Marco Antonio Gutiérrez

Multi-robot collaborative platforms for humanitarian relief actions

In this paper we describe the main components and technical challenges required for the implementation of a multi-robot collaboration platform towards supporting humanitarian relief actions. The platform supports collaborative work between a fleet of UAVs, mobile stations and light-weight fast-speed robots. The platform can be used on both land or marine environments allowing a wide diversity of rescue, surveillance and relief operations. The paper presents the entire robotic system of the platform along with some mobile station-base collaborative tasks, inter UAVs and fast-speed mobile platform collaboration. Finally, we present potential application scenarios where these platforms can be deployed.

Simultaneous planning and mapping (SPAM) for a manipulator by best next move in unknown environments

In this paper, we propose a SPAM (Simultaneous Planning and Mapping) technique for a manipulator type robot working in an uncertain environment via a Best Next Move algorithm. Demands for a smart decision to move a manipulator such as humanoid arms in uncertain or crowded environments call for a simultaneous planning and mapping technique. We assume no a priori knowledge of either the obstacles or the rest of the environment exits. For rapid map building and path planning, we use a skin type setup based on 3D depth camera sensors that completely encompass the entire body of a manipulator. The 3D sensors capture the point clouds used to create an instantaneous c-space map whereby a Best Next Move algorithm directs the motion of the manipulator. The Best Next Move algorithm utilizes the gradient of the density distribution of the k-nearest-neighborhood sets in c-space. It has tendency to travel along the direction by which the point clouds spread in space, thus rendering faster mapping of c-space obstacles. The proposed algorithm is compared with several sensor based algorithms for performance measurement such as map completion rate, distribution of samples, total nodes, etc. Some improved performances are reported for the proposed algorithm. Several possible applications include semi-autonomous tele-robotics planning, humanoid arm path planning, among others.

Integrating planning perception and action for informed object search

This paper presents a method to reduce the time spent by a robot with cognitive abilities when looking for objects in unknown locations. It describes how machine learning techniques can be used to decide which places should be inspected first, based on images that the robot acquires passively. The proposal is composed of two concurrent processes. The first one uses the aforementioned images to generate a description of the types of objects found in each object container seen by the robot. This is done passively, regardless of the task being performed. The containers can be tables, boxes, shelves or any other kind of container of known shape whose contents can be seen from a distance. The second process uses the previously computed estimation of the contents of the containers to decide which is the most likely container having the object to be found. This second process is deliberative and takes place only when the robot needs to find an object, whether because it is explicitly asked to locate one or because it is needed as a step to fulfil the mission of the robot. Upon failure to guess the right container, the robot can continue making guesses until the object is found. Guesses are made based on the semantic distance between the object to find and the description of the types of the objects found in each object container. The paper provides quantitative results comparing the efficiency of the proposed method and two base approaches.

A Passive Learning Sensor Architecture for Multimodal Image Labeling: An Application for Social Robots

Object detection and classification have countless applications in human–robot interacting systems. It is a necessary skill for autonomous robots that perform tasks in household scenarios. Despite the great advances in deep learning and computer vision, social robots performing non-trivial tasks usually spend most of their time finding and modeling objects. Working in real scenarios means dealing with constant environment changes and relatively low-quality sensor data due to the distance at which objects are often found. Ambient intelligence systems equipped with different sensors can also benefit from the ability to find objects, enabling them to inform humans about their location. For these applications to succeed, systems need to detect the objects that may potentially contain other objects, working with relatively low-resolution sensor data. A passive learning architecture for sensors has been designed in order to take advantage of multimodal information, obtained using an RGB-D camera and trained semantic language models. The main contribution of the architecture lies in the improvement of the performance of the sensor under conditions of low resolution and high light variations using a combination of image labeling and word semantics. The tests performed on each of the stages of the architecture compare this solution with current research labeling techniques for the application of an autonomous social robot working in an apartment. The results obtained demonstrate that the proposed sensor architecture outperforms state-of-the-art approaches.

A Multimodal Control Architecture for Autonomous Unmanned Aerial Vehicles

We present our preliminary work on a multimodal control architecture that enables an operator to manage an autonomous Unmanned Aerial Vehicle (UAV) through high level tasks in an indoors environment. The intelligence embedded in our architecture is able to decode these tasks into low level instructions that a UAV is able to execute. Our system allows the user to operate the UAV through speech, text or keyboard/mouse input, all presented in a web based graphical user interface that can be accessed from any Internet powered device.