When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hagedorn, Steffen, Donkov, Luka, Distelzweig, Aron, Condurache, Alexandru P.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917019438284800
author Hagedorn, Steffen
Donkov, Luka
Distelzweig, Aron
Condurache, Alexandru P.
author_facet Hagedorn, Steffen
Donkov, Luka
Distelzweig, Aron
Condurache, Alexandru P.
contents Planner evaluation in closed-loop simulation often uses rule-based traffic agents, whose simplistic and passive behavior can hide planner deficiencies and bias rankings. Widely used IDM agents simply follow a lead vehicle and cannot react to vehicles in adjacent lanes, hindering tests of complex interaction capabilities. We address this issue by integrating the state-of-the-art learned traffic agent model SMART into nuPlan. Thus, we are the first to evaluate planners under more realistic conditions and quantify how conclusions shift when narrowing the sim-to-real gap. Our analysis covers 14 recent planners and established baselines and shows that IDM-based simulation overestimates planning performance: nearly all scores deteriorate. In contrast, many planners interact better than previously assumed and even improve in multi-lane, interaction-heavy scenarios like lane changes or turns. Methods trained in closed-loop demonstrate the best and most stable driving performance. However, when reaching their limits in augmented edge-case scenarios, all learned planners degrade abruptly, whereas rule-based planners maintain reasonable basic behavior. Based on our results, we suggest SMART-reactive simulation as a new standard closed-loop benchmark in nuPlan and release the SMART agents as a drop-in alternative to IDM at https://github.com/shgd95/InteractiveClosedLoop.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14677
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks
Hagedorn, Steffen
Donkov, Luka
Distelzweig, Aron
Condurache, Alexandru P.
Robotics
Artificial Intelligence
Machine Learning
Multiagent Systems
Planner evaluation in closed-loop simulation often uses rule-based traffic agents, whose simplistic and passive behavior can hide planner deficiencies and bias rankings. Widely used IDM agents simply follow a lead vehicle and cannot react to vehicles in adjacent lanes, hindering tests of complex interaction capabilities. We address this issue by integrating the state-of-the-art learned traffic agent model SMART into nuPlan. Thus, we are the first to evaluate planners under more realistic conditions and quantify how conclusions shift when narrowing the sim-to-real gap. Our analysis covers 14 recent planners and established baselines and shows that IDM-based simulation overestimates planning performance: nearly all scores deteriorate. In contrast, many planners interact better than previously assumed and even improve in multi-lane, interaction-heavy scenarios like lane changes or turns. Methods trained in closed-loop demonstrate the best and most stable driving performance. However, when reaching their limits in augmented edge-case scenarios, all learned planners degrade abruptly, whereas rule-based planners maintain reasonable basic behavior. Based on our results, we suggest SMART-reactive simulation as a new standard closed-loop benchmark in nuPlan and release the SMART agents as a drop-in alternative to IDM at https://github.com/shgd95/InteractiveClosedLoop.
title When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks
topic Robotics
Artificial Intelligence
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2510.14677