Experimental Results for Over-the-Horizon Planetary Exploration Using a LIDAR Sensor

Rekleitis, Ioannis; Bedwani, Jean-Luc; Gingras, David R.; Dupuis, Érick

doi:10.1007/978-3-642-00196-3_9

Cited by 13 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The computation time was on average 14 seconds for the destinations at five meters, and 25 seconds for ten meters. The proposed planning method was very efficient, the paths were computed in seconds using ITMs with several thousand triangles, and the computed paths were on average 25% longer than a straight line between start and destination [19]. As noted earlier, a path was always found if a feasible path, for a given cost function, existed.…”

Section: Overviewmentioning

confidence: 95%

See 1 more Smart Citation

Autonomous planetary exploration using LIDAR data

Rekleitis

Bedwani

Dupuis

2009

2009 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-In this paper we present the approach for autonomous planetary exploration developed at the Canadian Space Agency. The goal of this work is to autonomously navigate to remote locations, well beyond the sensing horizon of the rover, with minimal interaction with a human operator. We employ LIDAR range sensors due to their accuracy, long range and robustness in the harsh lighting conditions of space. Irregular Triangular Meshes (ITMs) are used for representing the environment providing an accurate yet compact spatial representation. In this paper a novel path-planning technique through the ITM is introduced, which guides the rover through flatter terrain and safely away from obstacles. Experiments performed in CSA's Mars emulation terrain that validate our approach are also presented. I. INTRODUCTIONMobile robotics has enabled scientific breakthroughs in planetary exploration [1]. Recent accomplishments have demonstrated beyond doubt the necessity and feasibility of semi-autonomous rovers for conducting scientific exploration on other planets. Both Mars Exploration Rovers (MERs) "Spirit" and "Opportunity" have the ability to detect and avoid obstacles, picking a path that would take them along a safe trajectory. MER's have reached traverses of 300m/sol. On occasion, the rovers have had to travel to locations that were at the fringe of the horizon of their sensors or even slightly beyond.The next rover missions to Mars are the "Mars Science Laboratory" (MSL) [2] and ESA's ExoMars [3]. Both of these missions have set target traverse distances on the order of one kilometer per day. Both the MSL and ExoMars rovers are therefore expected to drive regularly a significant distance beyond the horizon of their environment sensors. Earthbased operators will therefore not know a-priori the detailed geometry of the environment and will thus not be able to select via-points for the rovers throughout their traverses.One of the key technologies that will be required is the ability to sense and model the 3D environment in which the rover has to navigate. To address the above mentioned issues, the Canadian Space Agency is developing a suite of technologies for long-range rover navigation. For the purposes of this paper, "long-range" is defined as a traverse that takes the rover beyond the horizon of the rover's environment sensors.In the next Section we discuss the state-of-the-art in robotic planetary exploration. Section II presents the overall process for planetary exploration together with a short description of our test-bed. Next we present a summary of our approach to environmental modelling, Section IV

show abstract

Section: Overviewmentioning

confidence: 95%

“…Each scan contains 111,000 (SICK based LIDAR) or 31,200 (ILRIS 3D) points on average depending on the sensor. The employment of ITMs for terrain modelling maintained the high levels of accuracy while at the same time reducing the data volume by 90%-95% [19].…”

Section: Overviewmentioning

confidence: 99%

Autonomous planetary exploration using LIDAR data

Rekleitis

Bedwani

Dupuis

2009

2009 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…TINs are able to more easily capture sudden elevation changes and are also more flexible and efficient than grid maps in relatively flat areas. In robotics, TINs have been used extensively; see Leal, Scheding, and Dissanayake (2001) and Rekleitis, Bedwani, Gingras, and Dupuis (2008). Leal et al (2001) present an approach to performing online 3D multiresolution reconstruction of unknown and unstructured environments to yield a stochastic representation of space.…”

Section: Introductionmentioning

confidence: 99%

“…Leal et al (2001) present an approach to performing online 3D multiresolution reconstruction of unknown and unstructured environments to yield a stochastic representation of space. Recent work in the space exploration domain presents a LIDAR-based approach to terrain modeling using TINs (Rekleitis et al, 2008). This work decimates coplanar triangles into a single triangle to provide a more compact representation.…”

