Under the Hood of Transformer Networks for Trajectory Forecasting

by   Luca Franco, et al.

Transformer Networks have established themselves as the de-facto state-of-the-art for trajectory forecasting but there is currently no systematic study on their capability to model the motion patterns of people, without interactions with other individuals nor the social context. This paper proposes the first in-depth study of Transformer Networks (TF) and Bidirectional Transformers (BERT) for the forecasting of the individual motion of people, without bells and whistles. We conduct an exhaustive evaluation of input/output representations, problem formulations and sequence modeling, including a novel analysis of their capability to predict multi-modal futures. Out of comparative evaluation on the ETH+UCY benchmark, both TF and BERT are top performers in predicting individual motions, definitely overcoming RNNs and LSTMs. Furthermore, they remain within a narrow margin wrt more complex techniques, which include both social interactions and scene contexts. Source code will be released for all conducted experiments.


Transformer Networks for Trajectory Forecasting

Most recent successes on forecasting the people motion are based on LSTM...

Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion

In this paper, we address the problem of forecasting the trajectory of a...

Forecasting of depth and ego-motion with transformers and self-supervision

This paper addresses the problem of end-to-end self-supervised forecasti...

Hierarchical Motion Encoder-Decoder Network for Trajectory Forecasting

Trajectory forecasting plays a pivotal role in the field of intelligent ...

SMEMO: Social Memory for Trajectory Forecasting

Effective modeling of human interactions is of utmost importance when fo...

Please sign up or login with your details

Forgot password? Click here to reset