ScaTE: A Scalable Framework for Self- Supervised Traversability Estimation in Unstructured Environments

Seo, Junwon; Kim, Taekyung; Kwak, Kiho; Min, June Kee; Shim, Inwook

doi:10.1109/lra.2023.3234768

Cited by 18 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, some methods try to predict the traversability by the CNNs directly. For instance, Seo et al (2022) propose a scalable framework for learning traversability from 3D point cloud in a self‐supervised manner. Although these learning‐based approaches have achieved good results on some datasets, they usually need a large amount of annotated data for training and the model could not be easily transferred to different environments or LiDAR types, which limits their practical applications.…”

Section: Related Workmentioning

confidence: 99%

Traversability analysis for autonomous driving in complex environment: A LiDAR‐based terrain modeling approach

Xue

Liang³

et al. 2023

Journal of Field Robotics

View full text Add to dashboard Cite

For autonomous driving, traversability analysis is one of the most basic and essential tasks. In this paper, we propose a novel LiDAR‐based terrain modeling approach, which could output stable, complete, and accurate terrain models and traversability analysis results. As terrain is an inherent property of the environment that does not change with different view angles, our approach adopts a multiframe information fusion strategy for terrain modeling. Specifically, a normal distributions transform mapping approach is adopted to accurately model the terrain by fusing information from consecutive LiDAR frames. Then the spatial‐temporal Bayesian generalized kernel inference and bilateral filtering are utilized to promote the stability and completeness of the results while simultaneously retaining the sharp terrain edges. Based on the terrain modeling results, the traversability of each region is obtained by performing geometric connectivity analysis between neighboring terrain regions. Experimental results show that the proposed method could run in real‐time and outperforms state‐of‐the‐art approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Traversability analysis for autonomous driving in complex environment: A LiDAR‐based terrain modeling approach

Xue

Liang³

et al. 2023

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…Methods operating in a self-supervised manner aim to overcome this limitation by generating a training signal without relying on manual annotation. Instead they exploit information from other sensor modalities (Brooks and Iagnemma, 2012;Otsu et al, 2016;Castro et al, 2023;Seo et al, 2023;Higa et al, 2019;Meng et al, 2023;Zürn et al, 2021;Sathyamoorthy et al, 2022), or the interaction of the robot with the environment (Richter and Roy, 2017;Seo et al, 2022;Frey et al, 2023;Ahtiainen et al, 2017;Gasparino et al, 2022;Cai et al, 2022;Xue et al, 2023b;Sathyamoorthy et al, 2022;Cai et al, 2023;Jung et al, 2023). The generated supervision signal allows training a model that predicts a look-ahead estimate of the terrain, all without requiring the robot to be near to or interact with the terrain.…”

Section: Traversability From Self-supervisionmentioning

confidence: 99%

“…(Richter and Roy, 2017) proposed to use anomaly detection to predict safe image regions for indoor navigation with a wheeled robot. Multiple other works integrated the concept of anomaly detection and tools available in evidential deep learning to learn from real-world data without manual labeling (Frey et al, 2023;Schmid et al, 2022;Seo et al, 2022;Wellhausen et al, 2020;Cai et al, 2023). Contrastive learning has shown promising results in learning expressive representations that can be used for traversability estimation in a self-supervised manner (Seo et al, 2023;Xue et al, 2023b;Jung et al, 2023).…”

Section: Traversability From Self-supervisionmentioning

confidence: 99%

Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environments

Frey¹,

Hoeller²,

Khattak³

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Autonomous navigation at high speeds in off-road environments necessitates robots to comprehensively understand their surroundings using onboard sensing only. The extreme conditions posed by the off-road setting can cause degraded camera image quality due to poor lighting and motion blur, as well as limited sparse geometric information available from LiDAR sensing when driving at high speeds. In this work, we present RoadRunner, a novel framework capable of predicting terrain traversability and an elevation map directly from camera and LiDAR sensor inputs. RoadRunner enables reliable autonomous navigation, by fusing sensory information, handling of uncertainty, and generation of contextually informed predictions about the geometry and traversability of the terrain while operating at low latency. In contrast to existing methods relying on classifying handcrafted semantic classes and using heuristics to predict traversability costs, our method is trained end-to-end in a self-supervised fashion. The RoadRunner network architecture builds upon popular sensor fusion network architectures from the autonomous driving domain, which embed LiDAR and camera information into a common Bird's Eye View perspective. Training is enabled by utilizing an existing traversability estimation stack to generate training data in hindsight in a scalable manner from realworld off-road driving datasets. Furthermore, RoadRunner improves the system latency by a factor of ∼ 4, from 500 ms to 140 ms, while improving the accuracy for traversability costs and elevation map predictions. We demonstrate the effectiveness of RoadRunner in enabling safe and reliable offroad navigation at high speeds in multiple real-world driving scenarios through unstructured desert environments.

show abstract

“…Following our prior work [58], we design a realistic offroad environment with various components including large bumps and randomly patterned rough terrains (see Fig. 5).…”

Section: Uncertainty-aware Deploymentmentioning

confidence: 99%

Shopping with AI: Consumers' perceived autonomy in the age of AI

Kim

2022

Human-Centered Artificial Intelligence

View full text Add to dashboard Cite

ScaTE: A Scalable Framework for Self- Supervised Traversability Estimation in Unstructured Environments

Cited by 18 publications

References 26 publications

Traversability analysis for autonomous driving in complex environment: A LiDAR‐based terrain modeling approach

Traversability analysis for autonomous driving in complex environment: A LiDAR‐based terrain modeling approach

Locomotion Policy Guided Traversability Learning using Volumetric Representations of Complex Environments

Shopping with AI: Consumers' perceived autonomy in the age of AI

Contact Info

Product

Resources

About