Section: Introductionmentioning

confidence: 99%

Gaussian process modeling of large‐scale terrain

Vasudevan

Ramos

Nettleton

et al. 2009

Journal of Field Robotics

156

View full text Add to dashboard Cite

Building a model of large-scale terrain that can adequately handle uncertainty and incompleteness in a statistically sound way is a challenging problem. This work proposes the use of Gaussian processes as models of large-scale terrain. The proposed model naturally provides a multiresolution representation of space, incorporates and handles uncertainties aptly, and copes with incompleteness of sensory information. Gaussian process regression techniques are applied to estimate and interpolate (to fill gaps in occluded areas) elevation information across the field. The estimates obtained are the best linear unbiased estimates for the data under consideration. A single nonstationary (neural network) Gaussian process is shown to be powerful enough to model large and complex terrain, effectively handling issues relating to discontinuous data. A local approximation method based on a "moving window" methodology and implemented using k-dimensional (KD)-trees is also proposed. This enables the approach to handle extremely large data sets, thereby completely addressing its scalability issues. Experiments are performed on large-scale data sets taken from real mining applications. These data sets include sparse mine planning data, which are representative of a global positioning system-based survey, as well as dense laser scanner data taken at different mine sites. Further, extensive statistical performance evaluation and benchmarking of the technique has been performed through cross-validation experiments. They conclude that for dense and/or flat data, the proposed approach will perform very competitively with grid-based approaches using standard interpolation techniques and triangulated irregular networks using triangle-based interpolation techniques; for sparse and/or complex data, however, it would significantly outperform them. C 2009 Wiley Periodicals, Inc.

show abstract

“…Over the years, these drawbacks have been partially addressed in several ways, such as scalability and fast inference (Jordan and Zell, 2017), or in works such as those by Lacroix et al (2002) and Frankhauser et al (2014), that attempt to incorporate uncertainty estimates in the EM model. TINs (Rekleitis et al, 2008), on the other hand, sample a set of points that capture important aspects of the observed terrain surface, which are then connected to their nearest neighbors to produce a triangular network model. While better able to capture sudden elevation changes and more efficient when dealing with flat areas, TINs struggle with dense sensor data (Triebel et al, 2006), due to the huge memory footprint produced by highly textured surfaces, and are still unable to formally incorporate spatial dependencies and measurement uncertainty.…”

Section: Introductionmentioning

confidence: 99%

Variational Hilbert regression for terrain modeling and trajectory optimization

Guizilini

Ramos

2019

The International Journal of Robotics Research

View full text Add to dashboard Cite

The ability to generate accurate terrain models is of key importance in a wide variety of robotics tasks, ranging from path planning and trajectory optimization to environment exploration and mining applications. This paper introduces a novel regression methodology for terrain modeling that can approximate arbitrarily complex functions based on a series of simple kernel calculations, using variational Bayesian inference. A sparse feature vector is used to efficiently project input points into a high-dimensional reproducing kernel Hilbert space, according to a set of inducing points automatically generated from clustering available data. Each inducing point maintains its own regression model in addition to individual kernel parameters, and the entire set is iteratively optimized as more data are collected in order to maximize a global variational lower bound. We also show how kernel and regression model parameters can be jointly learned, to achieve a better approximation of the underlying function. Experimental results show that the proposed methodology consistently outperforms current state-of-the-art techniques, while producing a continuous model with a fully probabilistic treatment of uncertainties, well-defined gradients, and highly scalable to large-scale datasets. As a practical application of the proposed terrain modeling technique, we explore the problem of trajectory optimization, deriving gradients that allow the efficient generation of continuous paths using standard optimization algorithms, minimizing a series of useful properties (i.e. distance traveled, changes in elevation, and terrain variance).

show abstract

Experimental Results for Over-the-Horizon Planetary Exploration Using a LIDAR Sensor

Cited by 13 publications

References 25 publications

Autonomous planetary exploration using LIDAR data

Autonomous planetary exploration using LIDAR data

Gaussian process modeling of large‐scale terrain

Variational Hilbert regression for terrain modeling and trajectory optimization

Contact Info

Product

Resources

About