MomADv2: Reliable Temporal Memory for End-to-End Autonomous Driving

Ziying Song; Shengkai Zhang; Lin Liu; Peiliang Wu; Lei Yang; Dongyang Xu; Bin Sun; Li Wang

cs.CVAug 24, 2026

MomADv2: Reliable Temporal Memory for End-to-End Autonomous Driving

Authors: Ziying Song, Shengkai Zhang, Lin Liu, Peiliang Wu, Lei Yang, Dongyang Xu, Bin Sun, Li Wang, +3 more

Organizations: School of Artificial Intelligence (School of Software), Yanshan University · Beijing Jiaotong University · Nanyang Technological University · Tsinghua University · China Automotive Technology and Research Center Co., Ltd. · School of Mechanical Engineering, Beijing Institute of Technology · University of Macau · The University of Queensland

Abstract

Long-horizon planning is critical for safe autonomous driving in complex scenarios. Existing methods improve planning continuity with temporal memory, but such memory may become invalid and mislead decisions when the driving command changes. Thus, selectively leveraging useful history while suppressing command-inconsistent memory remains a key challenge. To address this issue, we propose MomADv2, a reliable state-space memory framework for long-horizon end-to-end autonomous driving. At its core, MomADv2 introduces a Selective State-Space Planning Memory Query Module, which filters historical planning queries based on temporal continuity and command consistency, selects planning modes relevant to the current command, and models the evolution of planning intentions through a selective state-space mechanism. To further alleviate local trajectory deviations and error accumulation in long-horizon planning, we design a Flow-Matching Trajectory Residual Refiner. It learns a continuous residual correction field from the refined planning output to the expert trajectory, enabling fine-grained trajectory refinement while preserving the stability of anchor-based planning. Extensive experiments on closed-loop NAVSIM and Bench2Drive, as well as open-loop nuScenes, demonstrate that MomADv2 improves long-horizon planning consistency and reduces the average collision rate by 15.6% over MomAD under 6-second planning.

Figures & tables

Figure 1: Motivation of MomADv2. (a) Long-horizon planning requires consistent intentions across planning cycles. (b) Existing methods, represented by MomAD ( Song et al. 2025 ; Jia et al. 2025 ; Zhang et al. 2025a ) , indiscriminately reuse history, introducing new interference. (c) MomADv2 selectively preserves reliable states and refines local trajectory deviations via flow matching. (d) This reliable memory inheritance enables more accurate and safer long-horizon planning.

Figure 2: Overview of MomADv2 . Multi-view images are encoded into map and detection representations to generate initial ego planning queries. A Selective State-Space Planning Memory Query module retains valid historical queries based on scene, token, command, and buffer consistency. A Flow-Matching Trajectory Residual Refiner then predicts a conditional residual velocity field toward the expert trajectory, producing smooth, accurate, and temporally consistent long-horizon planning.

Figure 3: Flow Matching Supervision learns a query-conditioned residual velocity field that transforms the SSM-enhanced planner trajectory toward the expert trajectory. During inference, Gated Residual Refinement integrates this field with a few Euler steps and uses a bounded residual gate to improve trajectory accuracy while preserving anchor-based planning stability.

