Pedestrian Intention Prediction: A Multi-task Perspective

TL;DR

This paper introduces a multi-task recurrent neural network for predicting pedestrian intentions and visual states, including bounding boxes, to enhance autonomous vehicle safety with improved speed and comparable accuracy.

Contribution

It presents a novel multi-task learning approach that jointly predicts pedestrian intentions and visual states, including bounding boxes, with a simpler and faster architecture.

Findings

Outperforms previous intention prediction methods on JAAD dataset

Achieves comparable bounding box prediction accuracy with a simpler, faster model

Model is more than twice as fast as previous complex architectures

Abstract

In order to be globally deployed, autonomous cars must guarantee the safety of pedestrians. This is the reason why forecasting pedestrians' intentions sufficiently in advance is one of the most critical and challenging tasks for autonomous vehicles. This work tries to solve this problem by jointly predicting the intention and visual states of pedestrians. In terms of visual states, whereas previous work focused on x-y coordinates, we will also predict the size and indeed the whole bounding box of the pedestrian. The method is a recurrent neural network in a multi-task learning approach. It has one head that predicts the intention of the pedestrian for each one of its future position and another one predicting the visual states of the pedestrian. Experiments on the JAAD dataset show the superiority of the performance of our method compared to previous works for intention prediction. Also, although its simple architecture (more than 2 times faster), the performance of the bounding box prediction is comparable to the ones yielded by much more complex architectures. Our code is available online.