A RUGD Dataset for Autonomous Navigation and Visual Perception in Unstructured Outdoor Environments

Wigness, Maggie; Eum, Sungmin; Rogers, John G.; Han, David K.; Kwon, Heesung

doi:10.1109/iros40897.2019.8968283

Cited by 101 publications

(62 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More significantly, the proposed SFNet achieves the state-of-theart performance on Cityscapes [5] and ADE20K [6] with the lowest amount of computation compared to the state-of-theart methods. Our segmentation method also performed quite well on images taken from an unstructured natural environment, accurately capturing intricate and irregular shapes and structures, such as RUGD dataset [7] depicted on the right column of Figure 1.…”

Section: Introductionmentioning

confidence: 83%

“…To evaluate the proposed method, experiments are conducted on Cityscapes [5], ADE20K [6] and RUGD [7] datasets. Experimental results show that the proposed method achieves a novel state-of-the-art performance and spends the lowest amount of computation against state-of-the-art methods.…”

Section: Methodsmentioning

confidence: 99%

“…It has twenty thousand images for training and two thousand images for validation. In our training setting, images were cropped to 473 x 473. c: RUGD Dataset RUGD dataset [7] is a recently introduced video dataset tailored for semantic segmentation in unstructured environments. Different from the Citycapes [5] and ADE20K [6], it focuses on off-road autonomous navigation scenario collected from a Clearpath Husky ground robot traversing in a variety of natural, unstructured semi-urban areas.…”

Section: B: Ade20k Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Sketch-and-Fill Network for Semantic Segmentation

et al. 2021

Self Cite

View full text Add to dashboard Cite

Recent efforts in semantic segmentation using deep learning framework have made notable advances. While achieving high performance, however, they often require heavy computation, making them impractical to be used in real world applications. There are two reasons that produce prohibitive computational cost: 1) heavy backbone CNN to create high resolution of contextual information and 2) complex modules to aggregate multi-level features. To address these issues, we propose the computationally efficient architecture called "Sketch-and-Fill Network (SFNet)" with a three-stage Coarse-to-Fine Aggregation (CFA) module for semantic segmentation. In the proposed network, lower-resolution contextual information is first produced so that the overall computation in the backbone CNN is largely reduced. Then, to alleviate the detail loss of the lower-resolution contextual information, the CFA module forms global structures and fills fine details in a coarse-to-fine manner. To preserve global structures, the contextual information is passed without any reduction to the CFA module. Experimental results show that the proposed SFNet achieves significantly lower computational loads while delivering comparable or improved segmentation performance with state-of-the-art methods. Qualitative results show that our method is superior to state-ofthe-art methods in capturing fine detail while keeping global structures on Cityscapes, ADE20K and RUGD benchmarks.

show abstract

Section: Introductionmentioning

confidence: 83%

Section: Methodsmentioning

confidence: 99%

Section: B: Ade20k Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Sketch-and-Fill Network for Semantic Segmentation

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Color based terrain classification was performed to label obstacles and generate navigational behaviors (Manduchi et al (2005)). More recently, semantic segmentation methods based on deep learning (Long et al (2015)) were successfully used to classify off-road terrains (Jiang et al (2020); Wigness et al (2019)) and perform the task of terrain navigation.…”

Section: Terrain Classification Methodsmentioning

confidence: 99%

Self-Reflective Terrain-Aware Robot Adaptation for Consistent Off-Road Ground Navigation

Siva¹,

Wigness²,

Rogers³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Ground robots require the crucial capability of traversing unstructured and unprepared terrains and avoiding obstacles to complete tasks in real-world robotics applications such as disaster response. When a robot operates in off-road field environments such as forests, the robot's actual behaviors often do not match its expected or planned behaviors, due to changes in the characteristics of terrains and the robot itself. Therefore, the capability of robot adaptation for consistent behavior generation is essential for maneuverability on unstructured off-road terrains. In order to address the challenge, we propose a novel method of self-reflective terrain-aware adaptation for ground robots to generate consistent controls to navigate over unstructured off-road terrains, which enables robots to more accurately execute the expected behaviors through robot self-reflection while adapting to varying unstructured terrains. To evaluate our method's performance, we conduct extensive experiments using real ground robots with various functionality changes over diverse unstructured off-road terrains. The comprehensive experimental results have shown that our self-reflective terrain-aware adaptation method enables ground robots to generate consistent navigational behaviors and outperforms the compared previous and baseline techniques.

show abstract

“…To enable the classification model to be fully trained and have a wide range of adaptability, a reasonable dataset needs to be constructed. In the process of supervised training of the SVM, a public dataset of Robot Unstructured Ground Driving (RUGD) is used [37]. The dataset contains more than 7000 frames of pixel-level images.…”

mentioning

confidence: 99%

Detection and Modeling of Unstructured Roads in Forest Areas Based on Visual-2D Lidar Data Fusion

Lei

Yao

Zhao

et al. 2021

Forests

View full text Add to dashboard Cite

The detection and recognition of unstructured roads in forest environments are critical for smart forestry technology. Forest roads lack effective reference objects and manual signs and have high degrees of nonlinearity and uncertainty, which pose severe challenges to forest engineering vehicles. This research aims to improve the automation and intelligence of forestry engineering and proposes an unstructured road detection and recognition method based on a combination of image processing and 2D lidar detection. This method uses the “improved SEEDS + Support Vector Machine (SVM)” strategy to quickly classify and recognize the road area in the image. Combined with the remapping of 2D lidar point cloud data on the image, the actual navigation requirements of forest unmanned navigation vehicles were fully considered, and road model construction based on the vehicle coordinate system was achieved. The algorithm was transplanted to a self-built intelligent navigation platform to verify its feasibility and effectiveness. The experimental results show that under low-speed conditions, the system can meet the real-time requirements of processing data at an average of 10 frames/s. For the centerline of the road model, the matching error between the image and lidar is no more than 0.119 m. The algorithm can provide effective support for the identification of unstructured roads in forest areas. This technology has important application value for forestry engineering vehicles in autonomous inspection and spraying, nursery stock harvesting, skidding, and transportation.

show abstract

A RUGD Dataset for Autonomous Navigation and Visual Perception in Unstructured Outdoor Environments

Cited by 101 publications

References 41 publications

Sketch-and-Fill Network for Semantic Segmentation

Sketch-and-Fill Network for Semantic Segmentation

Self-Reflective Terrain-Aware Robot Adaptation for Consistent Off-Road Ground Navigation

Detection and Modeling of Unstructured Roads in Forest Areas Based on Visual-2D Lidar Data Fusion

Contact Info

Product

Resources

About