STRIDE: Evaluating Spatiotemporal Reasoning in Driving Edge Cases

Lieqi Liu; Rui gao; Jia-Chen Gu; Wenbo Hu; Zhaobin Mo; Ahmadreza Moradipari; Nejib Ammar; Wei Wang

cs.CVOct 16, 2026

STRIDE: Evaluating Spatiotemporal Reasoning in Driving Edge Cases

Authors: Lieqi Liu, Rui gao, Jia-Chen Gu, Wenbo Hu, Zhaobin Mo, Ahmadreza Moradipari, Nejib Ammar, Wei Wang,

Organizations: University of California, Los Angeles · Toyota InfoTech Labs

Abstract

In autonomous driving, perceiving surrounding objects is not enough: failing to understand how they move and interact over time can lead to dangerous decisions. Evaluating vision-language models (VLMs) therefore requires testing whether they connect past spatial observations to future consequences. Yet existing benchmarks often assess edge cases through basic perception questions or test temporal understanding in simple scenarios, leaving complex spatiotemporal reasoning underexplored. We introduce STRIDE (SpatioTemporal Reasoning In Driving Edge Cases), an object-centric benchmark for long-tail, safety-critical driving scenarios. STRIDE covers six task families: spatial perception, spatial understanding, temporal memory, temporal extrapolation, trajectory prediction, and scene-context awareness. It pairs multiple-choice questions probing individual spatiotemporal judgments with related free-form visual question answering (VQA) requiring detailed scene explanations and justifications of driving decisions. We prioritize scenes with unusual object behaviors and complex traffic interactions, generate reference answers from structured dataset annotations through automated procedures, and use limited language-model assistance and human verification to ensure annotation quality. Across 12 proprietary, open-weight, and driving-specialized models, even the best performer, GPT-6-Astra, achieves only 43.4% average multiple-choice accuracy, versus an approximately 20% random-choice baseline. Further analysis reveals that strong performance in describing driving scenes does not necessarily translate to accurate safety-critical judgments, and that models struggle more with reconstructing object motion than recalling past positions. STRIDE thus exposes spatiotemporal driving limitations that aggregate VQA scores can conceal.

Figures & tables

Figure 1: Overview of STRIDE . Built from multi-view temporal driving data, STRIDE evaluates spatiotemporal capabilities at the object and scene levels through complementary tasks. Qwen3.6-27B and GPT-6-Astra achieve substantially lower multiple-choice questions (MCQ) accuracy on STRIDE than on the previous benchmark ( Fruhwirth-Reisinger et al., 2026 ) .

Benchmark	Input		QA Format	Capabilities
Benchmark	Format	View	QA Format	Spatial	Temporal	Edge Cases	Grounding	Ego Traj.
NuScenes-QA ( Qian et al., 2024 )	Image / Video	Surround
DriveLM-nuScenes ( Sima et al., 2024 )	Image	Surround
Reason2Drive ( Nie et al., 2024 )	Video	Mixed
LingoQA ( Marcu et al., 2024 )	Video	Front
OmniDrive ( Wang et al., 2025 )	Image	Surround

Table 1: Comparison of representative autonomous-driving vision-language benchmarks. : explicitly evaluated; : no dedicated evaluation reported. “Mixed” indicates dataset-dependent camera configurations. : multiple-choice or fixed-vocabulary short-answer QA; : open-ended QA. A capability is marked only when explicitly evaluated: Spatial concerns where objects are and how they relate, Temporal concerns reasoning across frames or about what happens next, Edge Cases concerns unusual or safety-critical situations, Grounding requires explicit localization, and Ego Traj. requires future ego-trajectory coordinates.

Figure 2: Data generation pipeline of STRIDE . From left to right, dataset annotations and extracted signals are converted into structured labels. Manually designed hybrid format pair these labels with five-frame context to generate linked MCQ answers and verbalized OEQ references, followed by human review and curation.

Figure 3: Coverage of STRIDE . (a) Share of tagged clips containing each challenging situation in nuScenes and Waymo E2E. (b) Share of clips within each task family carrying the same scenario tag (SC: scene context, SP: spatial perception, SU: spatial understanding, TM: temporal memory, TE: temporal extrapolation, TRJ: trajectory). Tags are multi-label, so columns need not sum to $100\%$ . (c) Future ego-maneuver composition by speed change over unique ground-truth motion patterns; bars are normalized within each maneuver.

