A Self-Training Approach-Based Traversability Analysis for Mobile Robots in Urban Environments

Lee, Deokjung; Chung, Woojin

doi:10.1109/icra48506.2021.9561394

Cited by 14 publications

(10 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. In such environments, the detection of traversable regions plays a significant role in guaranteeing safety In our previous work in [28], we developed a traversability analysis based on elevation mapping. The semi-supervised learning approach was adopted to alleviate the data labeling cost.…”

Section: Traversability Analysis a Self-training Approachmentioning

confidence: 99%

See 1 more Smart Citation

ODS-Bot: Mobile Robot Navigation for Outdoor Delivery Services

et al. 2022

Self Cite

View full text Add to dashboard Cite

Autonomous mobile robots have been used in outdoor delivery services. Delivery robots have to cope with dynamic obstacles and various environmental conditions. Although several successful technological solutions are available for indoor applications, there are still plenty of unsolved problems in outdoor environments. In this study, we concentrate on three technological challenges hindering the development of campus delivery robots. The first challenge is robust localization in various dynamic outdoor environments. Localization results obtained using lidars and Global Navigation Satellite System (GNSS) sensors show complementary advantages and disadvantages. The proposed localization strategy efficiently combines information from multiple sensors. The second challenge is safe navigation based on the detection of the traversable region. The presented terrain traversability analysis provides clear, real-time positive and negative obstacle information. The third challenge is the requirement of an effective path planning strategy to reduce the risk of collisions or deadlocks. We collected the appearance history of regional dynamic obstacles in the map. The resultant path was carefully generated to avoid crowded areas. Experimental verifications have been successfully conducted on the Korea University campus. The presented results clearly indicate that the proposed methods are essential to achieve safe and reliable navigation in dynamic, real-world environments.

show abstract

Section: Traversability Analysis a Self-training Approachmentioning

confidence: 99%

“…The traversability mapping results were utilized for local path planning in the form of an occupancy grid map. A negative obstacle detector, as described in [28], was also adopted. Fig.…”

Section: B Experimentsmentioning

confidence: 99%

ODS-Bot: Mobile Robot Navigation for Outdoor Delivery Services

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Here we give a brief overview of related work and refer interested readers to articles (Borges et al, 2022), (Sevastopoulos and Konstantopoulos, 2022) and (Wettergreen et al, 2008) for more comprehensive information. A new field of research emerges when terrain analysis is supported with artificial intelligence (Lee and Chung, 2021), (Guastella and Muscato, 2020), (Arena et al, 2021). The most commonly used technologies for distance detection and high-resolution distance measurement in autonomous navigation systems are 3D cameras and LiDAR sensors.…”

Section: Related Workmentioning

confidence: 99%

Terrain Prediction With a Low-Cost Lidar Sensor for Mobile Robots

Edlinger

Nüchter²

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Terrain modelling influences various aspects of mobile robot navigation. The ability to explore in rough terrain and to recognise ground conditions are essential to perform different activities efficiently, safely and satisfactorily. For this reason, intelligent vehicles and robotic systems need cognitive capabilities to understand the terrain and derive information from it. The information is mostly acquired and processed by very high resolution 3D-cameras and LiDAR sensors which provide full 360-degree environmental view to deliver accurate 3D data. The aim of this paper is to find out whether a low-cost sensor variant can measure sufficient and significant data from the terrain in order to modify the navigation behaviour and provide the correct control commands. In this paper we describe a low-cost sensor with Infrared Time-of-Flight (ToF) technology and 64 pixel depth image. Furthermore, different experiments on the detection of the sensor were conducted and with appropriate filters and signal processing algorithms the environmental perception could be significantly improved. In summary, our results provide both evidence and guidelines for the use of the selected sensor in environmental perception to improve local obstacle detection and terrain modelling, which we believe will lead to a very cost-effective improvement in competence and situational awareness.

show abstract

“…However, like conventional mapping techniques, they do not attempt to directly predict the physical outcome of a robot's actions. This stands in contrast to experiential learning methods that directly learn which observations correspond to traversable or untraversable terrains or obstacles, though a number of works in robotic perception have incorporated elements of experiential learning, for example, for learning to classify traversability [29][30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

Learning robotic navigation from experience: principles, methods and recent results

Levine

Shah

2022

Phil. Trans. R. Soc. B

View full text Add to dashboard Cite

Navigation is one of the most heavily studied problems in robotics and is conventionally approached as a geometric mapping and planning problem. However, real-world navigation presents a complex set of physical challenges that defies simple geometric abstractions. Machine learning offers a promising way to go beyond geometry and conventional planning, allowing for navigational systems that make decisions based on actual prior experience. Such systems can reason about traversability in ways that go beyond geometry, accounting for the physical outcomes of their actions and exploiting patterns in real-world environments. They can also improve as more data is collected, potentially providing a powerful network effect. In this article, we present a general toolkit for experiential learning of robotic navigation skills that unifies several recent approaches, describe the underlying design principles, summarize experimental results from several of our recent papers, and discuss open problems and directions for future work. This article is part of the theme issue ‘New approaches to 3D vision’.

show abstract

A Self-Training Approach-Based Traversability Analysis for Mobile Robots in Urban Environments

Cited by 14 publications

References 20 publications

ODS-Bot: Mobile Robot Navigation for Outdoor Delivery Services

ODS-Bot: Mobile Robot Navigation for Outdoor Delivery Services

Terrain Prediction With a Low-Cost Lidar Sensor for Mobile Robots

Learning robotic navigation from experience: principles, methods and recent results

Contact Info

Product

Resources

About