementation.

Validated on diverse scenarios with improved long-term forecasts.

Abstract

The success of autonomous systems will depend upon their ability to safely navigate human-centric environments. This motivates the need for a real-time, probabilistic forecasting algorithm for pedestrians, cyclists, and other agents since these predictions will form a necessary step in assessing the risk of any action. This paper presents a novel approach to probabilistic forecasting for pedestrians based on weighted sums of ordinary differential equations that are learned from historical trajectory information within a fixed scene. The resulting algorithm is embarrassingly parallel and is able to work at real-time speeds using a naive Python implementation. The quality of predicted locations of agents generated by the proposed algorithm is validated on a variety of examples and considerably higher than existing state of the art approaches over long time horizons.