DriveZero: End-to-End Driving Beyond Human Demonstrations

Hao He; Chengcheng Hu; Zirun Su; Heng Zhang; Haisong Liu; Jinke Li; Haochen Tian; Zhenwei Shen

cs.CVSep 5, 2026

DriveZero: End-to-End Driving Beyond Human Demonstrations

Authors: Hao He, Chengcheng Hu, Zirun Su, Heng Zhang, Haisong Liu, Jinke Li, Haochen Tian, Zhenwei Shen,

Organizations: Xiaomi EV AD & Robotics, L3 Team

Abstract

Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constrained by the quality and behavioral coverage of the recorded trajectories. This report presents DriveZero, an end-to-end system that learns driving behavior beyond human demonstrations. It decomposes driving into a perception model and an action model, pretrains each in the regime best suited to it, and combines them into one end-to-end planner. The two models call for different learning recipes: perception must understand the world, and benefits from massive and diverse visual data; action must interact with it, and requires closed-loop feedback. On the action side, we introduce DriveRL, a mixed-agent closed-loop reinforcement-learning framework. It converts real driving logs into interactive worlds, where a privileged teacher policy is trained with PPO through closed-loop rollouts. For the perception model, DriveVFM consolidates multiple frozen vision foundation models, including DINOv3, SigLIP2, SAM and Depth Anything V2, into a single backbone from raw images alone, requiring no task-specific annotations. DriveZero then unifies the two: a camera-only planner that distills the frozen DriveRL teacher through its rolled-out trajectories. The goal-conditioned teacher can moreover be queried under augmented driving intents, yielding diverse, goal-consistent supervision that logged data cannot provide. On nuPlan, DriveRL with value-guided test-time action search achieves a mean score of 93.57 across the Val14, Test14-hard, and Test14-random community splits in both non-reactive and reactive modes, exceeding the Log-Replay expert on all three splits. DriveZero achieves state-of-the-art performance on NAVSIMv1, NAVSIMv2 and the closed-loop HUGSIM benchmark without any human trajectory supervision.

Figures & tables

Figure 1: Overview of our end-to-end driving system. (1) Decoupled pretraining. The action model, DriveRL, is a privileged policy trained from scratch with closed-loop RL in mixed-agent interactive worlds built from real nuPlan logs. At inference, a value-guided test-time search rolls out several sampled actions, scores them using short-horizon rewards and the critic, and conditionally replaces the modal action with a higher-value candidate. The perception model, DriveVFM, distills frozen vision foundation models into a single driving backbone from raw images, without task-specific labels. (2) Unification by distillation. DriveZero initializes its encoder from DriveVFM and learns from DriveRL rollouts instead of human trajectories, yielding a camera-only end-to-end planner. (3) Performance. DriveRL exceeds the log-replay expert and prior methods on all six nuPlan closed-loop settings; DriveZero surpasses the human driver on NAVSIMv1 and sets the state of the art on NAVSIMv2 and HUGSIM without any human trajectory supervision.

Figure 2: Overview of the end-to-end student policy distillation framework. The privileged DriveRL teacher rolls out a 20-step trajectory from structured scene observations. The camera-only student DriveZero uses DriveVFM features and a command-conditioned Transformer planner to generate multiple 20-step trajectory proposals. Winner-takes-all (WTA) trajectory supervision transfers the teacher behavior, while the proposal-scoring branch is trained against PDM targets. The teacher is used only during training and is removed at inference time.

Component	Teacher configuration
Token width / attention heads	256 / 4
Ego-to-agent / ego-to-map attention	2 / 1 layers
Agent history	5 frames at 5 Hz
Agent / map capacity	96 / 256 tokens
Continuous action	Longitudinal jerk and tire steering-angle rate
Normalized action support	$(0,1)^{2}$

Table 1: DriveRL training configuration. Core architecture and control settings. Complete implementation details are provided in Appendix.