$\operatorname{Method}$	$\operatorname{Venue}$	$\operatorname{L2\ (m)}\downarrow$							$\operatorname{Col.\ Rate\ (\%)}\downarrow$
$\operatorname{Method}$	$\operatorname{Venue}$	1s	2s	3s	4s	5s	6s	$\operatorname{Avg.}$	1s	2s	3s	4s	5s	6s	$\operatorname{Avg.}$
$\operatorname{UniAD}$ ( Hu et al. 2023 )	CVPR’23	0.47	0.91	1.35	1.91	2.47	3.07	1.70	0.25	0.36	0.61	0.99	1.64	2.51	1.06
$\operatorname{SparseDrive}$ ( Sun et al. 2024 )	CVPR’23	0.43	0.87	1.23	1.75	2.32	2.95	1.59	0.19	0.31	0.56	0.87	1.54	2.33	0.97
$\operatorname{MomAD}$ ( Song et al. 2025 )	CVPR’25	0.41	0.85	1.13	1.67	1.98	2.45	1.42	0.17	0.30	0.54	0.83	1.43	2.13	0.90
$\operatorname{LAW}$ ( Li et al. 2025c )	ICLR’25	0.40	0.87	1.16	1.71	2.03	2.61	1.46	0.19	0.33	0.57	0.86	1.51	2.31	0.96
$\operatorname{Epona}$ ( Zhang et al. 2025b )	ICCV’25	0.39	0.91	1.17	1.73	2.02	2.75	1.50	0.14	0.18	0.45	0.74	1.48	2.23	0.87

Table 1: Planning results for 6-second long-horizon planning on the nuScenes validation set.

$\operatorname{Method}$	$\operatorname{Venue}$	$\operatorname{Open-loop}$	$\operatorname{Closed-loop}$
$\operatorname{Method}$	$\operatorname{Venue}$	$\operatorname{Avg.L2}\downarrow$	$\operatorname{DS}\uparrow$	$\operatorname{SR\ (\%)}\uparrow$	$\operatorname{Effi}\uparrow$	$\operatorname{Comf}\uparrow$
DriveAdapter* ( Jia et al. 2023 )	ICCV’23	1.01	64.22	33.08	70.22	16.01
DriveDPO ( Shang et al. 2025 )	NeurIPS’25	-	62.02	30.62	-	-
Raw2Drive ( Yang et al. 2025 )	NeurIPS’25	-	71.36	50.24	-	-
DriveTrans* ( Jia et al. 2025 )	ICLR’25	0.62	63.46	35.01	100.64	20.78
WoTE* ( Li et al. 2025e )	ICCV’25	-	61.71	31.36	-	-

Table 2:

\operatorname{\textbf{Open-Loop}}

and

\operatorname{\textbf{Closed-Loop}}

results on

\operatorname{\textbf{Bench2Drive}}

(V0.0.3) under base training set. * denotes expert feature distillation. ‘DS’ denotes Driving Score, ‘SR’ denotes Success Rate, ‘Effi’ denotes Efficiency, and ‘Comf’ denotes Comfortness.

Method	Venue	NC $\uparrow$	DAC $\uparrow$	TTC $\uparrow$	Comf. $\uparrow$	EP $\uparrow$	PDMS $\uparrow$
TransFuser ( Chitta et al. 2023 )	TPAMI’22	97.7	92.8	92.8	100	79.2	84.0
VADv2 ( Jiang et al. 2026 )	ICLR’26	97.2	89.1	91.6	100	76.0	80.9
GoalFlow ( Xing et al. 2025 )	CVPR’25	98.3	93.8	94.3	100	79.8	85.7
Hydra-MDP ( Li et al. 2024 )	Arxiv’24	98.3	96.0	94.6	100	78.7	86.5
FUMP ( Liu et al. 2025a )	Arxiv’25	98.1	96.2	94.2	100	82.0	87.8
DiffusionDrive ( Liao et al. 2025 )	CVPR’25	98.2	96.2	94.7	100	82.2	88.1

Table 3: Comparison on planning-oriented NAVSIMv1 navtest split with

\operatorname{\textbf{Closed-Loop}}

metrics.

