Stochastic Occupancy Grid Map Prediction in Dynamic Scenes

TL;DR

This paper introduces a stochastic prediction algorithm using a variational autoencoder for mobile robots to forecast future dynamic scene states, leveraging robot and object motion, with demonstrated improvements in accuracy and robustness.

Contribution

The paper proposes a novel variational autoencoder-based stochastic prediction algorithm that incorporates robot and object motion for dynamic scene prediction.

Findings

Achieves more accurate predictions than existing algorithms.

Demonstrates robustness across simulated and real-world datasets.

Validates effectiveness in navigation tasks with a predictive planner.

Abstract

This paper presents two variations of a novel stochastic prediction algorithm that enables mobile robots to accurately and robustly predict the future state of complex dynamic scenes. The proposed algorithm uses a variational autoencoder to predict a range of possible future states of the environment. The algorithm takes full advantage of the motion of the robot itself, the motion of dynamic objects, and the geometry of static objects in the scene to improve prediction accuracy. Three simulated and real-world datasets collected by different robot models are used to demonstrate that the proposed algorithm is able to achieve more accurate and robust prediction performance than other prediction algorithms. Furthermore, a predictive uncertainty-aware planner is proposed to demonstrate the effectiveness of the proposed predictor in simulation and real-world navigation experiments. Implementations are open source at https://github.com/TempleRAIL/SOGMP.