Method	Human	Val14 $\uparrow$		Test14-hard $\uparrow$		Test14-random $\uparrow$
Method	Human	NR	R	NR	R	NR	R
Log-Replay	✗	93.53	80.32	85.96	68.80	94.03	75.86
IDM [ 77 ]	✗	75.60	77.33	56.15	62.26	70.39	74.42
PDM-Closed [ 17 ]	✓	92.84	92.12	65.08	75.19	90.05	91.63
UrbanDriver [ 65 ]	✓	68.57	64.11	50.40	49.95	51.83	67.15
PlanTF [ 8 ]	✓	84.27	76.95	69.70	61.61	85.62	79.58

Table 2: Closed-Loop Performance on the nuPlan [ 2 ] Benchmark. “Human” indicates whether human demonstrations are used as training supervision. DriveRL-TTS applies value-guided test-time action search to the same checkpoint as DriveRL. Best scores are bolded ; second-best scores are underlined .

Setting	Val14 $\uparrow$		Test14-hard $\uparrow$		Test14-random $\uparrow$		Mean $\uparrow$	$\bm{\Delta}$ $\uparrow$
Setting	NR	R	NR	R	NR	R	Mean $\uparrow$	$\bm{\Delta}$ $\uparrow$
DriveRL	95.16	94.25	89.97	89.18	94.50	95.00	93.01	0.00
DriveRL-TTS ( $N=8$ )	95.17	94.49	89.97	89.05	94.92	95.11	93.12	+0.11
DriveRL-TTS ( $N=16$ )	95.22	94.38	89.98	88.97	95.29	94.98	93.13	+0.13
DriveRL-TTS ( $N=32$ )	95.49	94.43	90.95	88.85	95.83	94.84	93.40	+0.39
DriveRL-TTS ( $N=64$ )	95.54	94.53	91.13	89.15	95.93	95.12	93.57	+0.56

Table 3: Test-time Scaling of a Fixed DriveRL Checkpoint . DriveRL directly executes the Beta mode, whereas DriveRL-TTS evaluates policy-supported action candidates using a five-step rollout and a switching margin. Mean is the unweighted average over the six evaluations, and

\Delta

is measured relative to DriveRL.

Method	Input	Human	NC $\uparrow$	DAC $\uparrow$	TTC $\uparrow$	C $\uparrow$	EP $\uparrow$	PDMS $\uparrow$
PDM-Closed	GT	✓	94.6	99.8	89.9	86.9	99.9	89.1
Human Driver	GT	✓	100	100	100	99.9	87.5	94.8
TransFuser [ 9 ]	C & L	✓	97.7	92.8	92.8	100	79.2	84.0
DRAMA [ 95 ]	C & L	✓	98.0	93.1	94.8	100	80.1	85.5
VAD-v2 [ 31 ]	C & L	✓	98.1	94.8	94.3	100	80.6	86.2
DiffusionDrive [ 45 ]	C & L	✓	98.2	96.2	94.7	100	82.2	88.1

Table 4: Pseudo Closed-Loop Performance on the NAVSIMv1 navtest [ 18 ] benchmark. Input: GT = ground-truth symbolic inputs; C = camera; L = LiDAR. “Human” indicates whether human demonstrations are used as training supervision. “-Scale” denotes scaling up the training set with simulation data from SimScale [ 76 ] . Best scores are bolded ; second-best scores are underlined .

