SafeCritic: Collision-Aware Trajectory Prediction

TL;DR

SafeCritic is a novel trajectory prediction model that combines generative adversarial networks and reinforcement learning to generate and evaluate safe, collision-free paths for vulnerable road users in urban environments.

Contribution

It introduces a hybrid model that integrates GANs and reinforcement learning with environment-aware Critic for safe trajectory prediction, addressing a key gap in existing methods.

Findings

Significant improvement over state-of-the-art on large-scale datasets

Critic effectively classifies trajectory safety

Model generates multiple realistic and safe trajectories

Abstract

Navigating complex urban environments safely is a key to realize fully autonomous systems. Predicting future locations of vulnerable road users, such as pedestrians and cyclists, thus, has received a lot of attention in the recent years. While previous works have addressed modeling interactions with the static (obstacles) and dynamic (humans) environment agents, we address an important gap in trajectory prediction. We propose SafeCritic, a model that synergizes generative adversarial networks for generating multiple "real" trajectories with reinforcement learning to generate "safe" trajectories. The Discriminator evaluates the generated candidates on whether they are consistent with the observed inputs. The Critic network is environmentally aware to prune trajectories that are in collision or are in violation with the environment. The auto-encoding loss stabilizes training and prevents mode-collapse. We demonstrate results on two large scale data sets with a considerable improvement over state-of-the-art. We also show that the Critic is able to classify the safety of trajectories.