Method	Stage	NC $\uparrow$	DAC $\uparrow$	DDC $\uparrow$	TL $\uparrow$	EP $\uparrow$	TTC $\uparrow$	LK $\uparrow$	HC $\uparrow$	EC $\uparrow$	EPDMS $\uparrow$
TransFuser	Stage1	96.2	79.5	99.1	99.5	84.1	95.1	94.2	97.5	79.1	23.1
TransFuser	Stage2	77.7	70.2	84.2	98.0	85.1	75.6	45.4	95.7	75.9	23.1
DiffusionDrive	Stage1	96.0	79.7	97.4	99.5	81.3	93.1	90.8	96.8	73.8	24.2
DiffusionDrive	Stage2	82.1	72.2	88.5	98.7	85.1	78.8	49.2	89.3	71.2	24.2
GuideFlow	Stage1	96.6	80.5	96.3	99.3	82.3	94.9	91.5	97.7	67.8	27.1
GuideFlow	Stage2	87.3	76.7	88.8	99.2	84.3	85.1	49.7	93.1	44.5	27.1

Table 4: Comparison with SOTA methods on the NAVSIMv2 navhard split ( Cao et al. 2025 ) .

Method	NC $\uparrow$	DAC $\uparrow$	DDC $\uparrow$	TL $\uparrow$	EP $\uparrow$	TTC $\uparrow$	LK $\uparrow$	HC $\uparrow$	EC $\uparrow$	EPDMS $\uparrow$
TransFuser ( Chitta et al. 2023 )	96.9	89.9	97.8	99.7	87.1	95.4	92.7	98.3	87.2	76.7
DiffusionDrive ( Liao et al. 2025 )	98.2	95.9	99.4	99.8	87.5	97.3	96.8	98.3	87.7	84.5
Hydra-MDP++ ( Li et al. 2025b )	97.2	97.5	99.4	99.6	83.1	96.5	94.4	98.2	70.9	81.4
DriveSuprim ( Yao et al. 2026 )	97.5	96.5	99.4	99.6	88.4	96.6	95.5	98.3	77.0	83.1
DiffusionDriveV2 ( Zou et al. 2025 )	97.7	96.6	99.2	99.8	88.9	97.2	96.0	97.8	91.0	87.5
DriveWorld-VLA ( Liu et al. 2026 )	98.6	99.1	99.6	99.8	87.4	97.9	97.0	97.8	78.6	86.8

Table 5: Comparison with SOTA methods on the NAVSIMv2 navtest split ( Cao et al. 2025 ) .

SSM-Q	FM-Ref	NC $\uparrow$	DAC $\uparrow$	TTC $\uparrow$	Comf. $\uparrow$	EP $\uparrow$	PDMS $\uparrow$
		97.7	92.8	92.8	100	79.2	84.0
✓		98.2	94.5	94.0	100	82.1	86.9
✓	✓	98.7	96.8	95.4	100	84.5	89.9

Table 6: Ablation study of the two core modules on the NAVSIMv1 navtest split. SSM-Q denotes the Selective State-Space Planning Memory Query Module, and FM-Ref denotes the Flow-Matching Trajectory Residual Refiner.

Method	Memory Strategy	Col. Rate (%) $\downarrow$
Method	Memory Strategy	1s	2s	3s	4s	5s	6s	Avg.
MomAD	Historical query reuse	0.17	0.30	0.54	0.83	1.43	2.13	0.90
MomADv2	No historical memory	0.16	0.29	0.52	0.86	1.48	2.18	0.92
MomADv2	Naive historical query fusion	0.18	0.34	0.60	0.94	1.62	2.35	1.01
MomADv2	Command-aware memory	0.12	0.25	0.47	0.82	1.46	2.19	0.89
MomADv2	+ Temporal-continuity filtering	0.08	0.21	0.41	0.78	1.39	2.12	0.83

Table 7: Ablation study of reliable temporal memory on the nuScenes validation set. All MomADv2 variants keep the FM-Ref and only differ in the historical memory strategy.

$K$	NC $\uparrow$	DAC $\uparrow$	TTC $\uparrow$	Comf. $\uparrow$	EP $\uparrow$	PDMS $\uparrow$
1	98.4	95.4	94.7	100	82.4	88.2
2	98.7	96.3	95.0	100	82.8	89.1
4	98.7	96.8	95.4	100	84.5	89.9
6	98.5	95.7	94.6	100	82.3	88.5
8	98.1	95.0	94.1	100	81.9	87.7

Table 8: Ablation study of historical memory length

K

on the NAVSIMv1 navtest split.