Method	Human	Stage	NC $\uparrow$	DAC $\uparrow$	DDC $\uparrow$	TLC $\uparrow$	EP $\uparrow$	TTC $\uparrow$	LK $\uparrow$	HC $\uparrow$	EC $\uparrow$	S. $\uparrow$	EPDMS $\uparrow$
		S1	94.4	98.8	100	99.5	100	93.5	99.3	87.7	36.0	-
PDM-Closed ∗ [ 17 ]	✓	S2	90.5	90.6	95.4	98.4	100	86.6	74.2	91.9	29.7	-	56.6
		S1	96.2	79.6	99.1	99.6	84.1	95.1	94.2	97.6	79.1	-
LTF [ 9 ]	✓	S2	77.8	70.2	84.3	98.1	85.1	75.7	45.4	95.7	76.0	-	25.1
		S1	96.2	92.4	95.7	99.6	83.8	96.0	94.7	96.4	60.9	-
NavFormer [ 39 ]	✓	S2	85.7	81.0	83.5	97.6	90.1	82.4	48.2	94.9	48.4	-	34.1

Table 5: Pseudo Closed-Loop Performance on the NAVSIMv2 navhard [ 3 ] Benchmark. ∗ marks methods using ground-truth symbolic inputs; all others use camera inputs. “Human” indicates whether human demonstrations are used as training supervision, and “S.” indicates per-stage EPDM score. “-Scale” denotes scaling up the training set with simulation data from SimScale [ 76 ] . Best scores are bolded ; second-best scores are underlined .

Method	Human	RC $\uparrow$					HD-Score $\uparrow$
Method	Human	E	M	H	X	Avg.	E	M	H	X	Avg.
LTF [ 9 ]	✓	67.8	35.1	26.2	40.5	38.9	58.9	18.0	9.8	25.9	23.7
VAD [ 32 ]	✓	51.3	31.1	25.3	26.5	31.4	36.3	9.5	8.0	11.5	13.4
UniAD [ 28 ]	✓	78.4	60.5	33.6	17.8	45.9	64.9	45.8	20.6	6.6	32.7
DrivoR-Scale [ 34 ]	✓	70.4	54.4	28.2	39.2	46.4	64.8	50.3	16.8	25.8	38.1
GigaPixel [ 62 ]	✗	78.6	60.7	32.7	35.4	50.1	67.4	51.9	19.1	21.6	38.5

Table 6: True Closed-Loop Performance on the HUGSIM [ 103 ] Benchmark. Zero-shot generalization using the DriveZero model from the NAVSIMv1 evaluation. “Human” indicates whether human demonstrations are used as training supervision. “-Scale” denotes scaling up the training set with simulation data from SimScale [ 76 ] . Best scores are bolded ; second-best scores are underlined .

Study	Configuration	NC $\uparrow$	DAC $\uparrow$	EP $\uparrow$	TTC $\uparrow$	Comfort $\uparrow$	PDMS $\uparrow$
Visual Backbone	DA3 Small [ 47 ]	99.10	98.84	89.68	96.21	99.93	93.31
	DA2 ViT-S [ 90 ]	98.57	99.21	91.44	95.13	99.96	93.72
	DINOv2 ViT-S [ 57 ]	98.86	99.07	91.63	95.46	99.98	93.88
	DINOv3 ViT-S [ 71 ]	98.93	99.01	91.31	95.77	99.97	93.88
	DriveVFM ViT-S	99.17	99.14	91.79	96.29	99.98	94.41
DriveVFM Teachers	DINOv3 + SigLIP2 [ 71 , 78 ]	98.67	98.98	91.55	95.27	99.98	93.69

Table 7: DriveVFM and DriveZero ablations on the NAVSIMv1 navtest [ 18 ] benchmark.

Figure 3: Feature Representation Visualization. From left to right: input images, PCA visualizations of DINOv3 and DriveVFM patch features, and their cosine-similarity heatmaps relative to the ground prototype. Blue indicates higher similarity to the ground and red indicates lower similarity. Boxes mark the long-tail obstacles of interest.

Figure 4: Visualization of DriveZero-Scale vs. Human Driver in NAVSIM navtest [ 18 ] Benchmark.

Figure 5: Visualization of DriveZero-Scale vs. Previous SOTA Model in NAVSIM navtest [ 18 ] Benchmark.

Panel of Figure 6 — Figure 6: Visualization of DriveZero-Scale vs. Previous SOTA Model in the HUGSIM [ 103 ] Benchmark.

