TruckDrive: Long-Range Autonomous Highway Driving Dataset

TL;DR

TruckDrive is introduced, a highway-scale multimodal driving dataset captured with a sensor suite purpose-built for long range sensing, finding that state-of-the-art autonomous driving models do not generalize to ranges beyond 150 meters, exposing a systematic long-range gap that current architectures and training signals cannot close.

Abstract

Safe highway autonomy for heavy trucks remains an open and unsolved challenge: due to long braking distances, scene understanding of hundreds of meters is required for anticipatory planning and to allow safe braking margins. However, existing driving datasets primarily cover urban scenes, with perception effectively limited to short ranges of only up to 100 meters. To address this gap, we introduce TruckDrive, a highway-scale multimodal driving dataset, captured with a sensor suite purpose-built for long range sensing: seven long-range FMCW LiDARs measuring range and radial velocity, three high-resolution short-range LiDARs, eleven 8MP surround cameras with varying focal lengths and ten 4D FMCW radars. The dataset offers 475 thousands samples with 165 thousands densely annotated frames for driving perception benchmarking up to 1,000 meters for 2D detection and 400 meters for 3D detection, depth estimation, tracking, planning and end to end driving over 20 seconds sequences at highway speeds. We find that state-of-the-art autonomous driving models do not generalize to ranges beyond 150 meters, with drops between 31% and 99% in 3D perception tasks, exposing a systematic long-range gap that current architectures and training signals cannot close.

Figures (5)

• Figure 1: TruckDrive Dataset. Autonomous vehicles, especially heavy trucks, require long planning horizons for safe driving in highway scenarios due to higher speed and longer breaking distances. This requires perception ranges well beyond $300$ m, while the most common datasets are limited to $100$ m caesar2020nuscenessun2020scalability. We introduce the TruckDrive Dataset, a large scale multi-modal benchmark captured with a sensor setup tailored for long-range perception with LiDAR, radar and $3$D annotations up to $400$ m and images and $2$D annotations up to $1000$ m.
• Figure 2: Performance Saturation on Urban Datasets. We plot the performance of 2D and 3D OD, Tracking, Prediction and Depth Estimation of NuScenes caesar2020nuscenes and Kitti behley2020benchmarklidarbasedpanopticsegmentation leader boards across the years and observe a saturation of these benchmarks.
• Figure 3: Sensors Position and FoV. Sensor position (top) and the nominal instrumented horizontal field of view (bottom) of, from left to right, radars, LiDARs and cameras, highlighting the unprecedented ranges at which they can operate.
• Figure 4: Dataset Analysis. Our dataset comprises an unprecedented density of instance objects at ranges (greater than $200$ meters) yet to be explored in publicly available datasets (a,b), as well as driving speeds $5$ times higher (c) and sequences with traveled length up to $8$ times longer (d) than existing benchmarks.
• Figure 5: Driving Tasks and Challenges. We report qualitative results of the best baselines across planning, 2D/3D object detection, depth estimation and scene reconstruction. Even when trained on TruckDrive, existing methods struggle in the long-range, high-speed regime. Planning modules exhibit conservative behavior due to low-speed assumptions. Grid-based BEV models degrade perception as large spatial coverage demands heavy downsampling, erasing safety-critical details such as small debris or lost cargo liu2022bevfusion, while depth methods struggle beyond 200m and in sky regions guan2025bridgedepth, revealing limited distance awareness and motivating architectures for highway-scale perception.