Driving Expert Models
	nuScenes				Waymo E2E
Model	MCQ $\uparrow$	OEQ $\uparrow$	ADE $\downarrow$	FDE $\downarrow$	MCQ $\uparrow$	OEQ $\uparrow$	ADE $\downarrow$	FDE $\downarrow$
Random Chance	19.8	–	–	–	20.3	–	–	–
Human Performance	79	–	–	–	69	–	–	–
Dolphins ( Ma et al., 2024 )	18.5	3.24	8.16	3.81	22.2	1.86	18.43	8.60
UniAD 2.0 ( Hu et al., 2023 )	–	–	0.56	0.79	–	–	–	–

Table 2: Results on the nuScenes and Waymo E2E splits of STRIDE . MC accuracy is reported in percentage. OEQ performance is reported with scale 0-10. Best and second-best model results are shown in bold and underline , respectively.

(a) nuScenes	Model	Representative tasks
Capability		Task 1	Score	Task 2	Score
Spatial perception	G-Pro	SP-3: Distance Estimate	64%	SP-7: Spatial desc.	2.10
Spatial understanding	GPT-5.5	SC-6: Scene desc.	9.22	SU-2: Drivable region	22%
Temporal memory	GPT-5.5	TM-2: Prev. position	72%	TM-3: Recent motion	18%
Temporal extrapolation	Best	TE-1: Future motion	40%	TE-6: Scene evolution	6.98

Table 3: Representative per-task results used in the analysis. GPT-5.6: GPT-5.6-Sol; G-Fl.: Gemini-3.6-Flash; G-Pro: Gemini-3.1-Pro; Claude: Claude-Sonnet-5; Q35: Qwen3.6-35B-A3B; Q30-T/Q8-T: Qwen3-VL-30B-A3B-Thinking/Qwen3-VL-8B-Thinking.

Figure 4: Analysis of GPT-6-Astra’s driving capabilities. (a) Accuracy gaps between recalling previous object positions and reconstructing recent motion; $\Delta$ denotes the difference in percentage points. (b) Stronger positional judgments along with weaker spatial-constraint and future-event reasoning. (c) Favorable explanation scores with low accuracy on related driving judgments. Judge scores are multiplied by 10 for visualization on a shared 0–100 scale.

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Method	Pearson	Spearman	Mean $\|\Delta\|$
BLEU	$-0.290$	$-0.120$	$7.573$
METEOR	$0.098$	$0.356$	$5.580$
BLEURT	$0.193$	$0.195$	—
Qwen3-VL-32B (text-only)	$0.780$	$0.804$	$1.320$
GPT-5.5 (vision)	$0.870$	$0.781$	$0.880$
Qwen3-VL-32B (vision)	$0.788$	$0.845$	$0.900$

Appendix

Table 4: Agreement of different automatic evaluation methods with human judgments.

Template	Question	Reason for removal
SC-1	Weather and environmental condition	No suitable choice for dark scenes.
SC-2	Time of day	Samples are mostly daytime, so the label is not reliable.
SC-3	Road type and driving environment	Parked cars do not imply a parking lot, and the sample contains no highway.
TE-3	Future lane of the target object	The frames do not provide enough lane information.
TE-4	Ego response to the target object	Ground truth is incorrect.
TE-5	Next traffic event	Ground truth is incorrect and the question requires lane identification.

Appendix

Table 5: Multiple-choice templates removed after manual review of the 50-item sample. Each template contains 50 questions.

Task family	Questions	MCQ	OEQ	Scenes	Question IDs
Scene context	50	0	50	50	SC-6
Spatial perception	250	200	50	242	SP-1, SP-2, SP-3, SP-5, SP-7
Spatial understanding	200	150	50	186	SU-1, SU-2, SU-4, SU-7
Temporal memory	200	200	0	187	TM-2, TM-3, TM-4, TM-5
Temporal extrapolation	100	50	50	100	TE-1, TE-6
Trajectory	350	200	150	316	TRJ-1–TRJ-7

Appendix

Table 6: nuScenes question and scene counts by task family. Scene counts use scene_id . Scenes are reused across question IDs, so family scene counts do not sum to the split total (310 scenes appear in more than one family).

Task family	Questions	MCQ	OEQ	Scenes	Question IDs
Scene context	200	150	50	117	SC-1, SC-2, SC-3, SC-4
Spatial perception	150	100	50	108	SP-2, SP-3, SP-3a
Temporal memory	150	150	0	109	TM-2, TM-3, TM-5
Temporal extrapolation	200	200	0	158	TE-1, TE-2, TE-4, TE-5
Trajectory	500	300	200	135	TRJ-1–TRJ-10
Split total	1200	900	300	335	24 IDs

Appendix

Table 7: Waymo question and scene counts by task family. Scene counts use scene_id . The split also contains 691 unique bundles ( scene_id plus group_id ). Family scene counts do not sum to the split total (183 scenes appear in more than one family).

Model	Identifier	Reasoning / thinking
Proprietary LVLMs
GPT-5.5	gpt-5.5	reasoning_effort=low
GPT-5.6	gpt-5.6	reasoning_effort=low
GPT-6-Astra	gpt-6-Astra	reasoning_effort=low
Gemini-3.6-Flash	gemini-3.6-flash	thinking_level=low
Gemini-3.1-Pro	gemini-3.1-pro-preview	thinking_level=low

Appendix

Table 8: Evaluated models. Reasoning knobs are API- or family-specific; “–” means none. UniAD is scored only on TRJ-5.

Scene Context
			Proprietary						Open-weight					Driving Expert
ID	Task	Metric	GPT-5.5	GPT-5.6	GPT-6	G-Fl.	G-Pro	Claude	Q35	Q2.5	Q30-T	Q8-T	Q27	Dolphins
SC-6	Environment description	Judge $\uparrow$	9.22	8.94	8.94	8.50	7.22	8.94	8.84	7.16	9.14	9.10	8.94	4.58
Space Perception
SP-1	Trajectory direction	Acc. (%) $\uparrow$	24.0	32.0	38.0	36.0	24.0	16.0	14.0	20.0	20.0	18.0	6.0	26.0
SP-2	Relative position	Acc. (%) $\uparrow$	56.0	42.0	60.0	62.0	54.0	40.0	46.0	32.0	40.0	34.0	52.0	10.0

Appendix

Table 9: Fine-grained results on the nuScenes portion of STRIDE . MCQ accuracy is reported in percentage. OEQ responses are evaluated by the LVLM judge. For ADE, lower is better; for all other metrics, higher is better. Best and second-best results in each row are shown in bold and underline , respectively.

Scenario / Corner Case
			Proprietary						Open-weight						Driving Expert
ID	Task	Metric	GPT-5.5	GPT-5.6	GPT-6	G-Fl.	G-Pro	Claude	Q35	Q2.5	Q30-T	Q8-T	Q8-I	Q27	Dolphins
SC-1	Scene description	Acc. (%) $\uparrow$	44.0	46.0	48.0	40.0	38.0	40.0	32.0	42.0	36.0	38.0	44.0	40.0	32.0
SC-2	Main risk source	Acc. (%) $\uparrow$	28.0	24.0	36.0	20.0	30.0	36.0	22.0	24.0	26.0	34.0	26.0	30.0	20.0
SC-3	Preferred ego action	Acc. (%) $\uparrow$	48.0	46.0	44.0	42.0	44.0	38.0	36.0	46.0	38.0	42.0	38.0	44.0	26.0
SC-4	Scene/risk/action explanation	Judge $\uparrow$	8.08	7.80	7.76	7.46	4.22	8.28	7.14	4.02	6.92	6.98	7.40	7.76	2.38

Appendix

Table 10: Fine-grained results on the Waymo E2E split of STRIDE . MCQ accuracy is reported in percentage. OEQ responses are evaluated by the LVLM judge. For ADE, lower is better; for all other metrics, higher is better. Best and second-best results in each row are shown in bold and underline , respectively.

ID	Fmt	Template	N
SC-1	MCQ	What is the primary weather and environmental condition in the current scene? A Clear/Sunny; B Rain/Wet; C Overcast; D Snow/Ice; E Fog/Haze
SC-2	MCQ	Based on the lighting conditions and sky visibility, what is the estimated time of day? A Daytime; B Nighttime; C Dawn/Dusk
SC-3	MCQ	Which of the following best describes the overall road typology and driving environment? A Urban intersection; B Straight urban/suburban road; C Highway; D Construction zone; E Parking lot/off-road
SC-4	MCQ	How spatially dense or crowded is the current traffic environment considering all visible road users? A Sparse; B Moderate; C Dense
SC-5	MCQ	What is the baseline safety risk level of the overall scene, independent of any single specific object? A Low; B Moderate; C High
SC-6	OEQ	Describe the overall environment of the scene, including weather, lighting conditions, road type, and notable surrounding activity.	Y

Appendix

Table 11: Scene-context templates. SC-1–5 were dropped from the reviewed nuScenes split.

ID	Fmt	Template	N	W
SP-1	MCQ	What is the trajectory direction of <obj> in relation to the ego vehicle? A Toward ego; B Away from ego; C Left-to-right; D Right-to-left; E Static; F Same direction as ego	Y
SP-2	MCQ	What is the spatial relationship between <obj> and ego vehicle? A In front; B Front-left; C Front-right; D Directly left; E Directly right; F Rear-left; G Rear-right; H Behind	Y	Y
SP-3	MCQ	What is the approximate distance between <obj> and ego vehicle? A 0–5m; B 5–15m; C 15–30m; D 30–50m; E $>$ 50m	Y	Y
SP-4	MCQ	Use the ego vehicle’s lanes as reference, which lane is <obj> located in? A Same lane; B Left adjacent; C Right adjacent; D Two lanes left; E Two lanes right
SP-5	MCQ	What is the occlusion state of <obj> ? A Fully visible; B Partially occluded ( $<$ 50%); C Mostly occluded ( $\geq$ 50%); D Fully occluded but inferred	Y
SP-6	MCQ	Is <obj> on the drivable ground plane? A On road; B On sidewalk; C Above the ground

Appendix

Table 12: Space-perception templates.

ID	Fmt	Template	N
SU-1	MCQ	What physical constraints affect the ego vehicle given <obj> ? A Blocking ego lane; B Partially obstructing; C No constraint; D Dynamic obstruction in ego lane	Y
SU-2	MCQ	Which region around the ego vehicle is safely drivable? A Front only; B Front-left; C Front-right; D Left only; E Right only; F None; G All directions	Y
SU-3	MCQ	What is the risk level posed by <obj> to the ego vehicle? A Low; B Moderate; C High; D Critical/imminent collision
SU-4	MCQ	Does the ego vehicle have sufficient clearance to change lanes? A Safe left; B Safe right; C Unsafe both; D Safe both	Y
SU-5	MCQ	Which maneuver is geometrically feasible at this moment? A Maintain lane; B Lane change left; C Lane change right; D Turn left; E Turn right; F Stop only
SU-6	MCQ	How spatially dense is the environment around ego considering the number of objects and their distance to the ego? A Sparse; B Moderate; C Dense; D Highly congested

Appendix

Table 13: Space-understanding templates. This family is nuScenes-only.

ID	Fmt	Template	N	W
TE-1	MCQ	What is the most likely future motion of <obj> over the next few seconds? A Continue straight; B Turn left; C Turn right; D Stop; E Cross ego path	Y	Y
TE-2	MCQ	If both vehicles maintain their current motion, when would a collision occur? A No collision; B $>$ 10s; C 5–10s; D 2–5s; E $<$ 2s		Y
TE-3	MCQ	Which lane will <obj> most likely occupy in the next few seconds? A Remain; B Left lane; C Right lane; D Enter ego lane; E Exit roadway
TE-4	MCQ	What should be the ego vehicle’s primary response to <obj> ? A Maintain speed; B Slow down; C Prepare to stop; D Change lane; E Yield; F Emergency braking		Y
TE-5	MCQ	What traffic event is most likely to occur next? A Lane change; B Vehicle stopping; C Pedestrian crossing; D Vehicle merging; E No significant event		Y
TE-6	OEQ	Describe how the current scene is likely to evolve over the next few seconds and what actions the ego vehicle should take to maintain safety.	Y

Appendix

Table 14: Time-extrapolation templates.

ID	Fmt	Template	N	W
TM-1	MCQ	Which objects previously appeared in the scene but are no longer visible in current frame? A None; B Pedestrian; C Vehicle; D Bicycle; E Static obstacle; F Multiple objects
TM-2	MCQ	Where was <obj> located relative to the ego vehicle in the previous frame(s)? A In front; B Front-left; C Front-right; D Left; E Right; F Behind	Y	Y
TM-3	MCQ	What was the recent motion pattern of <obj> ? A Moving straight; B Slowing down; C Accelerating; D Turning left; E Turning right; F Stopped previously	Y	Y
TM-4	MCQ	How many objects are currently occluded but were previously visible in the previous frame? A None; B 1; C 2–3; D More than 3	Y
TM-5	MCQ	In which lane was <obj> located earlier in the sequence? A Same lane; B Left adjacent; C Right adjacent; D Outside roadway	Y	Y
TM-6	OEQ	Describe the recent history of the scene, including objects that appeared or disappeared, changes in their motion, and any interactions with the ego vehicle.

Appendix

Table 15: Time-memory templates.

ID	Fmt	Template	N	W
TRJ-1	MCQ	Based on the past 5 consecutive 360 ∘ multi-camera frames, what best describes the ego vehicle’s recent maneuver over those past frames? A Go straight; B Slightly veer left; C Slightly veer right; D Turn left; E Turn right; F Slow to near stop	Y	Y
TRJ-2	MCQ	Based on the past 5 consecutive 360 ∘ multi-camera frames, what is the most likely ego-vehicle maneuver over the next 5 future frames (approximately 2.5 seconds)? A – F as TRJ-1	Y	Y
TRJ-3	MCQ	Based on the past 5 consecutive 360 ∘ multi-camera frames, at the 5th future frame (approximately 2.5 seconds ahead), which relative endpoint region best matches the ego vehicle trajectory in the current ego-centric coordinate system? A Front-left; B Front-center; C Front-right; D Left-side; E Right-side; F Near current position	Y	Y
TRJ-4	MCQ	Based on the past 5 consecutive 360 ∘ multi-camera frames, how does the ego vehicle speed trend evolve over the next 5 future frames (approximately 2.5 seconds)? A Accelerating; B Constant speed; C Decelerating; D Stopping/nearly stopped	Y	Y
TRJ-5	OEQ	Using past ego positions <trajectory_history> in the ego frame (current ${=}[0,0]$ ), predict the next 5 future positions as a JSON array of 5 $[x,y]$ points.	Y	†
TRJ-6	OEQ	Same setup as TRJ-5, with known first future point <first_future_position> . Predict only the remaining 4 points.	Y	†

Appendix

Table 16: Trajectory-prediction templates. TRJ-5/6 on Waymo keep the ID but change the visual preamble (front-view,

\sim

2.0s); see Table 17 .

ID	Fmt	Waymo template
SC-1	MCQ	Which option best describes the current scene? A highway; B traffic intersection; C construction zone; D right turn
SC-2	MCQ	What is the main risk source in this scene? A Road debris; B Cut-in vehicle; C Crossing pedestrian/cyclist; D Unclear lane boundary; E No clear immediate risk
SC-3	MCQ	What is the preferred action for the ego vehicle? A Slow down; B Keep lane carefully; C Change lane; D Stop and wait; E Speed up
SC-4	OEQ	Briefly describe the scene, the main risk, and the preferred action.
SP-3a	OEQ	What is the approximate distance in meters between <obj> and the ego vehicle?
TRJ-5 †	OEQ	Based on the past 5 observed front-view frames sampled over approximately 2.0 seconds, predict the next 5 future ego positions as a JSON array of 5 $[x,y]$ points. Current frame is $[0,0]$ .

Appendix

Table 17: Templates that appear only on Waymo, or reuse a nuScenes ID with different wording. SC-1–4 here are scenario-corner-case , not scene-context. † TRJ-5/6 drop the 360 ∘ preamble and the pasted history, and ask for a front-view 2.0s horizon.

Autonomous Driving Benchmarks

Autonomous driving benchmarks evaluate how well vehicles perceive, predict, plan, and act safely across varied roads and conditions.

See all 140 papers

May 22, 2026

DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving

Spatiotemporal intelligence in autonomous driving (AD) requires an agent to integrate multi-view observations into a coherent scene representation, maintain object continuity across viewpoints and time, and reason about spatial relations, interactions, and future dynamics. However, existing AD vision-language benchmarks largely focus on single-view, static, ego-centric, or single-source question answering, leaving it unclear whether current Vision-Language Models (VLMs) can truly construct and reason over dynamic driving scenes. We introduce DriveSpatial, a benchmark of 15.6K human-verified QA pairs across 20 tasks from five large-scale AD datasets. DriveSpatial evaluates four abilities: Cognitive Scene Construction, Multi-view Relational Understanding, Temporal Reasoning, and Generalization. Unlike prior benchmarks, DriveSpatial is generated from a dynamic multi-relational scene graph that encodes object states, spatial relations, interactions, camera visibility, and temporal correspondences, enabling QA pairs that enforce genuine cross-view and spatiotemporal reasoning. Evaluating 15 representative VLMs reveals a substantial human-model gap: the strongest model trails humans by 28.4 points, with Cognitive Scene Construction emerging as the key bottleneck. Further diagnostics show that language-only prompting is insufficient, while explicit BEV grounding consistently improves performance. These results suggest that current VLMs lack the scene-construction ability needed for reliable spatiotemporal driving intelligence. DriveSpatial and its construction pipeline will be released to support future research.

Hao Vo, Khoa Vo, Phu Loc Nguyen +10

University of Arkansas, USA · Google Research, Google · University of Liverpool, UK +1

VLM Evaluation Autonomous Driving Datasets Autonomous Driving Benchmarks Vision-Language Models VLMs for Autonomous Driving Autonomous Driving Perception+3

Ask PDF

May 27, 2026

ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving

Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between reasoning and trajectory generation. However, the robustness of such systems under realistic input perturbations remains largely unexplored. We show that these models are highly vulnerable to realistic input perturbations, achieving up to 89% attack success rate (ASR) on reasoning and up to 72% on trajectory manipulation in closed-loop simulation, leading to increased collision rates and degraded safety metrics. Using NVIDIA's recent Alpamayo models as representative industry-developed VLAs, we conduct the first systematic black-box study of reasoning-enabled VLA models under realistic textual input corruptions, evaluating their impact on reasoning and driving behavior. We introduce a reasoning-aware evaluation framework capturing both semantic and structural aspects of reasoning, along with safety-centric measures. We also introduce a benchmark for evaluating attacks and defenses on reasoning-trajectory interactions in autonomous driving. Our results highlight the need for rigorous evaluation and improved defenses to ensure the safety of reasoning-enabled VLA systems in autonomous driving.

Mohammadreza Teymoorianfard, Jean-Philippe Monteuuis, Jonathan Petit +1

University of Massachusetts Amherst · Qualcomm

VLMs for Autonomous Driving Autonomous Driving Safety Evaluation Autonomous Driving Adversarial Attacks on VLA Models VLM Reasoning Vision-Language-Action Models+2

Ask PDF

Apr 9, 2026

CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning

Cooperative autonomous driving requires traffic scene understanding from both vehicle and infrastructure perspectives. While vision-language models (VLMs) show strong general reasoning capabilities, their performance in safety-critical traffic scenarios remains insufficiently evaluated due to the ego-vehicle focus of existing benchmarks. To bridge this gap, we present CrashSight, a large-scale vision-language benchmark for roadway crash understanding using real-world roadside camera data. The dataset comprises 250 crash videos, annotated with 13K multiple-choice question-answer pairs organized under a two-tier taxonomy. Tier 1 evaluates the visual grounding of scene context and involved parties, while Tier 2 probes higher-level reasoning, including crash mechanics, causal attribution, temporal progression, and post-crash outcomes. We benchmark 8 state-of-the-art VLMs and show that, despite strong scene description capabilities, current models struggle with temporal and causal reasoning in safety-critical scenarios. We provide a detailed analysis of failure scenarios and discuss directions for improving VLM crash understanding. The benchmark provides a standardized evaluation framework for infrastructure-assisted perception in cooperative autonomous driving. The CrashSight benchmark, including the full dataset and code, is accessible at https://mcgrche.github.io/crashsight.

Rui Gan, Junyi Ma, Pei Li +4

University of Wisconsin–Madison · University of Wyoming · Columbia University

Autonomous Driving Benchmarks Autonomous Driving Safety Evaluation Autonomous Driving Temporal Video Understanding

Ask PDF

Abstract

Autonomous Driving Benchmarks

Explore similar work

DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving

ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving

CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning