ManeuverFlow: Maneuver Hypothesis Generation with Future Evidence for Trajectory Evaluation and Refinement in End-to-End Autonomous Driving

Yuhao Wei; Yong Chen; Chen Yang; Yingchen Wang; Delin Ouyang; Lingfeng Qi; Qi Lan; Zhanhua Zhang

cs.ROOct 9, 2026

ManeuverFlow: Maneuver Hypothesis Generation with Future Evidence for Trajectory Evaluation and Refinement in End-to-End Autonomous Driving

Authors: Yuhao Wei, Yong Chen, Chen Yang, Yingchen Wang, Delin Ouyang, Lingfeng Qi, Qi Lan, Zhanhua Zhang,

Organizations: Chongqing University · Artificial Intelligence Center, Geely Automotive Research Institute

Abstract

End-to-end planning in complex scenes must model diverse driving intentions and select the most appropriate trajectory using scene context and future risks. However, multi-query regression may collapse to one mode, while anchor-based and generative planners share a scaling bottleneck: small candidate sets limit maneuver coverage or discovery of high-quality trajectories, whereas large sets increase generation and scoring costs. We propose ManeuverFlow to generate trajectories for distinct intentions in one step and evaluate and refine them using current and future evidence. The model selects relevant maneuver modes, draws corresponding noise from the Gaussian mixture prior, and maps it to intention-specific trajectories through a maneuver-routed mixture-of-experts MeanFlow field. Current features and future features predicted by the world model are aggregated along each candidate path into trajectory-specific evidence for PDM-factor prediction. Using the same evidence, the refiner predicts local Frenet residuals for selected candidates; refined and retained candidates are then jointly re-scored for selection. With a lightweight TransFuser-style ResNet-34 backbone, ManeuverFlow achieves 90.6 PDMS and 90.1 EPDMS on NAVSIM v1/v2 navtest, respectively. On WorldEngine's recent 3DGS closed-loop benchmark, it attains the highest listed PDMS $^\ast$ scores of 75.19 and 74.58 under logged and IDM-controlled traffic, respectively. Code: https://github.com/wyh-autonomy/maneuverflow.

Figures & tables

Figure 1: Candidate-based planning paradigms. (a) Query candidates without explicit mode structure, scored from current features. (b) Fixed-anchor candidates evaluated with per-candidate future rollouts. (c) ManeuverFlow with maneuver-structured generation, shared-future evidence, and Frenet refinement before joint re-scoring.

Figure 2: Post-hoc candidate-quality analysis of the frozen Maneuver-Mixture MeanFlow Field (M 3 F) across 12,146 NAVSIM v1 navtest scenes, excluded from training and model selection. Curves report best and Top- $\kappa$ mean PDMS over nested pools; HumanAgent 94.8 is a dashed reference.

Figure 3: Overview of ManeuverFlow. Scene-conditioned M-GMP and the shared planning context drive one-step M 3 F generation of base hypotheses, which Metric Prism pre-scores using trajectory-specific evidence from a shared future BEV field. ECFR refines the selected $R$ hypotheses, which join the retained bases for evidence re-query and joint re-scoring.

Figure 4: Architecture of M 3 F. Interpolated trajectory-state tokens first query BEV and ego features, then agent memories. Time-conditioned AdaLN modulates each block, while maneuver-routed experts parameterize the interval-averaged field for one-step trajectory transport.

Method	Venue	Backbone	NC $\uparrow$	DAC $\uparrow$	TTC $\uparrow$	Comf. $\uparrow$	EP $\uparrow$	PDMS $\uparrow$
UniAD ( Hu et al. 2023 )	CVPR 2023	ResNet-34	97.8	91.9	92.9	100.0	78.8	83.4
TransFuser TF ( Chitta et al. 2023 )	TPAMI 2023	ResNet-34	97.7	92.8	92.8	100.0	79.2	84.0
World4Drive ( Zheng et al. 2025b )	ICCV 2025	ResNet-34	97.4	94.3	92.8	100.0	79.9	85.1
GoalFlow TF ( Xing et al. 2025 )	CVPR 2025	ResNet-34	98.3	93.8	94.3	100.0	79.8	85.7
DiffusionDrive TF ( Liao et al. 2025 )	CVPR 2025	ResNet-34	98.2	96.2	94.7	100.0	82.2	88.1
WoTE TF ( Li et al. 2025b )	ICCV 2025	ResNet-34	98.5	96.8	94.9	99.9	81.9	88.3

Table 1: NAVSIM v1 navtest mean results under a single official benchmark version; baselines use official results. Standard deviations are reported in the supplementary material.

