ACT-Bench: Towards Action Controllable World Models for Autonomous Driving

• URL: http://arxiv.org/abs/2412.05337v1
• Date: Fri, 06 Dec 2024 01:06:28 GMT
• Title: ACT-Bench: Towards Action Controllable World Models for Autonomous Driving
• Authors: Hidehisa Arai, Keishi Ishihara, Tsubasa Takahashi, Yu Yamaguchi,
• Abstract summary: World models have emerged as promising neural simulators for autonomous driving.<n>We develop an open-access evaluation framework, ACT-Bench, for quantifying action fidelity.<n>We demonstrate that the state-of-the-art model does not fully adhere to given instructions, while Terra achieves improved action fidelity.
• Score: 2.6749009435602122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World models have emerged as promising neural simulators for autonomous driving, with the potential to supplement scarce real-world data and enable closed-loop evaluations. However, current research primarily evaluates these models based on visual realism or downstream task performance, with limited focus on fidelity to specific action instructions - a crucial property for generating targeted simulation scenes. Although some studies address action fidelity, their evaluations rely on closed-source mechanisms, limiting reproducibility. To address this gap, we develop an open-access evaluation framework, ACT-Bench, for quantifying action fidelity, along with a baseline world model, Terra. Our benchmarking framework includes a large-scale dataset pairing short context videos from nuScenes with corresponding future trajectory data, which provides conditional input for generating future video frames and enables evaluation of action fidelity for executed motions. Furthermore, Terra is trained on multiple large-scale trajectory-annotated datasets to enhance action fidelity. Leveraging this framework, we demonstrate that the state-of-the-art model does not fully adhere to given instructions, while Terra achieves improved action fidelity. All components of our benchmark framework will be made publicly available to support future research.

Related papers

• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• ResWorld: Temporal Residual World Model for End-to-End Autonomous Driving [40.28153843744977]
  We propose Temporal Residual World Model (TR-World), which focuses on dynamic object modeling.<n>By calculating the temporal residuals of scene representations, the information of dynamic objects can be extracted without relying on detection and tracking.<n>We also propose Future-Guided Trajectory Refinement (FGTR) module, which conducts interaction between prior trajectories and the future BEV features.
  arXiv  Detail & Related papers  (2026-02-11T14:12:26Z)
• DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving [49.11389494068169]
  We present DrivingGen, the first comprehensive benchmark for generative driving world models.<n>DrivingGen combines a diverse evaluation dataset curated from both driving datasets and internet-scale video sources.<n>General models look better but break physics, while driving-specific ones capture motion realistically but lag in visual quality.
  arXiv  Detail & Related papers  (2026-01-04T13:36:21Z)
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability [84.52205243353761]
  Recent work proposes using world models to generate controlled virtual environments in which AI agents can be tested before deployment. We investigate ways of simplifying world models that remain agnostic to the AI agent under evaluation.
  arXiv  Detail & Related papers  (2025-04-06T20:35:44Z)
• End-to-End Driving with Online Trajectory Evaluation via BEV World Model [52.10633338584164]
  We propose an end-to-end driving framework WoTE, which leverages a BEV World model to predict future BEV states for Trajectory Evaluation. We validate our framework on the NAVSIM benchmark and the closed-loop Bench2Drive benchmark based on the CARLA simulator, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-04-02T17:47:23Z)
• LEGO-Motion: Learning-Enhanced Grids with Occupancy Instance Modeling for Class-Agnostic Motion Prediction [12.071846486955627]
  We introduce a novel occupancy-instance modeling framework for class-agnostic motion prediction tasks, named LEGO-Motion. Our model comprises (1) a BEV encoder, (2) an Interaction-Augmented Instance, and (3) an Instance-Enhanced BEV. Our method achieves state-of-the-art performance, outperforming existing approaches.
  arXiv  Detail & Related papers  (2025-03-10T14:26:21Z)
• Bench2Drive-R: Turning Real World Data into Reactive Closed-Loop Autonomous Driving Benchmark by Generative Model [63.336123527432136]
  We introduce Bench2Drive-R, a generative framework that enables reactive closed-loop evaluation. Unlike existing video generative models for autonomous driving, the proposed designs are tailored for interactive simulation. We compare the generation quality of Bench2Drive-R with existing generative models and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-11T06:35:18Z)
• WorldSimBench: Towards Video Generation Models as World Simulators [79.69709361730865]
  We classify the functionalities of predictive models into a hierarchy and take the first step in evaluating World Simulators by proposing a dual evaluation framework called WorldSimBench. WorldSimBench includes Explicit Perceptual Evaluation and Implicit Manipulative Evaluation, encompassing human preference assessments from the visual perspective and action-level evaluations in embodied tasks. Our comprehensive evaluation offers key insights that can drive further innovation in video generation models, positioning World Simulators as a pivotal advancement toward embodied artificial intelligence.
  arXiv  Detail & Related papers  (2024-10-23T17:56:11Z)
• CERES: Critical-Event Reconstruction via Temporal Scene Graph Completion [7.542220697870245]
  This paper proposes a method for on-demand scenario generation in simulation, grounded on real-world data. By integrating scenarios derived from real-world datasets into the simulation, we enhance the plausibility and validity of testing.
  arXiv  Detail & Related papers  (2024-10-17T13:02:06Z)
• OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB [40.62577054196799]
  We introduce a large-scale synthetic dataset OmniPose6D, crafted to mirror the diversity of real-world conditions. We present a benchmarking framework for a comprehensive comparison of pose tracking algorithms.
  arXiv  Detail & Related papers  (2024-10-09T09:01:40Z)
• MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking [51.28485682954006]
  We propose a pure Mamba-based framework (MambaVT) to fully exploit intrinsic-temporal contextual modeling for robust visible-thermal tracking. Specifically, we devise the long-range cross-frame integration component to globally adapt to target appearance variations. Experiments show the significant potential of vision Mamba for RGB-T tracking, with MambaVT achieving state-of-the-art performance on four mainstream benchmarks.
  arXiv  Detail & Related papers  (2024-08-15T02:29:00Z)
• JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds [79.00975648564483]
  Trajectory forecasting models, employed in fields such as robotics, autonomous vehicles, and navigation, face challenges in real-world scenarios. This dataset provides comprehensive data, including the locations of all agents, scene images, and point clouds, all from the robot's perspective. The objective is to predict the future positions of agents relative to the robot using raw sensory input data.
  arXiv  Detail & Related papers  (2023-11-05T18:59:31Z)
• GEO-Bench: Toward Foundation Models for Earth Monitoring [139.77907168809085]
  We propose a benchmark comprised of six classification and six segmentation tasks. This benchmark will be a driver of progress across a variety of Earth monitoring tasks.
  arXiv  Detail & Related papers  (2023-06-06T16:16:05Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)
• Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction [31.02081143697431]
  Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and video-surveillance applications. We propose a lightweight attention-based recurrent backbone that acts solely on past observed positions. We employ a common goal module, based on a U-Net architecture, which additionally extracts semantic information to predict scene-compliant destinations.
  arXiv  Detail & Related papers  (2022-04-25T11:12:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.