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Setting	Value	Setting	Value
World initialization	11 frames / 2 s	Rollout horizon	110 steps at 5 Hz
Worlds per rank	2,048	Traffic quota / rank	1,024 reactive + 1,024 replay
Distributed scale	12 nodes / 96 GPUs	Global rollout batch	196,608 worlds
Nominal transitions / rank	225,280	Optimizer minibatch / rank	20,480
Minibatches / epoch	11	Optimization epochs	4
Optimizer steps / update	44	Training updates	2,400

Appendix

Table A1 : Training and rollout configuration. Runtime and optimization settings for DriveRL teacher.

Input	Per-item shape	History or capacity	Frame
Goal anchors	2-D point	2 anchors per policy input	Ego
Ego state	9-D	Current frame	Ego
Actor history	15-D / frame	5 frames; $\leq 96$ actors including ego	Ego
Vector-map segment	10-D / token	$\leq 256$ tokens, including $\leq 64$ lane centers	Ego
Traffic-light state	4-D / segment	Attached to the corresponding map segment	Map segment

Appendix

Table A2 : Structured Teacher input schema. Listed capacities are maximum counts after policy filtering.

Aspect	PPO training	Formal nuPlan deployment
Source	Future-log positions	Current ego state + route polyline
Update	Once at reset; fixed per episode	Every planner step
Slots	One or two; duplicate a single goal	Two; near and far route goals
Snapping	50% logged / 50% lane projection	Causal route polyline
Order semantics	Shared encoder + mean pool	Same unordered-set semantics

Appendix

Table A3 : Training and deployment goal protocols. Goal sources, update schedules, and slot semantics used by the Teacher.

Parameter	Value / range	Unit
Longitudinal jerk	$[-8.00,5.00]$	$\mathrm{m/s^{3}}$
Tire steering rate	$[-0.80,0.80]$	$\mathrm{rad/s}$
Positive jerk cap ( $a\geq 0$ )	1.00	$\mathrm{m/s^{3}}$
Wheelbase	3.09	m
Rear axle to center	1.46	m
Maximum acceleration	4.00	$\mathrm{m/s^{2}}$

Appendix

Table A4 : Action and vehicle-dynamics parameters. Physical command ranges and constants used by the kinematic bicycle model.

Split / mode	Score	Collision	Drivable	Direction	Making progress	TTC	Progress	Speed	Comfort
Val14 NR	95.16	98.75	100.00	99.60	98.93	95.97	96.30	98.80	98.84
Val14 R	94.25	98.57	100.00	99.24	98.75	95.80	93.83	99.21	98.66
Test14-hard NR	89.97	98.90	98.90	98.16	98.16	93.38	91.74	97.67	95.96
Test14-hard R	89.18	97.43	99.26	98.53	96.69	94.49	88.73	98.69	96.32
Test14-random NR	94.50	98.08	99.23	99.81	100.00	95.40	95.48	98.33	98.85
Test14-random R	95.00	98.85	99.62	100.00	99.62	96.55	93.34	98.85	98.85

Appendix

Table A5 : Detailed nuPlan metrics for DriveRL. Results across six evaluation settings; higher is better for every column.

Setting	Single-Ego Teacher	Self-Play Teacher
Policy-controlled actors	Ego only	Ego + $\leq 10$ vehicle NPCs
Traffic composition	Log/IDM mixed50	Policy NPCs + log/IDM mixed50
Training samples	922,703	909,645 (subset of Single-Ego data)
Worlds per rank	2,048	512
Global rollout worlds	196,608	49,152

Appendix

Table A6 : Configuration differences between DriveRL and DriveRL-SelfPlay. The two policies use the same mixed-agent simulator and PPO objective.