Method	NC $\uparrow$	DAC $\uparrow$	DDC $\uparrow$	TLC $\uparrow$	EP $\uparrow$	TTC $\uparrow$	LK $\uparrow$	HC $\uparrow$	EC $\uparrow$	EPDMS $\uparrow$
Ego Status MLP ( Dauner et al. 2024 )	93.1	77.9	92.7	99.6	86.0	91.5	89.4	98.3	85.4	64.0
TransFuser TF ( Chitta et al. 2023 )	96.9	89.9	97.8	99.7	87.1	95.4	92.7	98.3	87.2	76.7
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
DiffusionDrive TF ( Liao et al. 2025 )	98.2	96.3	99.4	99.8	87.4	97.4	97.0	98.3	87.7	88.3
MeanFuser LTF ( Wang et al. 2026 )	98.3	97.2	99.6	99.8	87.6	97.4	97.3	98.3	88.2	89.5
Ours LTF	98.61	98.13	99.25	99.80	87.27	97.96	96.13	98.26	85.17	89.70

Table 2: NAVSIM v2 navtest mean results under a single official benchmark version; baselines use official results. Standard deviations are reported in the supplementary material.

Method	Traffic	SR $\uparrow$	EP $\uparrow$	PDMS ${}^{\ast}\uparrow$
VADv2 ( Jiang et al. 2026 )	Log	77.08	48.00	63.81
VADv2 ( Jiang et al. 2026 )	IDM	73.66	46.71	60.98
DiffusionDrive ( Liao et al. 2025 )	Log	86.24	45.09	69.83
DiffusionDrive ( Liao et al. 2025 )	IDM	85.85	43.88	68.22
MeanFuser ( Wang et al. 2026 )	Log	87.25	55.90	73.81
MeanFuser ( Wang et al. 2026 )	IDM	87.15	55.60	73.28

Table 3: Closed-loop results on all WorldEngine scenarios.

Model	Components	Prior	Flow	Evidence	Refiner	NC $\uparrow$	EP $\uparrow$	PDMS $\uparrow$
Base	Direct planner	–	–	–	–	97.73	79.24	84.01
$\mathcal{M}_{0}$	Candidate-based MeanFlow	Single	Dense MF	Cur.	–	97.21	81.05	86.14
$\mathcal{M}_{1}$	+ M-GMP and Dense-XL	M-GMP-8	Dense-XL	Cur.	–	97.02	81.63	87.91
$\mathcal{M}_{2}$	+ maneuver-routed flow	M-GMP-8	M 3 F	Cur.	–	97.64	82.12	88.35
$\mathcal{M}_{3}$	+ future evidence	M-GMP-8	M 3 F	Cur.+Fut.	–	98.52	84.41	89.93
$\mathcal{M}_{4}^{\mathrm{Cur}}$	w/o future branch	M-GMP-8	M 3 F	Cur.	ECFR	98.27	84.50	90.03

Table 4: Cumulative ablations with matched full-pipeline controls on NAVSIM v1 navtest (standard TF). Dense-XL is parameter-count matched to M 3 F;

\mathcal{M}_{4}^{\mathrm{Cur}}

disables the predicted-future branch, while

\mathcal{M}_{4}^{\mathrm{KM}}

replaces M-GMP-8 with KMeans-8. Cur./Fut. = current/predicted-future BEV evidence.

Figure 5: Six urban scenes with the top-three maneuver components shown in paired BEV and front-view projections.

Component routing		PDMS $\uparrow$ at proposal budget $N$
$k$	M-GMP target recall@ $k$ (%)	8	16	32	64	128
1	87.20	89.85	90.04	90.26	90.33	90.42
2	96.46	90.04	90.15	90.43	90.54	90.59
3	98.30	90.06	90.28	90.41	90.58 †	90.56
4	99.21	90.10	90.27	90.42	90.57	90.67
M 3 F activ. bound (MB) $\downarrow$		1.11	2.07	3.99	7.82	15.50

Table 5: M-GMP routing and proposal-budget sensitivity on NAVSIM v1 navtest; FPS: perception–M 3 F; † : default.

ID	Motion family	Condition	Count (%)
0	Stop/Crawl	$D_{n}<5$	12,044 (11.66)
1	Cruise	$\|\bar{\psi}_{n}\|\leq 4.5^{\circ}$ , $\|\Delta\bar{s}_{n}\|\leq\eta_{s}$	8,695 (8.42)
2	Accelerating	$\|\bar{\psi}_{n}\|\leq 4.5^{\circ}$ , $\Delta\bar{s}_{n}>\eta_{s}$	17,339 (16.79)
3	Decelerating	$\|\bar{\psi}_{n}\|\leq 4.5^{\circ}$ , $\Delta\bar{s}_{n}<-\eta_{s}$	24,501 (23.72)
4	Left lane change	$4.5^{\circ}<\bar{\psi}_{n}\leq 13^{\circ}$	9,330 (9.03)
5	Left turn	$\bar{\psi}_{n}>13^{\circ}$	18,174 (17.60)

Table S1: Rule-defined, trajectory-derived M-GMP maneuver families and their occupancy in the NAVSIM navtrain data used for prior construction.