K

denotes the number of historical planning states used in the SSM-Q.

Figure 4: Visualization of MomADv2 on nuScenes dataset.

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

$\operatorname{Method}$	$\operatorname{Multi-Ability(\%)\uparrow}$
$\operatorname{Method}$	$\operatorname{Merging}\uparrow$	$\operatorname{Overtaking}\uparrow$	$\operatorname{EmergencyBrake}\uparrow$	$\operatorname{Give\>Way}\uparrow$	$\operatorname{Traffic\>Sign}\uparrow$	$\operatorname{Mean}\uparrow$
DriveAdapter* ( Jia et al. 2023 )	28.82	26.38	48.76	50.00	56.43	42.08
DriveDPO ( Shang et al. 2025 )	-	-	-	-	-	-
Raw2Drive ( Yang et al. 2025 )	43.35	51.11	60.00	50.00	62.26	53.34
DriveTrans* ( Jia et al. 2025 )	17.57	35.00	48.36	40.00	52.10	38.60
WoTE* ( Li et al. 2025e )	-	-	-	-	-	-

Appendix

Table 9:

\operatorname{Multi-Ability}

results on

\operatorname{\textbf{Bench2Drive}}

(V0.0.3) under base training set. ‘mmt’ refers multi-mode trajectory variant of

\operatorname{VAD}

and † denotes the re-implementation. * denotes expert feature distillation.

Method	Venue	TPC (m) $\downarrow$
		4s	5s	6s
UniAD ( Hu et al. 2023 )	CVPR’23	1.49	1.81	2.41
VAD ( Jiang et al. 2023 )	ICCV’23	1.55	1.73	2.17
SparseDrive ( Sun et al. 2024 )	ICRA’25	1.33	1.66	1.99
MomAD ( Song et al. 2025 )	CVPR’25	1.19	1.45	1.61
MomADv2 (Ours)	-	1.04	1.32	1.61

Appendix

Table 10: Comparison of trajectory prediction consistency on the nuScenes validation set. TPC denotes Trajectory Prediction Consistency, where lower values indicate better temporal stability.

$\operatorname{Method}$	$\operatorname{L2\ (m)}\downarrow$				$\operatorname{Col.\ Rate\ (\%)}\downarrow$
$\operatorname{Method}$	1s	2s	3s	$\operatorname{Avg.}$	1s	2s	3s	$\operatorname{Avg.}$
$\operatorname{UniAD}$ ( Hu et al. 2023 )	0.48	0.96	1.65	1.03	0.10	0.15	0.61	0.29
$\operatorname{VAD}$ ( Jiang et al. 2023 )	0.41	0.70	1.05	0.72	0.11	0.24	0.42	0.26
$\operatorname{DiffusionDrive}$ ( Liao et al. 2025 )	0.29	0.58	0.96	0.61	0.02	0.05	0.22	0.09
$\operatorname{DIVER}$ ( Song et al. 2026b )	–	–	–	–	0.01	0.05	0.15	0.07
$\operatorname{FocalAD}$ ( Sun et al. 2026 )	0.27	0.57	0.96	0.60	0.00	0.04	0.24	0.09

Appendix

Table 11: Planning results for 3-second short-horizon planning on the nuScenes validation set.

		$L_{2}$ (m) $\downarrow$			Col. Rate (%) $\downarrow$
SSM-Q	FM-Ref	4s	5s	6s	4s	5s	6s
		1.67	1.98	2.45	0.87	1.54	2.33
$\checkmark$		1.33	1.84	2.43	0.80	1.44	2.12
$\checkmark$	$\checkmark$	1.32	1.82	2.40	0.72	1.33	2.03

Appendix

Table 12: Ablation study of the two core modules on the nuScenes validation set under open-loop evaluation.

