RELLIS-3D Dataset: Data, Benchmarks and Analysis

Jiang, Peng; Osteen, Philip R.; Wigness, Maggie; Saripalli, Srikanth

doi:10.1109/icra48506.2021.9561251

Cited by 142 publications

(88 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Fusing a terrain's semantic (visual) and geometric (point cloud) features for better classification has also been studied [3]. These works typically fall under the supervised-classification category and utilize large handlabeled datasets of images [18], [19] to train classifiers. However, manually annotating datasets is time-and laborintensive, not scalable to large amounts of data, and may not be applicable for robots of different sizes, inertias, and dynamics [20].…”

Section: A Characterizing Traversabilitymentioning

confidence: 99%

TerraPN: Unstructured Terrain Navigation using Online Self-Supervised Learning

Sathyamoorthy¹,

Weerakoon²,

Guan³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present TerraPN, a novel method to learn the surface characteristics (texture, bumpiness, deformability, etc.) of complex outdoor terrains for autonomous robot navigation. Our method predicts navigability cost maps for different surfaces using patches of RGB images, odometry, and IMU data. Our method dynamically varies the resolution of the output cost map based on the scene to improve its computational efficiency. We present a novel extension to the Dynamic-Window Approach (DWA-O) to account for a surface's navigability cost while computing robot trajectories. DWA-O also dynamically modulates the robot's acceleration limits based on the variation in the robot-terrain interactions. In terms of perception, our method learns to predict navigability costs in ∼ 20 minutes for five different surfaces, compared to 3-4 hours for previous scene segmentation methods, and leads to a decrease in inference time. In terms of navigation, our method outperforms previous works in terms of vibration costs and generates robot velocities suitable for different surfaces.• A novel method that trains a neural network in an online self-supervised manner to learn a terrain's surface

show abstract

Section: A Characterizing Traversabilitymentioning

confidence: 99%

TerraPN: Unstructured Terrain Navigation using Online Self-Supervised Learning

Sathyamoorthy¹,

Weerakoon²,

Guan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…While many autonomous driving datasets exist, most focus on urban environments [6][7][8][9][10]. For off-road driving, existing datasets only focus on scene understanding, with a special focus on semantic segmentation [11][12][13][14][15][16]. We argue the semantic labels (i.e.…”

Section: Introductionmentioning

confidence: 99%

TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models

Triest¹,

Sivaprakasam²,

J.³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present TartanDrive, a large scale dataset for learning dynamics models for off-road driving. We collected a dataset of roughly 200,000 off-road driving interactions on a modified Yamaha Viking ATV with seven unique sensing modalities in diverse terrains. To the authors' knowledge, this is the largest real-world multi-modal off-road driving dataset, both in terms of number of interactions and sensing modalities. We also benchmark several state-of-the-art methods for model-based reinforcement learning from high-dimensional observations on this dataset. We find that extending these models to multi-modality leads to significant performance on off-road dynamics prediction, especially in more challenging terrains. We also identify some shortcomings with current neural network architectures for the off-road driving task. Our dataset is available at https://github.com/castacks/tartan drive.

show abstract

“…The limited availability of off-road environment based datasets is another challenge which hinders the progression of off-road autonomous driving domain. For the robotic navigation in the off-road environment there are three main datasets (1) RELLIS-3D [4], (2) RUGD [5], and (3) Deep-Scene [6]. RELLIS-3D [4] is a multimodal dataset collected in an off-road environment, which contains annotations for 13,556 LiDAR scans and 6,235 images where ground truth in terms of annotated labels are provided.…”

Section: Introductionmentioning

confidence: 99%

“…For the robotic navigation in the off-road environment there are three main datasets (1) RELLIS-3D [4], (2) RUGD [5], and (3) Deep-Scene [6]. RELLIS-3D [4] is a multimodal dataset collected in an off-road environment, which contains annotations for 13,556 LiDAR scans and 6,235 images where ground truth in terms of annotated labels are provided. RUGD [5] dataset gives a rich ontology and large set of ground truths of 7546 annotations with 24 classes.…”

Section: Introductionmentioning

confidence: 99%

OFFSEG: A Semantic Segmentation Framework For Off-Road Driving

Viswanath¹,

Singh²,

Jiang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Off-road image semantic segmentation is challenging due to the presence of uneven terrains, unstructured class boundaries, irregular features and strong textures. These aspects affect the perception of the vehicle from which the information is used for path planning. Current off-road datasets exhibit difficulties like class imbalance and understanding of varying environmental topography. To overcome these issues we propose a framework for off-road semantic segmentation called as OFFSEG that involves (i) a pooled class semantic segmentation with four classes (sky, traversable region, nontraversable region and obstacle) using state-of-the-art deep learning architectures (ii) a colour segmentation methodology to segment out specific sub-classes (grass, puddle, dirt, gravel, etc.) from the traversable region for better scene understanding. The evaluation of the framework is carried out on two off-road driving datasets, namely, RELLIS-3D and RUGD. We have also tested proposed framework in IISERB campus frames. The results show that OFFSEG achieves good performance and also provides detailed information on the traversable region.

show abstract

RELLIS-3D Dataset: Data, Benchmarks and Analysis

Cited by 142 publications

References 22 publications

TerraPN: Unstructured Terrain Navigation using Online Self-Supervised Learning

TerraPN: Unstructured Terrain Navigation using Online Self-Supervised Learning

TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models

OFFSEG: A Semantic Segmentation Framework For Off-Road Driving

Contact Info

Product

Resources

About