Feature-rich path planning for robust navigation of MAVs with Mono-SLAM

Sadat, Seyed Abbas; Chutskoff, Kyle; Jungić, Damir; Wawerla, Jens; Vaughan, Richard

doi:10.1109/icra.2014.6907420

Cited by 47 publications

(36 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [Mu et al, 2015, Mu et al, 2016, Mu et al, 2017, the map is summarized into high-priority features by actively selecting the most informative measurements. In [Sadat et al, 2014], a variation of RRT is developed to plan a trajectory that maximizes the number of observed features. Similarly, [Costante et al, 2018] also developed a variation of RRT but instead consider the photometric information (i.e., texture) and geometry to estimate localization uncertainty.…”

Section: Active Perceptionmentioning

confidence: 99%

Perception‐aware autonomous mast motion planning for planetary exploration rovers

Strader

Otsu

Agha–mohammadi

2019

Journal of Field Robotics

View full text Add to dashboard Cite

Highly accurate real-time localization is of fundamental importance for the safety and efficiency of planetary rovers exploring the surface of Mars. Mars rover operations rely on vision-based systems to avoid hazards as well as plan safe routes. However, vision-based systems operate on the assumption that sufficient visual texture is visible in the scene. This poses a challenge for vision-based navigation on Mars where regions lacking visual texture are prevalent. To overcome this, we make use of the ability of the rover to actively steer the visual sensor to improve fault tolerance and maximize the perception performance. This paper answers the question of where and when to look by presenting a method for predicting the sensor trajectory that maximizes the localization performance of the rover. This is accomplished by an online assessment of possible trajectories using synthetic, future camera views created from previous observations of the scene. The proposed trajectories are quantified and chosen based on the expected localization performance. In this work, we validate the proposed method in field experiments at the Jet Propulsion Laboratory (JPL) Mars Yard. Furthermore, multiple performance metrics are identified and evaluated for reducing the overall runtime of the algorithm. We show how actively steering the perception system increases the localization accuracy compared to traditional fixed-sensor configurations.

show abstract

Section: Active Perceptionmentioning

confidence: 99%

Perception‐aware autonomous mast motion planning for planetary exploration rovers

Strader

Otsu

Agha–mohammadi

2019

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…Many other techniques have been used for exploration with MAVs, for example the work of Mostegel et al (2014), who focus more on localization stability rather than reconstruction, or the one by Sadat et al (2014), whose path planning algorithm focus on maximizing feature richness. A particularly interesting approach is the one by Forster et al (2014), which computes, similarly to us, the path by maximizing the information gain over a set of candidate trajectories, but in contrast to us, considers the texture of the explored surface.…”

Section: Related Workmentioning

confidence: 99%

Information-Driven Autonomous Exploration for a Vision-Based Mav

Palazzolo

Stachniss

2017

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Most micro aerial vehicles (MAV) are flown manually by a pilot. When it comes to autonomous exploration for MAVs equipped with cameras, we need a good exploration strategy for covering an unknown 3D environment in order to build an accurate map of the scene. In particular, the robot must select appropriate viewpoints to acquire informative measurements. In this paper, we present an approach that computes in real-time a smooth flight path with the exploration of a 3D environment using a vision-based MAV. We assume to know a bounding box of the object or building to explore and our approach iteratively computes the next best viewpoints using a utility function that considers the expected information gain of new measurements, the distance between viewpoints, and the smoothness of the flight trajectories. In addition, the algorithm takes into account the elapsed time of the exploration run to safely land the MAV at its starting point after a user specified time. We implemented our algorithm and our experiments suggest that it allows for a precise reconstruction of the 3D environment while guiding the robot smoothly through the scene.

show abstract

“…Hoppe et al [10] create a full network of poses for an Unmanned Aerial Vehicle (UAV), but assumes prior knowledge of the environment. Sadat et al [21] and Mostegel et al [18] plan optimal paths for a monocular Visual Odometry (VO) system, but require a set endpoint. Uniquely, we propose a unified approach that can balance the two competing objectives of exploration and refinement by probing the current estimate of geometry using raycasting and a voxel based representation.…”

Section: Next-best View (Nbv) Estimationmentioning

confidence: 99%

Next-Best Stereo: Extending Next-Best View Optimisation For Collaborative Sensors

Maldonado¹,

Hadfield²,

Pugeault³

et al. 2016

Procedings of the British Machine Vision Conference 2016

View full text Add to dashboard Cite

Most 3D reconstruction approaches passively optimise over all data, exhaustively matching pairs, rather than actively selecting data to process. This is costly both in terms of time and computer resources, and quickly becomes intractable for large datasets.This work proposes an approach to intelligently filter large amounts of data for 3D reconstructions of unknown scenes using monocular cameras. Our contributions are twofold: First, we present a novel approach to efficiently optimise the Next-Best View (NBV) in terms of accuracy and coverage using partial scene geometry. Second, we extend this to intelligently selecting stereo pairs by jointly optimising the baseline and vergence to find the NBV's best stereo pair to perform reconstruction. Both contributions are extremely efficient, taking 0.8ms and 0.3ms per pose, respectively.Experimental evaluation shows that the proposed method allows efficient selection of stereo pairs for reconstruction, such that a dense model can be obtained with only a small number of images. Once a complete model has been obtained, the remaining computational budget is used to intelligently refine areas of uncertainty, achieving results comparable to state-of-the-art batch approaches on the Middlebury dataset, using as little as 3.8% of the views.

show abstract

Feature-rich path planning for robust navigation of MAVs with Mono-SLAM

Cited by 47 publications

References 15 publications

Perception‐aware autonomous mast motion planning for planetary exploration rovers

Perception‐aware autonomous mast motion planning for planetary exploration rovers

Information-Driven Autonomous Exploration for a Vision-Based Mav

Next-Best Stereo: Extending Next-Best View Optimisation For Collaborative Sensors

Contact Info

Product

Resources

About