Joan Aranda

Control of an ambulatory exoskeleton with a brain-machine interface for spinal cord injury gait rehabilitation

The closed-loop control of rehabilitative technologies by neural commands has shown a great potential to improve motor recovery in patients suffering from paralysis. Brain–machine interfaces (BMI) can be used as a natural control method for such technologies. BMI provides a continuous association between the brain activity and peripheral stimulation, with the potential to induce plastic changes in the nervous system. Paraplegic patients, and especially the ones with incomplete injuries, constitute a potential target population to be rehabilitated with brain-controlled robotic systems, as they may improve their gait function after the reinforcement of their spared intact neural pathways. This paper proposes a closed-loop BMI system to control an ambulatory exoskeleton—without any weight or balance support—for gait rehabilitation of incomplete spinal cord injury (SCI) patients. The integrated system was validated with three healthy subjects, and its viability in a clinical scenario was tested with four SCI patients. Using a cue-guided paradigm, the electroencephalographic signals of the subjects were used to decode their gait intention and to trigger the movements of the exoskeleton. We designed a protocol with a special emphasis on safety, as patients with poor balance were required to stand and walk. We continuously monitored their fatigue and exertion level, and conducted usability and user-satisfaction tests after the experiments. The results show that, for the three healthy subjects, 84.44 ± 14.56% of the trials were correctly decoded. Three out of four patients performed at least one successful BMI session, with an average performance of 77.6 1 ± 14.72%. The shared control strategy implemented (i.e., the exoskeleton could only move during specific periods of time) was effective in preventing unexpected movements during periods in which patients were asked to relax. On average, 55.22 ± 16.69% and 40.45 ± 16.98% of the trials (for healthy subjects and patients, respectively) would have suffered from unexpected activations (i.e., false positives) without the proposed control strategy. All the patients showed low exertion and fatigue levels during the performance of the experiments. This paper constitutes a proof-of-concept study to validate the feasibility of a BMI to control an ambulatory exoskeleton by patients with incomplete paraplegia (i.e., patients with good prognosis for gait rehabilitation).

Visual human machine interface by gestures

Like oral communication, gestures are a natural way to carry out human machine interface. In the early days of robotic systems, human gesture was used to control robot movements by means of a master-slave structure. In spite of the use if robot programming languages, manual control is the most reliable way to carry out complex tasks in unstructured environments. In these situations, a non-contact, passive and remote system can be helpful to control a teleoperated robot by means of human gestures. In this paper, a vision system able to detect, locate and track the head and hands of a human body is presented. The system uses several calibrated cameras placed around the operator scenario to locate the body parts of a person in 3D. The system combines different computer vision techniques to increase the reliability of the body parts detection: image movement detection, user skin colour segmentation and stereo. The data provided by these modules are focused looking for coherence according to the human body dimensions. With the scheme proposed it is possible to obtain a low-cost real-time system for human computer interfacing based in a natural way of communication (gestures). Civil area such as big robots in shipyards, mines, public works or cranes is some possible applications.

Real-time architecture for cable tracking using texture descriptors

We present a texture analysis algorithm based on perceptual features. A specific architecture has been developed in order to implement texture features extraction which is low cast, easy-to-implement and reprogrammable depending on the vision system conditions. We apply our algorithm in detection and tracking of submarine cable where underwater vehicles control requires high speed in visual information treatment.

Image segmentation combining region depth and object features

Object recognition systems need image segmentation processes that relate image regions to world objects. These methods present often three problems: the generation of a large number of small regions, undersegmentation (different objects are associated to the same image region) and oversegmentation (a scene object is segmented in various regions). In order to overcome these problems, we propose an image segmentation method that combines depth information and object surface properties obtained from a pair of stereo images. The system work under the standard assumption that 3D objects have planar faces and regular shapes. First a region growing segmentation process is applied to both images generating two labeled images. Then, depth information of the region frontiers is obtained by matching the labeled segments from left and right image rows. The stereo matching problem is solved by finding a path through a 2D search plane whose axes are the left and right segmented lines. Original image regions are then merged based on their size, surface information and frontiers depth information. In this way, image regions are associated to surfaces that are contiguous in the 3D space and they present a common property (such as gray level, color or texture).

