RECTOR: Priority-Aware Rule-Based Reranking for Compliance-Aware Autonomous Driving Trajectory Selection
Not on the map. Why?
Abstract (arXiv)
Autonomous driving stacks must pick one trajectory from a multi-modal candidate set; choosing by model confidence ignores safety, traffic-law, and comfort constraints. We present textscRECTOR (Rule-Enforced Constrained Trajectory Orchestrator), a post-generation reranking layer that scores candidates against a tiered rulebook (Safety~succ~Legal~succ~Road~succ~Comfort) via differentiable proxies and a scene-conditioned applicability mechanism, then selects with a deterministic varepsilon-lexicographic rule that preserves cross-tier priority by construction -- without retraining the predictor. On the Waymo Open Motion Dataset textttvalidationinteractive split (43,219 augmented instances, K=6), under Protocol~B (28-rule proxy catalog, oracle applicability) rule-aware selection cuts Safety+Legal violations from 28.58% to 20.42% and Total from 40.32% to 32.41% versus confidence-only on the same candidates. A uniform-weight weighted-sum baseline matches binary compliance on this benchmark -- the empirical lift comes from rule-aware ranking, while the lexicographic guarantee is the structural differentiator no weight calibration can replicate. Under adversarial confidence corruption, confidence-only selection fails in 100% of scenarios while both rule-aware selectors reject the injected mode in ~96%. All figures are proxy-evaluator results (not a safety certificate), open-loop, 5,s horizon, U.S. rules, validation split.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 24 May 2026.
Builds on
20 of 27 references.
References · 20
- 2017Constrained Policy Optimizationcited by 983
- 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 599
- 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 537
- 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
- 2020TNT: Target-driveN Trajectory Predictioncited by 347
- 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 295
- 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
- 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 280
- 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 270
- 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
- 2022Guided Conditional Diffusion for Controllable Traffic Simulationcited by 190
- 2018Differentiable MPC for End-to-end Planning and Controlcited by 189
8 more
- 2023Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Researchcited by 160
- 2023MotionLM: Multi-Agent Motion Forecasting as Language Modelingcited by 156
- 2023GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Drivingcited by 141
- 2017On a Formal Model of Safe and Scalable Self-driving Carscited by 131
- 2023Language-Guided Traffic Simulation via Scene-Level Diffusioncited by 111
- 2022M2I: From Factored Marginal Trajectory Prediction to Interactive Predictioncited by 81
- 2021SafetyNet: Safe planning for real-world self-driving vehicles using machine-learned policiescited by 69
- 2019Liability, Ethics, and Culture-Aware Behavior Specification using Rulebookscited by 43
Built on by
Citing papers per year: 2026: 1.
1 paper.