In this paper, we propose an approach to learn compact representations from salient landmarks detected by a visual attention algorithm to recognize previously visited places in underwater environments. Instead of using hand-crafted local descriptors as it has been typically done in visual place recognition, we use a convolutional autoencoder to obtain an ad hoc descriptor generator from salient landmarks. The main advantage of using an autoencoder is that it can learn in an unsupervised manner directly from the salient landmarks. In addition, we show that it is possible to do the training with less than 100,000 examples instead of several hundreds of thousands or even millions of labeled examples as in other convolutional architectures. The trained convolutional autoencoder is used to obtain descriptors for salient landmarks that are later utilized in a voting scheme to calculate similarity between images with the objective of finding if a place has already been visited. The proposed method has obtained good results compared to SeqSLAM and FAB-MAP in different datasets obtained from robotic explorations of coral reefs in real life conditions. Moreover, when the visual attention algorithm is used, fewer features are required to get a good performance in terms of precision and recall compared when using the SURF method to extract visual features.

In this paper, we present a method for vision-based place recognition in environments with a high content of similar features and that are prone to variations in illumination. The high similarity of features makes difficult the disambiguation between two different places. The novelty of our method relies on using the Bag of Words (BoW) approach to derive an image descriptor from a set of relevant regions, which are extracted using a visual attention algorithm. We name our approach Bag of Relevant Regions (BoRR). The descriptor of each relevant region is built by using a 2D histogram of the chromatic channels of the CIE-Lab color space. We have compared our results with those using state of the art descriptors that include the BoW and demonstrate that our approach performs better in most of the cases.

For underwater robotics applications involving monitoring and inspection tasks, it is important to capture quality color images in real time. In this paper, we propose a statistically learning method with an automatic selection of the training set for restoring the color of underwater images. Our statistical model is a Markov Random Field with Belief Propagation (MRF-BP). The quality of the results depends strongly on the trained correlations between the degraded image and its corresponding color image. However, it is not possible to have color ground truth data given the inherent conditions of underwater environments. Thus, we build a color adaptive training set by applying a multiple color space analysis to those frames that present a high change in its distribution from the previous frame and use only those frames for training. Experimental results in real underwater video sequences demonstrate that our approach is feasible, even when visibility conditions are poor, as our method can recover and discriminate between different colors in objects that may seem similar to the human eye.

We present a behavioral approach for autonomous robotic exploration of marine habitat with collision avoidance given little or no prior information. In our previous work, a vision-based reactive navigation paradigm with a predefined forward direction allowed an underwater robot to avoid unexpected obstacles. In this work, we have now incorporated visual perceptive invariants to guide the navigation as a human diver would do, thus eliminating the need for a predefined trajectory or exact pose estimation, i.e., we are adding behavioral patterns to turn the navigation into an exploration. Our exploration architecture consists of a tracker of regions of interest and, a collision avoidance behavior. During the exploration, the robot's navigation system is guided towards the most relevant region while continuously checking for free space (water) to navigate. The proposed framework successfully combines both behaviors despite their opposite nature (moving towards a region to explore it while avoiding collisions). We have implemented our approach on an environment-friendly robot, which uses fins instead of propellers to allow for a non-invasive and cautious exploration. Results of sea trials performed at different locations and depths demonstrate the feasibility of our approach.

We present a visual based approach for reactive autonomous navigation of an underwater vehicle. In particular, we are interested in the exploration and continuous monitoring of coral reefs in order to diagnose disease or physical damage. An autonomous underwater vehicle needs to decide in real time the best route while avoiding collisions with fragile marine life and structure. We have opted to use only visual information as input. We have improved the Simple Linear Iterative Cluster algorithm which, together with a simple nearest neighbor classifier, robustly segment and classify objects from water in a fast and efficient way, even in poor visibility conditions. From the resulting classification and the current robot's direction and orientation, the next possible free-collision route can be estimated. This is achieved by grouping together neighboring water superpixels (considered as “regions of interest”). Finally, we use a model-free robust control scheme that allows the robot to autonomously navigate through the free-collision routes obtained in the first step. The experimental results, both in simulations and in practice, show the effectiveness of the proposed navigation system.