Visual System to Help Blind People to Cross the Street

A system to improve mobility of blind people based on computer vision is presented. It consists of a portable PC endowed with a digital camera and a pair of auriculars. The system is able to detect and to track green and red traffic lights used by the pedestrians without this disability. Colour histogram analysis whereas structural data have been used to recognize these traffic symbols. In order to handle with illumination changes a simple adaptation scheme is proposed. By means of the auriculars, the system inform to the user about semaphore state and also about its pan position in real time.

Tracking capabilities in computer vision for industrial applications

A tracking system has been developed with a compromise between complexity and cost and efficiency in mind. The tracking system consists of a PC fitted with a specific one-card processor designed in our laboratory that acquires the image and implements the recognition algorithm at video rate. We describe the recognition method, the hardware architecture, and some applications and results. The system can be extended to track targets in 3-D using two cameras and two processors. Finally we describe different applications already tested: A robot servo-positioning system in moving parts operation, a tracking system for vehicles for traffic supervision and control, and a tracking system for people for the study of their behavior.

A tracking system for dynamic control of convoys

Abstract An experimental control system for the flexible transport of goods by convoys is described. In this transport system convoys can be built automatically. The goal is that every vehicle attach to or disengage from the convoy when it receives the corresponding order by remote control. Each trailer follows the previous one in the convoy by means of a specific vision module. The vision module consists of a low-cost hardware designed to acquire and binarize the image. The algorithms use this binary image to detect and locate a mark placed on the rear of the preceding trailer. From this information the guidance system defines the trajectory to be tracked and generates the control orders to the steering wheels. The trailers are automated guided vehicles (AGV), each having its own tracking system that does not require any physical contact.

Low cost architecture for structure measure distance computation

Huge and expensive computation resources are usually required to perform graph labelling at high speed. This fact restricts an extensive use of this methodology in industrial applications such as visual inspection. A new systolic architecture is presented which computes structural distances between cliques of different graphs based on a modified incremental Levenshtein distance algorithm. The distances obtained are used as a support function for graph labelling using probabilistic relaxation techniques. The proposed architecture computes the distances between k input cliques of an input graph and one reference clique of a reference graph. It does not limit the number of cliques nor cliques complexity of the input graph, so any input graph can be labelled. A low cost solution has been implemented based on FPGAs.

An interactive robotic system for human assistance in domestic environments

This work introduces an interactive robotic system for assistance, conceived to tackle some of the challenges that domestic environments impose. The system is organized into a network of heterogeneous components that share both physical and logical functions to perform complex tasks. It consists of several robots for object manipulation, an advanced vision system that supplies in-formation about objects in the scene and human activity, and a spatial augmented reality interface that constitutes a comfortable means for interacting with the system. A first analysis based on users’ experiences confirms the importance of having a friendly user interface. The inclusion of context awareness from visual perception enriches this interface allowing the robotic system to become a flexible and proactive assistant.

Recovering Planned Trajectories in Robotic Rehabilitation Therapies under the Effect of Disturbances

Robotic rehabilitation is an emerging technology in the field of Neurorehabilitation, which aims to achieve an effective patient recovery. This research focusses on the control strategy for an assistive exoskeleton aiming to reduce the effects of disturbances on planned trajectories during rehabilitation therapies. Disturbances are mostly caused by muscle synergies or by unpredictable actions produced by functional electrical stimulation. The effect of these disturbances can be either assistive or resistive forces depending on the patients movement, which increase or decrease the speed of the affected joints by forcing the control unit to act consequently. In some therapies, like gait assistance, it is also essential to maintain synchronization between joint movements, to ensure a dynamic stability. A force control approach is used for all the joints individually, while two control methods are defined to act when disturbances are detected: Cartesian position control (Cartesian level) and Variable execution speed (joint level). The trajectory to be followed by the patient is previously recorded using an active exoskeleton, H1, worn by healthy subjects. A realistic simulation model of the exoskeleton is used for testing the effect of disturbances on the particular joints and on the planned trajectory and for evaluating the performance of the two proposed control methods. The performances of the presented methods are evaluated by comparing the resulting trajectories with respect to those planned. The evaluation of the most suitable method is performed considering the following factors: stability, minimum time delay and synchronization of the joints.