Skip to content
AI News HubLIVE
Original source2 min read

Old-School Planners Drive (Sometimes) Better Than Learned Ones

Summary

An arXiv study implements sixteen textbook driving planners and benchmarks them on nuScenes, nuPlan, and HUGSIM. On HUGSIM, nine of the sixteen outperform the learned planner of the end-to-end model UniAD using the same frozen perception; the best combination raises HD-Score from 32.0 to 41.8. In 31 of the 182 runs where UniAD's planner crashes into a car, the best textbook planner completes the route on identical perception, attributing those failures to planning rather than perception.

SourcearXiv RoboticsAuthor: Andreas Look
Old-School Planners Drive (Sometimes) Better Than Learned Ones
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 18 Nov 2026]

Title:Old-School Planners Drive (Sometimes) Better Than Learned Ones

View a PDF of the paper titled Old-School Planners Drive (Sometimes) Better Than Learned Ones, by Andreas Look

View PDF HTML (experimental)

Abstract:End-to-end driving models learn to plan from data, and hand-written planners are widely treated as a thing of the past. We test whether this is justified: we implement sixteen textbook planners, each combining a path source (reference line, A*, hybrid A*, RRT*) with a trajectory method (Frenet lattice, nonlinear optimization, $s$--$t$ search, dynamic window), and evaluate them on three benchmarks: open loop on nuScenes, closed loop on nuPlan with ground-truth perception, and photorealistic closed loop on HUGSIM. On HUGSIM, they replace only the planner of the end-to-end model UniAD and read its frozen perception, without an HD map or other privileged information. On nuScenes and nuPlan, the best textbook planners are competitive (L2 error of 0.735\,m against 0.947\,m for UniAD's planner; a nuPlan score of 79.3 against 76.1 for the rule-based PDM-Closed on Test14-hard with reactive agents). On HUGSIM, nine of the sixteen score above UniAD's learned planner on the same perception,. The best, a hybrid A* path followed by nonlinear trajectory optimization, raises HUGSIM's driving score (HD-Score) from 32.0 to 41.8. The gain is largest with standing and oncoming cars; against cars that steer at the ego, there is none. In 31 of the 182 runs in which UniAD's planner hits a car, the best textbook planner completes the route on the same perception: these crashes are due to the planner, not the perception.

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2611.25138 [cs.RO]

(or arXiv:2611.25138v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.25138

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Andreas Look [view email] [v1] Wed, 18 Nov 2026 20:18:35 UTC (1,554 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Old-School Planners Drive (Sometimes) Better Than Learned Ones, by Andreas Look

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Sixteen textbook planners combining path sources (reference line, A*, hybrid A*, RRT*) with trajectory methods (Frenet lattice, nonlinear optimization, s-t search, dynamic window) were evaluated on three benchmarks.
  • On nuScenes, the best textbook planner achieves 0.735 m L2 error versus 0.947 m for UniAD's planner; on nuPlan Test14-hard it scores 79.3 versus 76.1 for rule-based PDM-Closed.
  • On HUGSIM, nine of sixteen planners beat UniAD's learned planner on the same perception; the best, hybrid A* plus nonlinear trajectory optimization, lifts HD-Score from 32.0 to 41.8.
  • In 31 of 182 UniAD planner crash runs, the best textbook planner completes the route on the same perception, showing those crashes stem from the planner, not perception.

Highlights and analysis are generated automatically and may contain errors. Check the original source.