SCOPE: Stochastic Cartographic Occupancy Prediction Engine for Uncertainty-Aware Dynamic Navigation

TL;DR

SCOPE introduces real-time stochastic prediction engines that enhance dynamic environment modeling for mobile robot navigation, significantly improving safety and efficiency in crowded scenes.

Contribution

The paper presents a novel family of stochastic prediction engines optimized for real-time performance, enabling more accurate and robust environment predictions for robot navigation.

Findings

Achieves up to 89x faster inference speed

Uses 8x less memory than existing methods

Improves navigation safety and robustness in experiments

Abstract

This article presents a family of Stochastic Cartographic Occupancy Prediction Engines (SCOPEs) that enable mobile robots to predict the future states of complex dynamic environments. They do this by accounting for the motion of the robot itself, the motion of dynamic objects, and the geometry of static objects in the scene, and they generate a range of possible future states of the environment. These prediction engines are software-optimized for real-time performance for navigation in crowded dynamic scenes, achieving up to 89 times faster inference speed and 8 times less memory usage than other state-of-the-art engines. Three simulated and real-world datasets collected by different robot models are used to demonstrate that these proposed prediction algorithms are able to achieve more accurate and robust stochastic prediction performance than other algorithms. Furthermore, a series of simulation and hardware navigation experiments demonstrate that the proposed predictive uncertainty-aware navigation framework with these stochastic prediction engines is able to improve the safe navigation performance of current state-of-the-art model- and learning-based control policies.