DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents

TL;DR

DESIRE is a neural network framework that predicts multiple plausible futures of agents in dynamic scenes by considering interactions, scene context, and strategic planning, achieving high accuracy on benchmark datasets.

Contribution

It introduces a novel end-to-end deep stochastic model that captures multi-modal future outcomes and agent interactions for improved future scene prediction.

Findings

Significantly outperforms baseline methods on KITTI and Stanford Drone datasets.

Effectively models multi-modal future predictions with a stochastic variational autoencoder.

Enhances long-term prediction accuracy through a ranking and refinement mechanism.

Abstract

We introduce a Deep Stochastic IOC RNN Encoderdecoder framework, DESIRE, for the task of future predictions of multiple interacting agents in dynamic scenes. DESIRE effectively predicts future locations of objects in multiple scenes by 1) accounting for the multi-modal nature of the future prediction (i.e., given the same context, future may vary), 2) foreseeing the potential future outcomes and make a strategic prediction based on that, and 3) reasoning not only from the past motion history, but also from the scene context as well as the interactions among the agents. DESIRE achieves these in a single end-to-end trainable neural network model, while being computationally efficient. The model first obtains a diverse set of hypothetical future prediction samples employing a conditional variational autoencoder, which are ranked and refined by the following RNN scoring-regression module. Samples are scored by accounting for accumulated future rewards, which enables better long-term strategic decisions similar to IOC frameworks. An RNN scene context fusion module jointly captures past motion histories, the semantic scene context and interactions among multiple agents. A feedback mechanism iterates over the ranking and refinement to further boost the prediction accuracy. We evaluate our model on two publicly available datasets: KITTI and Stanford Drone Dataset. Our experiments show that the proposed model significantly improves the prediction accuracy compared to other baseline methods.