See Tomorrow, Act Today: Foresight-Driven Autonomous Driving

arXiv 2026 56.2 method, application

TLDR

ForeSight uses a world model to imagine future scenes before planning actions, achieving state-of-the-art autonomous driving on NAVSIM and nuScenes.

Reasoning

The paper presents a clear paradigm shift from reactive to anticipatory planning, with strong empirical results on real-world benchmarks. However, it does not discuss limitations such as computational cost or failure modes of the world model, and the reliance on a pretrained world model may limit generalizability.

Read-first score

Read-first score 56.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 52.

Recency 6%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Topical relevance 29%

74.3

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Citation impact 18%

71.1

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. citation_normalized_percentile=0.71065713

Methodology quality 18%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,experiment

Reproducibility 18%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Citation velocity 12%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

FrontierBridge

Rank sensitivity

Stability: volatile; rank range: 421.

Keyword Scores

world model

world dynamics prediction

generative world model

interactive world model

video world model

world simulator

model-based reinforcement learning world model

Deep Analysis

Innovations

Reframes autonomous driving as anticipatory decision-making by making future scene imagination the primary driver of action prediction, shifting from reactive to foresight-driven planning.
Introduces a two-stage framework: (1) generating plausible future visual worlds via a pretrained world model, and (2) planning actions conditioned on these imagined futures.
Proposes a paradigm shift from 'what should I do now?' to 'what will happen, and how should I respond?' enabling genuinely anticipatory rather than reactive planning.

Methodology

ForeSight operates in two stages: first, a pretrained world model generates plausible future visual worlds; second, actions are planned conditioned on these imagined futures. The framework is evaluated on the NAVSIM and nuScenes benchmarks, comparing against previous state-of-the-art end-to-end planners.

Key Results

Explicit future imagination significantly outperforms previous state-of-the-art alternatives on both NAVSIM and nuScenes, validating the foresight-driven approach for navigating dynamic, interactive scenarios.

Resources

Paper