Bridging Predictive Uncertainty and Safe Action: Sample-Conditioned Differentiable Planning for Autonomous Driving
About
Complex, dynamic, and interactive driving environments pose significant challenges for autonomous driving, primarily due to the pervasive uncertainty of surrounding traffic. A fundamental bottleneck in current systems is the disconnect between highly expressive uncertainty modeling and interpretable, safe motion planning. In this paper, we propose a novel sample-conditioned differentiable planning framework that bridges this gap by explicitly incorporating diffusion-generated future trajectories into the optimization process. Rather than compressing predictions into a single deterministic future or relying on black-box end-to-end architectures, our approach leverages a conditional diffusion model to generate a diverse set of plausible future scenarios. Crucially, these samples are directly fed into a differentiable planner, which explicitly mitigates predictive uncertainty via an empirical Conditional Value-at-Risk (CVaR) tail-risk constraint. This allows the planner to optimize a physically interpretable trajectory that is robust to rare yet safety-critical interactions. Furthermore, we introduce a directed graph representation for scene context that yields substantial improvements in both predictive effectiveness and computational efficiency. Validated through extensive open-loop and closed-loop evaluations on the Waymo Open Motion and Argoverse 2 datasets, our framework significantly outperforms state-of-the-art baselines in safety, efficiency, and ride comfort.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Closed-loop motion planning | WOMD closed-loop (test) | Acceleration Error (m/s^2)0.72 | 6 | |
| Motion forecasting | Argoverse Motion Forecasting 2 (test) | Acceleration (m/s^2)0.58 | 6 | |
| Motion forecasting | Argoverse 2 Motion Forecasting Dataset | Acceleration (m/s^2)1.43 | 6 | |
| Open-loop Motion Planning and Prediction | WOMD Scenario | Acceleration (m/s^2)0.52 | 6 |