Autonomous Vehicle Path Planning by Searching With Differentiable Simulation Article Swipe

PDF

Asen Nachkov , Jan-Nico Zaech , Danda Pani Paudel , Xi Wang ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2511.11043

Planning allows an agent to safely refine its actions before executing them in the real world. In autonomous driving, this is crucial to avoid collisions and navigate in complex, dense traffic scenarios. One way to plan is to search for the best action sequence. However, this is challenging when all necessary components - policy, next-state predictor, and critic - have to be learned. Here we propose Differentiable Simulation for Search (DSS), a framework that leverages the differentiable simulator Waymax as both a next state predictor and a critic. It relies on the simulator's hardcoded dynamics, making state predictions highly accurate, while utilizing the simulator's differentiability to effectively search across action sequences. Our DSS agent optimizes its actions using gradient descent over imagined future trajectories. We show experimentally that DSS - the combination of planning gradients and stochastic search - significantly improves tracking and path planning accuracy compared to sequence prediction, imitation learning, model-free RL, and other planning methods.

Related Topics

Vehicle Audio

Automated Guided Vehicle

Jewish Autonomous Oblast

Bradley Fighting Vehicle

Noble Eightfold Path

International Vehicle Registration Code

Multiple Independently Targetable Reentry Vehicle

Shining Path

Electric Vehicle

Autonomous Region Of Bougainville

Left-Hand Path And Right-Hand Path

Assault Amphibious Vehicle

Concepts

No concepts available.

Metadata

Type: preprint
Landing Page: http://arxiv.org/abs/2511.11043
PDF: https://arxiv.org/pdf/2511.11043
OA Status: green
OpenAlex ID: https://openalex.org/W4416714881

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416714881

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2511.11043

Digital Object Identifier
Title: Autonomous Vehicle Path Planning by Searching With Differentiable Simulation

Work title
Type: preprint

OpenAlex work type
Publication year: 2025

Year of publication
Publication date: 2025-11-14

Full publication date if available
Authors: Asen Nachkov, Jan-Nico Zaech, Danda Pani Paudel, Xi Wang

