Integrating Sensor Models in Deep Learning Boosts Performance: Application to Monocular Depth Estimation in Warehouse Automation

Yoneyama, Ryota; Durán, Ángel; Pobil, Ángel P. del

doi:10.3390/s21041437

Cited by 5 publications

(2 citation statements)

References 36 publications

(64 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One can see that most drones (94.44%) applied for warehouse management were lighter than tactical drones. The high utilization of UAVs that are lighter than 150 Kilograms largely depends on the fundamental characteristics of warehouse management related to indoor operations and confined spaces [31]. Regarding these characteristics, the heavier drones (tactical drone and strike drone) are not suited for most warehouse management activities, except intra-company delivery between long-distance outdoor warehouses (e.g., [32]).…”

Section: Rq1: "What Are the Past Applications Of Uavs In Warehouse Ma...mentioning

confidence: 99%

Implementation and Critical Factors of Unmanned Aerial Vehicle (UAV) in Warehouse Management: A Systematic Literature Review

Malang

Charoenkwan

Wudhikarn

2023

Drones

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) have proven to be a key solution for nearly automated or smart warehouse operations, enabling receiving, picking, storage, and shipping processes to be timely and more efficient. However, there is a relative scarcity of review studies specifically on UAV-based warehouse management. Research knowledge and insights on UAV applications in this field are also limited and could not sufficiently or practically support decision-making on commercial utilization. To leverage the potential applications and current situation of UAVs, this study provides a systematic literature review (SLR) on UAV adoption in warehouse management. SLR approach was critically conducted to identify, select, assess, and summarize findings, mainly on the two descriptive research questions; what are the past applications of UAV, and what are critical factors affecting UAV adoption in warehouse management? Five key critical factors and 13 sub-factors could be observed. The results revealed that hardware (e.g., payloads, battery power, and sensors) and software factors (e.g., scheduling, path planning, localization, and navigation algorithms) are the most influential factors impacting drone adoption in warehouse management. The managerial implications of our research findings that guide decision-makers or practitioners to effectively employ UAV-based warehouse management in good practice are also discussed.

show abstract

Section: Rq1: "What Are the Past Applications Of Uavs In Warehouse Ma...mentioning

confidence: 99%

Implementation and Critical Factors of Unmanned Aerial Vehicle (UAV) in Warehouse Management: A Systematic Literature Review

Malang

Charoenkwan

Wudhikarn

2023

Drones

View full text Add to dashboard Cite

show abstract

“…Finally, another approach also uses features but instead of a 3D sensor, it relies on the supervised deep learning of 2D RGB images [13]; as is common for deep learning, this method requires both a large dataset and a long training time. A proposal to alleviate this last drawback has been recently put forward for a related problem in warehouse automation [14].…”

Section: Introductionmentioning

confidence: 99%

A Practical Approach for Picking Items in an Online Shopping Warehouse

et al. 2021

Self Cite

View full text Add to dashboard Cite

Commercially viable automated picking in unstructured environments by a robot arm remains a difficult challenge. The problem of robot grasp planning has long been around but the existing solutions tend to be limited when it comes to deploy them in open-ended realistic scenarios. Practical picking systems are called for that can handle the different properties of the objects to be manipulated, as well as the problems arising from occlusions and constrained accessibility. This paper presents a practical solution to the problem of robot picking in an online shopping warehouse by means of a novel approach that integrates a carefully selected method with a new strategy, the centroid normal approach (CNA), on a cost-effective dual-arm robotic system with two grippers specifically designed for this purpose: a two-finger gripper and a vacuum gripper. Objects identified in the scene point cloud are matched to the grasping techniques and grippers to maximize success. Extensive experimentation provides clues as to what are the reasons for success and failure. We chose as benchmark the scenario proposed by the 2017 Amazon Robotics Challenge, since it represents a realistic description of a retail shopping warehouse case; it includes many challenging constraints, such as a wide variety of different product items with a diversity of properties, which are also presented with restricted visibility and accessibility.

show abstract

Bayesian cue integration of structure from motion and CNN-based monocular depth estimation for autonomous robot navigation

Mumuni

2022

Int J Intell Robot Appl

View full text Add to dashboard Cite

In recent years, monocular depth estimation (MDE) has witnessed a substantial performance improvement due to convolutional neural networks (CNNs). However, CNNs are vulnerable to adversarial attacks, which pose serious concerns for safety-critical and security-sensitive systems. Specifically, adversarial attacks can have catastrophic impact on MDE given its importance for scene understanding in applications like autonomous driving and robotic navigation. To physically assess the vulnerability of CNN-based depth prediction methods, recent work tries to design adversarial patches against MDE. However, these methods are not powerful enough to fully fool the vision system in a systemically threatening manner. In fact, their impact is partial and locally limited; they mislead the depth prediction of only the overlapping region with the input image regardless of the target object size, shape and location. In this paper, we investigate MDE vulnerability to adversarial patches in a more comprehensive manner. We propose a novel adaptive adversarial patch (APARATE 1 ) that is able to selectively jeopardize MDE by either corrupting the estimated distance, or simply manifesting an object as disappeared for the autonomous system. Specifically, APARATE is optimized to be shape and scale-aware, and its impact adapts to the target object instead of being limited to the immediate neighborhood. Our proposed patch achieves more than 14 meters mean depth estimation error, with 99% of the target region being affected. We believe this work highlights the threat of adversarial attacks in the context of MDE, and we hope it would alert the community to the real-life potential harm of this attack and motivate investigating more robust and adaptive defenses for autonomous robots.

show abstract

Integrating Sensor Models in Deep Learning Boosts Performance: Application to Monocular Depth Estimation in Warehouse Automation

Cited by 5 publications

References 36 publications

Implementation and Critical Factors of Unmanned Aerial Vehicle (UAV) in Warehouse Management: A Systematic Literature Review

Implementation and Critical Factors of Unmanned Aerial Vehicle (UAV) in Warehouse Management: A Systematic Literature Review

A Practical Approach for Picking Items in an Online Shopping Warehouse

Bayesian cue integration of structure from motion and CNN-based monocular depth estimation for autonomous robot navigation

Contact Info

Product

Resources

About