(a) Module architecture
Lifecycle	Module	Structure	Config. $(d,h,d_{\mathrm{ff}})$	Output
Shared	Perception encoder	ResNet-34; 4-stage TransFuser; 4 GPT/stage	$h=8$ ; $d_{\mathrm{ff}}=4d$ ; dropout 0.1	$F_{n}^{\mathrm{hi}},F_{n}^{\mathrm{lo}}$
	Scene/agent decoder	Two-layer Transformer decoder	$(256,8,1024)$ ; dropout 0	–
Hypothesize	M 3 F	6 DiT–MoE; 8 FFN experts/block	$(256,4,1024)$ ; attn./FFN 0/0.1	$\mathbb{R}^{8\times 4}$
Verify	World model	Recurrent predictor; causal refinement	–	4 abs. / 4 res.
	Evidence reader	Trajectory-guided BEV sampling; SlotPool	Token 512; $h=8$ ; dropout 0.1	$E_{n,i}$

Table S2: Reproducibility overview. (a) Module architecture; outputs omit the batch dimension (interfaces: Sec. 4.2 ). (b) Two-stage optimization; loss weights follow auxiliary / generation / verification / refinement. The score and residual losses include their internal scales of 10 and 5, respectively. Stage 2 initializes from Stage 1 and jointly optimizes all inference-time modules; the current model generates candidates for evaluator labeling.

Metric	LTF	TF
NC	$98.49{\pm}0.02$	$98.42{\pm}0.02$
DAC	$97.40{\pm}0.03$	$98.01{\pm}0.03$
TTC	$95.13{\pm}0.05$	$95.19{\pm}0.05$
Comf.	$99.99{\pm}0.00$	$99.99{\pm}0.01$
EP	$84.87{\pm}0.04$	$85.36{\pm}0.04$
PDMS	$89.98{\pm}0.06$	$90.58{\pm}0.05$

Table S3: Main-result variation, reported as mean

\pm

sample standard deviation across three independently trained checkpoints, each averaged over five evaluations. WorldEngine uses log replay (Log) or reactive IDM traffic.

Table 15

Figure S3: Controlled expert sweep and final-plan provenance. (a,b) Paired BEV/front views of two NAVSIM scenes. Thin E0–E7 trajectories are controlled responses sharing a fixed M-GMP source state, scene context, and transport interval; the source is omitted, dashed green is the logged reference, and thick red is the final trajectory $\tau_{n}^{\star}$ . The final plan comes from the full $N=64$ base/refined pool after ECFR, evidence re-query, and Metric Prism re-scoring rather than from the displayed sweep, with provenance E6 $\rightarrow$ ECFR in (a) and E7 $\rightarrow$ ECFR in (b). These examples expose route-conditioned response separation and final-plan provenance; dataset-level support is supplied by the quantitative component-support and matched-ablation results.

Figure S4: Descriptive, non-budget-matched gallery on six shared scenes with paired BEV/front views. (a) ManeuverFlow: a qualitative $N=32$ M 3 F draw, routed $16/8/8$ and colored by component; reported quantitative and deployment results use $N=64$ . (b) WoTE: the top 64 of 256 predictions by final reward. (c) DiffusionDrive: all 20 candidates ordered by logits. (d) MeanFuser: eight native proposal heads plus the fused output. Counts and selection are method-specific; no quantitative comparison is implied.

Autonomous Driving Planning

Autonomous driving planning selects safe, feasible vehicle actions and trajectories amid traffic, uncertainty, road rules, and changing goals.

See all 382 papers

FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving
Sep 20, 2026Xiang Li, Bikun Wang, Qing Xu +1Flow Matching Trajectory Generation
Cross-Domain Computing Solutions, Bosch
MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
Feb 23, 2026Junli Wang, Yinan Zheng, Xueyi Liu +9Autonomous Driving Planning End-to-End Autonomous Driving
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · Xiaomi EV +1
ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
May 22, 2026Xiyang Wang, Xinlin Wang, Tingguang Zhou +7Trajectory Generation VLMs for Autonomous Driving
1Afari Intelligent Drive · 2Tianjin University · University of Macau

Sep 20, 2026J/K move · Enter open · S save

FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving

Xiang Li, Bikun Wang, Qing Xu, Jianjun Wang

Cross-Domain Computing Solutions, Bosch

Flow Matching Trajectory Generation End-to-End Autonomous Driving Safe Motion Planning Autonomous Driving Planning

Open paper AskPDF arXiv

End-to-end autonomous driving maps current observations directly to future trajectories, yet those trajectories must remain valid as the scene evolves. Future state modeling aims to address this temporal mismatch, but general representations often contain information unrelated to ego planning and affect trajectory generation only through auxiliary supervision, static conditioning, or proposal evaluation. We propose FeasibleFlow, a one-step end-to-end generative framework that jointly transports a configuration-space feasibility field and multimodal ego trajectories. Our Asymmetric Joint MeanFlow uses the pathwise Jacobian-vector product in the MeanFlow identity to incorporate field evolution into trajectory transport. Because safety feedback is sparser than progress feedback, we further introduce the Anchor-relative ranker (ARR) and Pareto-ReinFlow to balance safety and progress in candidate selection and generation, respectively. Experiments on the NAVSIM benchmark demonstrate the strong performance of FeasibleFlow and validate both the joint transport of feasibility and trajectories and the proposed safety-first mechanisms.

Abstract

Autonomous Driving Planning

Explore similar work

FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving

MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving

ChainFlow-VLA: Causal Flow Planning with Vision-Language Models