Javier Sarria

Combination of RGB and Multispectral Imagery for Discrimination of Cabernet Sauvignon Grapevine Elements

This paper proposes a sequential masking algorithm based on the K-means method that combines RGB and multispectral imagery for discrimination of Cabernet Sauvignon grapevine elements in unstructured natural environments, without placing any screen behind the canopy and without any previous preparation of the vineyard. In this way, image pixels are classified into five clusters corresponding to leaves, stems, branches, fruit and background. A custom-made sensory rig that integrates a CCD camera and a servo-controlled filter wheel has been specially designed and manufactured for the acquisition of images during the experimental stage. The proposed algorithm is extremely simple, efficient, and provides a satisfactory rate of classification success. All these features turn out the proposed algorithm into an appropriate candidate to be employed in numerous tasks of the precision viticulture, such as yield estimation, water and nutrients needs estimation, spraying and harvesting.

High-Resolution Indirect Feet–Ground Interaction Measurement for Hydraulic-Legged Robots

Feet-ground interactions influence the legged robots stability. In this paper, a high-resolution indirect force measurement for hydraulic-legged robots is presented. The use of pressure transducers placed at one or both chambers of the robots double-effect hydraulic actuators is investigated, and conclusions are drawn regarding their capability for indirectly measuring the contact forces between the feet and the ground. Because of the nonlinear dynamic properties of hydraulic cylinders, friction modeling is essential to determine at all times the true forces of each foot against the soil. The test case is called ROBOCLIMBER, which is a bulky quadruped climbing and walking machine able to carry heavy-duty drilling equipment for landslide consolidation and monitoring works. Sensor calibration and signal filtering requirements are also taken into consideration. To end, the overall proposed approach to measure feet-ground interactions is experimentally evaluated.

Multisensory system for fruit harvesting robots. Experimental testing in natural scenarios and with different kinds of crops

The motivation of this research was to explore the feasibility of detecting and locating fruits from different kinds of crops in natural scenarios. To this end, a unique, modular and easily adaptable multisensory system and a set of associated pre-processing algorithms are proposed. The offered multisensory rig combines a high resolution colour camera and a multispectral system for the detection of fruits, as well as for the discrimination of the different elements of the plants, and a Time-Of-Flight (TOF) camera that provides fast acquisition of distances enabling the localisation of the targets in the coordinate space. A controlled lighting system completes the set-up, increasing its flexibility for being used in different working conditions. The pre-processing algorithms designed for the proposed multisensory system include a pixel-based classification algorithm that labels areas of interest that belong to fruits and a registration algorithm that combines the results of the aforementioned classification algorithm with the data provided by the TOF camera for the 3D reconstruction of the desired regions. Several experimental tests have been carried out in outdoors conditions in order to validate the capabilities of the proposed system.

A new manipulator structure for power‐assist devices

Purpose – The purpose of this paper is to introduce a new manipulator structure to configure power‐assist devices in order to protect the operator from suffering musculoskeletal disorders. The mechanical structure and the control system along with their main features are presented.Design/methodology/approach – The new structure was designed under the criterion of minimizing the torques required for handling payloads up to 75 kg as well as to configure a system to be controlled easily.Findings – A new structure based on electrical AC motors and capable of handling high payloads exerting low motor torque is provided.Originality/value – The paper describes how application of the criterion of minimizing the required torques to handle heavy payload produced a new manipulator structure. This structure is patent protected.

Reconfiguration of a Climbing Robot in an All-Terrain Hexapod Robot

This work presents the reconfiguration from a previous climbing robot to an all-terrain robot for applications in outdoor environments. The original robot is a six-legged climbing robot for high payloads. This robot has used special electromagnetic feet in order to support itself on vertical ferromagnetic walls to carry out specific tasks. The reconfigured all-terrain hexapod robot will be able to perform different applications on the ground, for example, as inspection platform for humanitarian demining tasks. In this case, the reconfigured hexapod robot will load a scanning manipulator arm with a specific metal detector as end-effector. With the implementation of the scanning manipulator on the hexapod robot, several tasks about search and localisation of antipersonnel mines would be carried out. The robot legs have a SCARA configuration, which allows low energy consumption when the robot performs trajectories on a quasi-flat terrain.

Validation of a Multisensory System for Fruit Harvesting Robots in Lab Conditions

This paper presents a multisensory system for the detection and localisation of fruits that are candidates to be harvested by a robotic manipulator. The devices that have been selected as primary sensors for this purpose are a high resolution colour camera, a multispectral imaging system that consists of a motorised filter wheel, and a Time-Of-Flight 3D camera. A controlled lighting system completes the set-up. The progressive RGB camera and the multispectral imaging system acquire the basic data inputs for the detection of areas of interest that belong to the fruits, whereas the Time-Of-Flight 3D camera provides fast acquisition of accurate distances enabling the localisation of the targets in the coordinate space. Several experimental tests have been carried out in laboratory conditions in order to evaluate the capabilities of the proposed multisensory system.

Indirect Force Measurement for Hydraulic Walking Robot

Force sensing is an important issue for the control of legged robots. In this paper an indirect force measurement for hydraulic walking robots is presented. The test case is ROBOCLIMBER, a bulky, quadruped climbing and walking machine whose weighty legs enable it to carry out heavy-duty drilling operations. The paper shows how the placement of pressure transducers at both ends of the double effect hydraulic jacks allows measuring indirectly the contact forces between the feet and the ground. Several experiments are carried out to calibrate all sensors within their operational range of interest. Because of dynamic properties of hydraulic cylinders friction modelling is an important task to be carried out in order to determine at all times the true forces of the feet against the soil. After calibration and friction modelling, sensors are subjected to experimental performance evaluation.

Instrumented Scanning Manipulator for Landmines Detection Tasks

This paper presents an instrumented robotic arm for landmines detection tasks during humanitarian demining activities. The manipulator has 5 DOF and it is endowed with a metal detector for landmines detection and a mini-TOF camera for mapping the terrain that has to be scanned. The mini-TOF camera provides a point cloud of the terrain that allows keeping the metal detector at a constant height above the ground and performing an efficient scanning of the contaminated terrain.

High Speed Fragile Object Manipulation

This paper describes the optimization of picking up soft goods moving on a belt conveyor using a high speed manipulator driven by linear motors and equipped with a vacuum gripper structure and a computer vision system. A special gripper with several grasping devices and with a rotational degree of freedom has been designed to cope with object orientation. The vision system determines the location and orientation of the objects in the task space of the robot and the control system is in charge of the correct manipulation of the products. Also, this work presents the development and results of a pastry industrial project, which has a particular emphasis, given its complexity, the Cartesian robot manipulator, which has been designed to optimize the process of handling and palletising in this industrial area.

Automatic Control of a Large Articulated Vehicle

This work presents the development of the automatic control of an articulated bus. It is describes the most relevant concepts of the architecture of perception and actuation implemented on a large wheeled vehicle, Volvo B10M articulated bus of 18.75m in length. In this work, some experimental results of strategies for lateral and longitudinal control of the bus are shown, when it travels on a guide rail through a guiding mechatronics box. Additionally, this article presents the concepts of the guiding rail detection and obstacle detection by means of two Lidar systems for the test lane detection in advance, and for the pedestrians’ safety, respectively. Several experimental results are presented in this manuscript.