Model	Val14 $\uparrow$		Test14-hard $\uparrow$		Test14-random $\uparrow$		Mean $\uparrow$
Model	NR	R	NR	R	NR	R	Mean $\uparrow$
DriveRL	95.16	94.25	89.97	89.18	94.50	95.00	93.01
Self-Play, 3-perturb + augmentation	95.08	94.48	88.30	87.27	94.60	94.68	92.40
Self-Play, 3-perturb	95.15	93.74	88.90	87.47	93.70	94.77	92.29
Self-Play, augmentation	94.91	94.38	88.56	87.92	93.43	94.22	92.24
Self-Play	95.09	93.92	90.04	88.96	95.04	95.63	93.11

Appendix

Table A7 : Self-Play Comparison on the Six Closed-Loop Evaluations. All Self-Play variants are trained for 4,800 updates; the Single-Ego baseline uses its reported 2,400-update checkpoint. The best checkpoint is reported for each run, and Mean is the unweighted average over the six evaluations.

TL input	Val14 $\uparrow$		Test14-hard $\uparrow$		Test14-random $\uparrow$
TL input	NR	R	NR	R	NR	R
Off	93.35	93.19	86.49	85.41	93.48	92.24
On	94.76	93.62	88.35	85.70	95.21	93.89
Difference	$+1.41$	$+0.43$	$+1.86$	$+0.29$	$+1.73$	$+1.65$

Appendix

Table A8 : Traffic-Light Input Ablation. The red-light detector is diagnostic only in both settings.

Objective	Policy-only violation	Val14 $\uparrow$		Test14-hard $\uparrow$		Test14-random $\uparrow$
Objective	Policy-only violation	NR	R	NR	R	NR	R
TL input only	3.88%	94.29	93.19	84.85	85.65	93.79	93.09
+ TL reward	2.03%	93.08	91.35	81.71	82.96	92.36	91.79
Difference	$-1.85$ pp	$-1.21$	$-1.84$	$-3.14$	$-2.69$	$-1.43$	$-1.30$

Appendix

Table A9 : Traffic-Light Reward and Violation-Termination Ablation. All runs use 32 GPUs; “pp” denotes percentage points.

Split / mode	Default $[g_{\mathrm{near}},g_{\mathrm{far}}]$	Near $[g_{\mathrm{near}},g_{\mathrm{near}}]$	Far $[g_{\mathrm{far}},g_{\mathrm{far}}]$
Val14 NR	95.16	94.97	94.36
Val14 R	94.25	94.00	93.22
Test14-hard NR	89.97	90.74	88.01
Test14-hard R	89.18	88.82	87.13
Test14-random NR	94.50	94.57	93.18
Test14-random R	95.00	95.23	92.84

Appendix

Table A10 : Goal-Anchor Layout Evaluation for the Fixed Single-Ego Teacher. The highest score in each row is bold.

Training distribution	Evaluation	Val14 $\uparrow$		Test14-hard $\uparrow$		Test14-random $\uparrow$		Mean $\uparrow$
Training distribution	Evaluation	NR	R	NR	R	NR	R	Mean $\uparrow$
Single / dual (1:1, default)	Near + far	94.76	93.62	88.35	85.70	95.21	93.89	91.92
Earlier of two duplicated	Near + near	94.23	93.35	86.78	87.38	94.73	93.23	91.62
Later of two duplicated	Far + far	93.04	92.43	83.10	82.31	93.27	90.95	89.18

Appendix

Table A11 : Goal-Anchor Training Distribution Ablation. Models are trained from scratch with 32-GPU Adam, and evaluation layouts are matched to the corresponding training distributions. Mean is the unweighted average over the six evaluations.

Hyperparameter	Value
Model Configuration
Sensors	CAM_F0 , CAM_B0 , CAM_L0 , CAM_R0
Input resolution	$960\times 512$ (W $\times$ H)
Prediction horizon / frequency	20 steps at $5\,\mathrm{Hz}$
Trajectory proposals	64
Planning representation	256 dimensions

Appendix

Table A12 : Model and Training Configuration for DriveZero-Scale.