List of authors in order
Landing page: https://arxiv.org/abs/2511.11043

Publisher landing page
PDF URL: https://arxiv.org/pdf/2511.11043

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2511.11043

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416714881
doi	https://doi.org/10.48550/arxiv.2511.11043
ids.doi	https://doi.org/10.48550/arxiv.2511.11043
ids.openalex	https://openalex.org/W4416714881
fwci
type	preprint
title	Autonomous Vehicle Path Planning by Searching With Differentiable Simulation
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language
locations[0].id	pmh:oai:arXiv.org:2511.11043
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2511.11043
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2511.11043
locations[1].id	doi:10.48550/arxiv.2511.11043
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2511.11043
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5092803228
authorships[0].author.orcid
authorships[0].author.display_name	Asen Nachkov
authorships[0].author_position	first
authorships[0].raw_author_name	Nachkov, Asen
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5031102089
authorships[1].author.orcid	https://orcid.org/0000-0003-2566-0841
authorships[1].author.display_name	Jan-Nico Zaech
authorships[1].author_position	middle
authorships[1].raw_author_name	Zaech, Jan-Nico
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5050696776
authorships[2].author.orcid	https://orcid.org/0000-0002-1739-1867
authorships[2].author.display_name	Danda Pani Paudel
authorships[2].author_position	middle
authorships[2].raw_author_name	Paudel, Danda Pani
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5101507173
authorships[3].author.orcid	https://orcid.org/0000-0002-4186-4935
authorships[3].author.display_name	Xi Wang
authorships[3].author_position	last
authorships[3].raw_author_name	Wang, Xi
authorships[3].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2511.11043
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-11-18T00:00:00
display_name	Autonomous Vehicle Path Planning by Searching With Differentiable Simulation
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T21:19:24.975087
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2511.11043
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2511.11043
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2511.11043
primary_location.id	pmh:oai:arXiv.org:2511.11043
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2511.11043
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2511.11043
publication_date	2025-11-14
publication_year	2025
referenced_works_count	0
abstract_inverted_index.-	52, 58, 129, 138
abstract_inverted_index.a	71, 81, 86
abstract_inverted_index.In	16
abstract_inverted_index.It	88
abstract_inverted_index.We	124
abstract_inverted_index.an	2
abstract_inverted_index.as	79
abstract_inverted_index.be	61
abstract_inverted_index.in	12, 27
abstract_inverted_index.is	20, 36, 46
abstract_inverted_index.of	132
abstract_inverted_index.on	90
abstract_inverted_index.to	4, 22, 34, 37, 60, 105, 147
abstract_inverted_index.we	64
abstract_inverted_index.DSS	112, 128
abstract_inverted_index.One	32
abstract_inverted_index.Our	111
abstract_inverted_index.RL,	153
abstract_inverted_index.all	49
abstract_inverted_index.and	25, 56, 85, 135, 142, 154
abstract_inverted_index.for	39, 68
abstract_inverted_index.its	7, 115
abstract_inverted_index.the	13, 40, 75, 91, 102, 130
abstract_inverted_index.way	33
abstract_inverted_index.Here	63
abstract_inverted_index.best	41
abstract_inverted_index.both	80
abstract_inverted_index.have	59
abstract_inverted_index.next	82
abstract_inverted_index.over	120
abstract_inverted_index.path	143
abstract_inverted_index.plan	35
abstract_inverted_index.real	14
abstract_inverted_index.show	125
abstract_inverted_index.that	73, 127
abstract_inverted_index.them	11
abstract_inverted_index.this	19, 45
abstract_inverted_index.when	48
abstract_inverted_index.agent	3, 113
abstract_inverted_index.avoid	23
abstract_inverted_index.dense	29
abstract_inverted_index.other	155
abstract_inverted_index.state	83, 96
abstract_inverted_index.using	117
abstract_inverted_index.while	100
abstract_inverted_index.(DSS),	70
abstract_inverted_index.Search	69
abstract_inverted_index.Waymax	78
abstract_inverted_index.across	108
abstract_inverted_index.action	42, 109
abstract_inverted_index.allows	1
abstract_inverted_index.before	9
abstract_inverted_index.critic	57
abstract_inverted_index.future	122
abstract_inverted_index.highly	98
abstract_inverted_index.making	95
abstract_inverted_index.refine	6
abstract_inverted_index.relies	89
abstract_inverted_index.safely	5
abstract_inverted_index.search	38, 107, 137
abstract_inverted_index.world.	15
abstract_inverted_index.actions	8, 116
abstract_inverted_index.critic.	87
abstract_inverted_index.crucial	21
abstract_inverted_index.descent	119
abstract_inverted_index.policy,	53
abstract_inverted_index.propose	65
abstract_inverted_index.traffic	30
abstract_inverted_index.However,	44
abstract_inverted_index.Planning	0
abstract_inverted_index.accuracy	145
abstract_inverted_index.compared	146
abstract_inverted_index.complex,	28
abstract_inverted_index.driving,	18
abstract_inverted_index.gradient	118
abstract_inverted_index.imagined	121
abstract_inverted_index.improves	140
abstract_inverted_index.learned.	62
abstract_inverted_index.methods.	157
abstract_inverted_index.navigate	26
abstract_inverted_index.planning	133, 144, 156
abstract_inverted_index.sequence	148
abstract_inverted_index.tracking	141
abstract_inverted_index.accurate,	99
abstract_inverted_index.dynamics,	94
abstract_inverted_index.executing	10
abstract_inverted_index.framework	72
abstract_inverted_index.gradients	134
abstract_inverted_index.hardcoded	93
abstract_inverted_index.imitation	150
abstract_inverted_index.learning,	151
abstract_inverted_index.leverages	74
abstract_inverted_index.necessary	50
abstract_inverted_index.optimizes	114
abstract_inverted_index.predictor	84
abstract_inverted_index.sequence.	43
abstract_inverted_index.simulator	77
abstract_inverted_index.utilizing	101
abstract_inverted_index.Simulation	67
abstract_inverted_index.autonomous	17
abstract_inverted_index.collisions	24
abstract_inverted_index.components	51
abstract_inverted_index.model-free	152
abstract_inverted_index.next-state	54
abstract_inverted_index.predictor,	55
abstract_inverted_index.scenarios.	31
abstract_inverted_index.sequences.	110
abstract_inverted_index.stochastic	136
abstract_inverted_index.challenging	47
abstract_inverted_index.combination	131
abstract_inverted_index.effectively	106
abstract_inverted_index.prediction,	149
abstract_inverted_index.predictions	97
abstract_inverted_index.simulator's	92, 103
abstract_inverted_index.significantly	139
abstract_inverted_index.trajectories.	123
abstract_inverted_index.Differentiable	66
abstract_inverted_index.differentiable	76
abstract_inverted_index.experimentally	126
abstract_inverted_index.differentiability	104
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile