Driving · 2026-11-05
MotoVerse: A Benchmark for Predictive Perception of Motorized Two-Wheelers in Dense Unstructured Traffic
Varun A. Paturkar, Shankar Gangisetty, C. V. Jawahar
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
The authors introduce MotoVerse, an ego-centric benchmark for predictive perception of motorized two-wheelers (MTWs) in dense, unstructured traffic. It contains 949 maneuver clips with trajectory annotations for 31,000+ surrounding road agents (16,000+ MTWs), for two tasks: ERMA (ego-rider maneuver anticipation) and TATP (traffic agent trajectory prediction).
Why it matters
The authors argue that MTWs are underrepresented in predictive perception research for autonomous driving and ADAS, and propose MotoVerse to enable challenge-aware evaluation from an MTW’s perspective, including dynamic ego-motion, weak traffic structure, and contextual occlusion.
Method
- Collect MotoVerse: 949 MTW maneuver clips in dense, unstructured traffic with trajectory annotations for 31,000+ surrounding agents (16,000+ MTWs).
- Define two predictive perception tasks: ERMA (Ego-Rider Maneuver Anticipation) and TATP (Traffic Agent Trajectory Prediction).
- Benchmark multiple model families including conventional predictors, general-purpose VLMs, driving-specific VLMs, and vision-language-action models; evaluate using a challenge taxonomy.
Abstract (from arXiv)
Motorized Two-Wheelers (MTWs) dominate personal transport across much of the Global South, yet remain largely overlooked in predictive perception research for autonomous driving and ADAS. We introduce MotoVerse, a benchmark for predictive perception from an MTW's ego-centric perspective. MotoVerse comprises 949 maneuver clips collected in dense, unstructured traffic and trajectory annotations for over 31,000 surrounding road agents, including over 16,000 MTWs, enabling two complementary tasks: Ego-Rider Maneuver Anticipation (ERMA) and Traffic Agent Trajectory Prediction (TATP). Each clip is further annotated with an MTW-specific challenge taxonomy comprising dynamic ego-motion, weak traffic structure and contextual occlusion, enabling challenge-aware evaluation. We benchmark established conventional prediction models, general-purpose Vision-Language Models (VLMs), driving-specific VLMs and vision-language-action models. Our experiments reveal three key insights: (i) video backbones reach most of their full-observation accuracy from the first fifth of a maneuver, whereas zero-shot VLMs need most of the maneuver to be observed; (ii) zero-shot VLMs, whether general-purpose or driving-specific, largely remain close to simple baselines on both tasks; a preliminary LoRA study shows that adaptation lifts anticipation sharply but leaves trajectory prediction behind conventional models; and (iii) the rider's own motion drives forecasting difficulty: for every model, including a static baseline, errors are highest during left turns and rise under dynamic ego-motion. We believe MotoVerse will serve as a challenging benchmark for safer and more robust predictive AI for intelligent two-wheelers. The dataset and evaluation code are publicly available at https://github.com/VarunIIITH/MotoVerse.
Related papers
- Breaking survivorship bias in driving world models
- BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model
- doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving
- Closed-Loop Aware Planning via Imitation-Free Speed Scoring for End-to-End Autonomous Driving
- GAIA-1: A Generative World Model for Autonomous Driving
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-11-04 · Indexed by Pub-AI: 2026-11-05 UTC
MotoVerse: A Benchmark for Predictive Perception of Motorized Two-Wheelers in Dense Unstructured Traffic
Preprint posted: 2026-11-04 · Original record ↗
- arxiv
- 2611.06007
Explicit source versions (1)
- v1 · 2026-11-04
- Preprint available
Source date: 2026-11-04 · First detected: 2026-11-05 UTC · Historical baseline
Source evidence (2)
- Official evidence ↗ · RSS guid=oai:arXiv.org:2611.06007v1; arxiv:announce_type=new; item pubDate (official metadata)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Motorized Two-Wheelers (MTWs) dominate personal transport across much of the Global South, yet remain largely overlooked in predictive perception research for autonomous driving and ADAS. We introduce MotoVerse, a benchmark for predictive perception from an MTW's ego-centric perspective. MotoVerse comprises 949 maneuver clips collected in dense, unstructured traffic and trajectory annotations for over 31,000 surrounding road agents, including over 16,000 MTWs, enabling two complementary tasks: Ego-Rider Maneuver Anticipation (ERMA) and Traffic Agent Trajectory Prediction (TATP). Each clip is further annotated with an MTW-specific challenge taxonomy comprising dynamic ego-motion, weak traffic structure and contextual occlusion, enabling challenge-aware evaluation. We benchmark established conventional prediction models, general-purpose Vision-Language Models (VLMs), driving-specific VLMs and vision-language-action models. Our experiments reveal three key insights: (i) video backbones reach most of their full-observation accuracy from the first fifth of a maneuver, whereas zero-shot VLMs need most of the maneuver to be observed; (ii) zero-shot VLMs, whether general-purpose or driving-specific, largely remain close to simple baselines on both tasks; a preliminary LoRA study shows that adaptation lifts anticipation sharply but leaves trajectory prediction behind conventional models; and (iii) the rider's own motion drives forecasting difficulty: for every model, including a static baseline, errors are highest during left turns and rise under dynamic ego-motion. We believe MotoVerse will serve as a challenging benchmark for safer and more robust predictive AI for intelligent two-wheelers. The dataset and evaluation code are publicly available at https://github.com/VarunIIITH/MotoVerse.
