Context-free Self-Conditioned GAN for Trajectory Forecasting
2026-03-09 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new method using a type of artificial intelligence called a self-conditioned GAN to understand different ways things move based on 2D paths, without needing extra context or labels. They tested their method for predicting future movements of humans and vehicles on roads. Their approach did better than other similar methods, especially when labeled data was scarce. Overall, the method worked best for human motion and showed good results for road agents as well.
self-conditioned GANtrajectory forecasting2D trajectoriesdiscriminator feature spaceunsupervised learninghuman motionroad agentsmode learningcontext-free methodsbehavioral patterns
Authors
Tiago Rodrigues de Almeida, Eduardo Gutierrez Maestro, Oscar Martinez Mozos
Abstract
In this paper, we present a context-free unsupervised approach based on a self-conditioned GAN to learn different modes from 2D trajectories. Our intuition is that each mode indicates a different behavioral moving pattern in the discriminator's feature space. We apply this approach to the problem of trajectory forecasting. We present three different training settings based on self-conditioned GAN, which produce better forecasters. We test our method in two data sets: human motion and road agents. Experimental results show that our approach outperforms previous context-free methods in the least representative supervised labels while performing well in the remaining labels. In addition, our approach outperforms globally in human motion, while performing well in road agents.