A conditional diffusion model produces diverse future trajectories that are passed directly into a differentiable planner equipped with an empirical CVaR tail-risk constraint and a directed-graph scene representation, evaluated on Waymo and Argoverse 2.
Integrating decision-making into differentiable optimization guided learning for end-to-end planning of autonomous vehicles,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bridging Predictive Uncertainty and Safe Action: Sample-Conditioned Differentiable Planning for Autonomous Driving
A conditional diffusion model produces diverse future trajectories that are passed directly into a differentiable planner equipped with an empirical CVaR tail-risk constraint and a directed-graph scene representation, evaluated on Waymo and Argoverse 2.