Backbone	NC $\uparrow$	DAC $\uparrow$	TTC $\uparrow$	Comfort $\uparrow$	EP $\uparrow$	DDC $\uparrow$	PDMS $\uparrow$
DINOv3 ViT-L	98.80	99.25	95.74	99.94	92.72	95.87	94.55
DriveVFM ViT-S	99.17	99.14	96.29	99.98	91.79	95.97	94.41
DriveVFM ViT-B	98.89	99.24	95.93	99.97	92.44	95.79	94.54
DriveVFM ViT-L	99.00	99.24	95.97	99.99	93.10	95.89	94.83

Appendix

Table A13 : Visual-backbone scaling for DriveZero on the NAVSIMv1 navtest benchmark. The backbones use the same data sources and identical mixture ratios. All downstream DriveZero variants use NAVSIM navtrain without SimScale and fine-tune rank-32 Q/V LoRA adapters.

Figure A2 : More Visualization Results of DriveZero-Scale vs. Previous SOTA Model in NAVSIM navtest [ 18 ] Benchmark.

End-to-End Autonomous Driving

End-to-end autonomous driving learns to turn sensor observations and driving context into vehicle actions or trajectories.

See all 221 papers

Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer
Oct 28, 2025Zhenxin Li, Nadine Chang, Wenhao Yao +9Reinforcement Learning End-to-End Autonomous Driving
Institute of Trustworthy Embodied AI, Fudan University · *Work done during an internship at NVIDIA. · NVIDIA +3
TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
Jun 16, 2026Zikang Xiong, Weixin Li, Zhouchonghao Wu +6End-to-End Autonomous Driving RL for Autonomous Driving
1Applied Intuition · 2UCLA · 3UC Berkeley
CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving
Jul 3, 2026Yunxiao Shi, Hong Cai, Mohammad Ghavamzadeh +1VLMs for Autonomous Driving End-to-End Autonomous Driving
Qualcomm AI Research

Oct 28, 2025J/K move · Enter open · S save

Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer

Zhenxin Li, Nadine Chang, Wenhao Yao, Xinglong Sun+8

Institute of Trustworthy Embodied AI, Fudan University · *Work done during an internship at NVIDIA. · NVIDIA+3

Reinforcement Learning End-to-End Autonomous Driving Autonomous Driving Autonomous Driving Planning RL for Autonomous Driving

Open paper AskPDF arXiv

Human demonstrations are widely considered the cornerstone of end-to-end (E2E) autonomous driving despite human demonstration's scarcity for long-tail and safety-critical scenarios. Nonetheless, current E2E autonomous driving (AD) training paradigms continue to rely on human demonstrations. Imitation learning (IL) requires human demonstrations for training, whereas reinforcement learning (RL) has emerged as a promising alternative to reduce this dependency. However, most existing RL methods for E2E AD still rely implicitly on human demonstrations. A pure rewards-based RL method can overcome the need for human demonstrations, but general RL policy gradient methods suffer from the cold-start problem. In this paper, we propose ZTRS (Zero-human demonstration end-to-end autonomous driving with TRajectory Scorer) - a complete RL-based E2E planning paradigm trained solely on real-world images and rule-based rewards, entirely without human demonstration. Through our proposed Exhaustive Policy Optimization (EPO), a policy gradient variant tailored for enumerable trajectory actions and dense supervision, ZTRS enables the model to generalize better to long-tail driving scenarios. We demonstrate this generalization through our SOTA performance against IL approaches on both long-tail Navhard and closed-loop HUGSIM datasets. Project page: https://zhenxinli.net/ZTRS/.

Abstract

End-to-End Autonomous Driving

Explore similar work

Zero-Human Demonstration End-to-end Autonomous Driving with Trajectory Scorer

TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations

CLEAR: Closed-Loop Reinforcement Learning at Scale for End-to-End Autonomous Driving