There's No Place Like Home: Visual Teach and Repeat for Emergency Return of Multirotor UAVs During GPS Failure

Warren, Michael; Greeff, Melissa; Patel, Bhavit; Collier, Jack; Schoellig, Angela P.; Barfoot, Timothy D.

doi:10.1109/lra.2018.2883408

Cited by 42 publications

(25 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually, these methods assume that the first location of the robot is known. The robot is placed at the beginning of the desired visual path to follow it [1,7,8,[11][12][13]. Therefore, they do not use any segment self-localization.…”

Section: Introductionmentioning

confidence: 99%

Two Efficient Visual Methods for Segment Self-localization

2021

View full text Add to dashboard Cite

Localization is an essential step in visual navigation algorithms in robotics. Some visual navigation algorithms define the environment through sequential images, which are called visual path. The interval between each consecutive image is called a segment. One crucial step in these kinds of navigation is to find the segment in which the robot is placed (segment selflocalization). Visual segment self-localization methods consist of two stages. In the first stage, a feature matching between the current image of the robot with all the images that form the visual path is done. Usually, in this stage, outliers removal methods such as RANSAC are used after matching to remove the outliers matched features. In the second stage, a segment is chosen depending on the results of the first one. Segment self-localization methods estimate a segment depending just on the percentage of the matched features. This leads to estimate the segment incorrectly in some cases. In this paper, another parameter also is considered to estimate the segment. The parameter is based on the perspective projection model. Moreover, instead of RANSAC which is a stochastic and time consuming method, a more straightforward and more effective method is proposed for outliers detection. The proposed methods are tested on Karlsruhe dataset, and acceptable results are obtained. Also, the methods are compared with three reviewed methods by Nguyen et al. (J Intell Robot Syst 84:217, 2016). Although the proposed methods use a more straightforward outlier method, they give more accurate results.

show abstract

Section: Introductionmentioning

confidence: 99%

Two Efficient Visual Methods for Segment Self-localization

2021

View full text Add to dashboard Cite

show abstract

“…This has challenged researchers to develop multirotor systems that can move beyond lab demonstrations to real-world scenarios where GPS or motion capture may not always be available. As such, in recent years significant advancements have been made in enabling faster flight using vision-based sensing as a lightweight and versatile alternative [2]- [4]. However, autonomous flight relying on imperfect visual sensing and state estimation drift and noise is still challenging.…”

Section: Introductionmentioning

confidence: 99%

“…The mismatch between the control specifications and visual measurement requires an additional state estimator to determine high-rate state estimates. Traditionally, the controllers and planners are designed independently of the state estimator [2]- [5].…”

Section: Introductionmentioning

confidence: 99%

Fly Out The Window: Exploiting Discrete-Time Flatness for Fast Vision-Based Multirotor Flight

Greeff¹,

Zhou²,

Schoellig³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Current control design for fast vision-based flight tends to rely on high-rate, high-dimensional and perfect state estimation. This is challenging in real-world environments due to imperfect sensing and state estimation drift and noise. In this letter, we present an alternative control design that bypasses the need for a state estimate by exploiting discrete-time flatness. To the best of our knowledge, this is the first work to demonstrate that discrete-time flatness holds for the Euler discretization of multirotor dynamics. This allows us to design a controller using only a window of input and output information. We highlight in simulation how exploiting this property in control design can provide robustness to noisy output measurements (where estimating higher-order derivatives and the full state can be challenging). Fast vision-based navigation requires high performance flight despite possibly noisy high-rate real-time position estimation. In outdoor experiments, we show the application of discrete-time flatness to vision-based flight at speeds up to 10 m/s and how it can outperform controllers that hinge on accurate state estimation.

show abstract

“…Sense and avoid technologies embedded in drone systems have already provided a great deal of safety on drone uses [11], even though these technologies are still needed to be improved significantly [12], [13]. Motlagh et al [14] addressed the regulations and standardization efforts, and public safety concerns on the ground.…”

Section: Introductionmentioning

confidence: 99%

Analysis and Optimization of Unmanned Aerial Vehicle Swarms in Logistics: An Intelligent Delivery Platform

et al. 2019

View full text Add to dashboard Cite

Deploying unmanned aerial vehicle (UAV) swarms in delivery systems are still in its infancy with regard to the technology, safety, and aviation rules and regulations. Optimal use of UAVs in dynamic environments is important in many aspects, e.g., increasing efficacy and reducing the air traffic, resulting in a safer environment, and it requires new techniques and robust approaches based on the capabilities of UAVs and constraints. This paper analyzes several delivery schemes within a platform, such as delivery with and without using air highways and delivery using a hybrid scheme along with several delivery methods (i.e., optimal, premium, and first-in first-out) to explore the use of UAV swarms as part of the logistics operations. In this platform, a dimension reduction technique, ''dynamic multiple assignments in multidimensional space,'' and several other new techniques along with Hungarian and cross-entropy Monte Carlo techniques are forged together to assign tasks and plan 3D routes dynamically. This particular approach is performed in such a way that UAV swarms in several warehouses are deployed optimally given the delivery scheme, method, and constraints. Several scenarios are tested on the simulator using small and big data sets. The results show that the distribution and the characteristics of data sets and constraints affect the decision on choosing the optimal delivery scheme and the method. The findings are expected to guide the aviation authorities in their decisions before dictating rules and regulations regarding effective, efficient, and safe use of UAVs. Furthermore, the companies that produce UAVs are going to take the demonstrated results into account for their functional design of UAVs along with other companies that aim to deliver their products using UAVs. Additionally, private industries, logistics operators, and municipalities are expected to benefit from the potential adoption of the simulator in strategic decisions before embarking on the practical implementation of UAV delivery systems.

show abstract

There's No Place Like Home: Visual Teach and Repeat for Emergency Return of Multirotor UAVs During GPS Failure

Cited by 42 publications

References 26 publications

Two Efficient Visual Methods for Segment Self-localization

Two Efficient Visual Methods for Segment Self-localization

Fly Out The Window: Exploiting Discrete-Time Flatness for Fast Vision-Based Multirotor Flight

Analysis and Optimization of Unmanned Aerial Vehicle Swarms in Logistics: An Intelligent Delivery Platform

Contact Info

Product

Resources

About