J. Zöllner

Bidirectional future graphs allow later evidence to retroactively correct earlier motion prediction segments, achieving state-of-the-art forecasting accuracy without LiDAR or ensembling.

End-to-end driving models can learn interpretable safety costs over reachable futures, drastically reducing collisions without fine-tuning.

AdvScene, a conditional latent diffusion model that is trained in two stages that Conditioning on ego driving displacement prevents the ego from remaining static, and RL finetuning induces criticality directly with non-differentiable safety-critical metrics is proposed.