We describe recent results obtained with AQUA, a mobile robot capable of swimming, walking and amphibious operation. Designed to rely primarily on visual sensors, the AQUA robot uses vision to navigate underwater using servo-based guidance, and also to obtain high-resolution range scans of its local environment. This paper describes some of the pragmatic and logistic obstacles encountered, and provides an overview of some of the basic capabilities of the vehicle and its associated sensors. Moreover, this paper presents the first ever amphibious transition from walking to swimming.

This paper describes an underwater walking robotic system being developed under the name AQUA, the goals of the AQUA project, the overall hardware and software design, the basic hardware and sensor packages that have been developed, and some initial experiments. The robot is based on the RHex hexapod robot and uses a suite of sensing technologies, primarily based on computer vision and INS, to allow it to navigate and map clear shallow-water environments. The sensor-based navigation and mapping algorithms are based on the use of both artificial floating visual and acoustic landmarks as well as on naturally occurring underwater landmarks and trinocular stereo.

We address the problem of computing dense range maps of indoor locations using only intensity images and partial depth. We allow a mobile robot to navigate the environment, take some pictures and few range data. Our method is based on interpolating the existing range data using statistical inferences learned from the available intensity image and from those (sparse) regions where both range and intensity information is present. The spatial relationships between the variations in intensity and range can be efficiently captured by the neighborhood system of a Markov random field (MRF). In contrast to classical approaches to depth recovery (i.e. stereo, shape from shading), we can afford to make only weak assumptions regarding specific surface geometries or surface reflectance functions since we compute the relationship between existing range data and the images we started with. Experimental results show the feasibility of our method.

This paper examines a novel method we have developed for computing range data in the context of mobile robotics. Our objective is to compute dense range maps of locations in the environment, but to do this using intensity images and very limited range data as input. We develop a statistical learning method for inferring and extrapolating range data from a combination of a single video intensity image and a limited amount of input range data. Our methodology is to compute the relationship between the observed range data and the variations in the intensity image, and use this to extrapolate new range values. These variations can be efficiently captured by the neighborhood system of a Markov random field (MRF) without making any strong assumptions about the kind of surfaces in the world. Experimental results show the feasibility of our method.

In this paper a range synthesis algorithm is proposed as an initial solution to the problem of 3D environment modeling from sparse data. We develop a statistical learning method for inferring and extrapolating range data from as little as one intensity image and from those (sparse) regions where both range and intensity information is available. Our work is related to methods for texture synthesis using Markov Random Field methods. We demonstrate that MRF methods can also be applied to general intensity images with little associated range information and used to estimate range values where needed without making any strong assumptions about the kind of surfaces in the world Experimental results show the feasibility of our method.

A method for object recognition that is invariant under translation, rotation and scaling is addressed. The first step of the method (pre-processing) takes into account the invariant properties of the normalized moment of inertia and a novel coding that extracts topological object characteristics. The second step (recognition) is achieved by using a holographic nearest-neighbor (HHN) algorithm, in which vectors obtained in the pre-processing step are used as inputs to it. The algorithm is tested in character recognition, using the 26 upper-case letters of the alphabet. Only four different orientations and one size (for each letter) were used for training. Recognition was tested with 17 different sizes and 14 rotations. The results are encouraging, since we achieved 98% correct recognition. Tolerance to boundary deformations and random noise was tested. Results for character recognition in "real" images of car plates are presented as well.

In this article a simple performance index for proper manipulator motion planning is presented. This index is derived by establishing a simple upper bound for a standard condition number of the Jacobian matrix. Here the proposed index behaviour is analyzed/tested on a planar redundant manipulator executing tasks under various scenarios.