Temporal Modeling	Avg. L2 $\downarrow$	Avg. Col. $\downarrow$	EPDMS $\uparrow$	FPS $\uparrow$
Concat + MLP	1.52	1.26	84.2	51.0
GRU	1.41	0.77	86.4	41.9
LSTM	1.34	0.80	86.7	39.6
Transformer	1.31	0.82	87.2	33.0
Vanilla SSM	1.25	0.81	87.0	43.6
Selective SSM / Mamba	1.21	0.76	87.9	43.0

Appendix

Table 13: Ablation study of temporal memory modeling methods. Avg. L2 and Avg. Col. are evaluated on nuScenes , and EPDMS is evaluated on NAVSIMv2 navtest .

Solver	NC $\uparrow$	DAC $\uparrow$	TTC $\uparrow$	Comf. $\uparrow$	EP $\uparrow$	PDMS $\uparrow$	FPS $\uparrow$
Euler	99.0	97.1	95.5	100	83.2	89.9	43
Heun	98.5	96.7	95.2	100	82.9	89.0	38

Appendix

Table 14: Ablation on solver choice on NAVSIMv2 navtest .

Figure 5: Qualitative visualization of MomADv2 on NAVSIM across diverse driving scenarios. Compared with GuideFlow, MomADv2 generates smoother and more temporally consistent trajectories, better adheres to lane geometry and drivable-area constraints, and enables safer interactions with surrounding traffic participants.

Figure 6: Qualitative visualization of 6-second long-horizon planning by MomADv2 on nuScenes.

Explore similar work

MomWorld: Momentum-Aware Latent World Model for Long-Horizon Autonomous Driving
Sep 27, 2026Ziying Song, Shengkai Zhang, Lei Yang +6Long-Horizon Planning Latent World Models
Nanyang Technological University · Beijing Jiaotong University · North University of China +2
GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving
Jun 15, 2026Ziying Song, Caiyan Jia, Lin Liu +8Causality-Aware End-To-End Autonomous Driving Autonomous Driving
Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China
AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving
Jan 5, 2026Yanhao Wu, Haoyang Zhang, Fei He +6Causality-Aware End-To-End Autonomous Driving Autonomous Driving
School of Software Engineering, XJTU · Horizon Robotics · Shenzhen Loop Area Institute +1

Sep 27, 2026, cs.ROJ/K move · Enter open · S save

MomWorld: Momentum-Aware Latent World Model for Long-Horizon Autonomous Driving

Ziying Song, Shengkai Zhang, Lei Yang, Haozhuang Chi+5

Nanyang Technological University · Beijing Jiaotong University · North University of China+2

Long-Horizon Planning Latent World Models Robot State World Models World Momentum Stochastic Gradient Descent

Open paper AskPDF arXiv

Long-horizon planning enables autonomous vehicles to anticipate scene evolution and potential risks, supporting safe and stable decisions in complex interactions. However, existing methods struggle to propagate motion trends from observed history into the future. Long rollouts based on a single latent state may further attenuate useful dynamics, retain stale motion patterns, and disrupt reliable near-term plans. We introduce MomWorld, a momentum-aware latent world model for long-horizon planning. MomWorld extracts scene motion trends from historical-to-current observations and propagates latent momentum into future horizons, jointly predicting future configuration and momentum states. A learnable momentum persistence mechanism preserves stable trends, scene-conditioned momentum updates adapt future dynamics, and a scene-adaptive reset gate suppresses stale momentum under abrupt changes. We further propose MoFlow, a momentum-conditioned flow-matching module that refines a base trajectory to align with the predicted future scene evolution in only a few integration steps, with a horizon-aware residual fusion that preserves near-term planning stability while permitting stronger long-range corrections. Extensive experiments on NAVSIM, nuScenes and Bench2Drive demonstrate that MomWorld improves long-horizon planning consistency and reduces the average collision rate by 12.2% relative to MomAD over a 6-second planning horizon.

Abstract

Explore similar work

MomWorld: Momentum-Aware Latent World Model for Long-Horizon Autonomous Driving

GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving

AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving