From Learned-Mode AV-Traffic Pairing to Planner Decisions: A Marginal-Preserving Study on Argoverse 2

arXiv:2609.14997v1 Announce Type: new Abstract: Joint motion forecasts pair each autonomous-vehicle (AV) future with surrounding traffic, but actor-level metrics do not show whether that structure matters to a planner. We study this question with a marginal-preserving product control that removes AV-traffic pairing among the learned modes while retaining the fixed constant-velocity pair and holding trajectories, actor-level marginals before planner conditioning, candidates, the cost terms and weights, and fallback fixed. The intervention also changes candidate-conditioned concentration. Across twelve runs on 1,400 held-out Argoverse 2 scenarios, the intervention changes 3.0% of route-level offline selections at $\tau=4$ m. Control-minus-joint recorded-trajectory regret is $-0.026$ and $-0.118$ at the two training sizes; crossed and seed-$t$ intervals span zero. At $\tau=1$ m, relative costs change in 87.9% of route evaluations and route-level offline selections in 8.1%. Before concentration matching, descriptive outcome estimates favor the control. Most of this gap disappears along an approximate concentration-matching path; the remaining contrasts are $+0.112$ and $-0.047$, and both crossed intervals span zero. Actor-level forecast metrics remain identical. Pairing-strength and temperature sweeps show that the decision contrast grows with pairing removal and sharper conditioning. The intervention changes planner decisions even though actor-level metrics remain unchanged. The matching analysis, however, cannot separate any recorded-outcome effect of learned-mode AV-traffic pairing from the accompanying change in conditioned concentration.

Abstract:Joint motion forecasts pair each autonomous-vehicle (AV) future with surrounding traffic, but actor-level metrics do not show whether that structure matters to a planner. We study this question with a marginal-preserving product control that removes AV-traffic pairing among the learned modes while retaining the fixed constant-velocity pair and holding trajectories, actor-level marginals before planner conditioning, candidates, the cost terms and weights, and fallback fixed. The intervention also changes candidate-conditioned concentration. Across twelve runs on 1,400 held-out Argoverse 2 scenarios, the intervention changes 3.0% of route-level offline selections at $\tau=4$ m. Control-minus-joint recorded-trajectory regret is $-0.026$ and $-0.118$ at the two training sizes; crossed and seed-$t$ intervals span zero. At $\tau=1$ m, relative costs change in 87.9% of route evaluations and route-level offline selections in 8.1%. Before concentration matching, descriptive outcome estimates favor the control. Most of this gap disappears along an approximate concentration-matching path; the remaining contrasts are $+0.112$ and $-0.047$, and both crossed intervals span zero. Actor-level forecast metrics remain identical. Pairing-strength and temperature sweeps show that the decision contrast grows with pairing removal and sharper conditioning. The intervention changes planner decisions even though actor-level metrics remain unchanged. The matching analysis, however, cannot separate any recorded-outcome effect of learned-mode AV-traffic pairing from the accompanying change in conditioned concentration.

8 pages, 4 figures. Accepted to the 16th Workshop on Planning, Perception and Navigation for Intelligent Vehicles (PPNIV), held in conjunction with IEEE/RSJ IROS 2026

Robotics (cs.RO)

arXiv:2609.14997 [cs.RO]

(or arXiv:2609.14997v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.14997 arXiv-issued DOI via DataCite (pending registration)

aiqbench analysis

From Learned-Mode AV-Traffic Pairing to Planner Decisions: A Marginal-Preserving Study on Argoverse 2

Related coverage